chore: release v1.85.0

- Browser strategy: headless first with automatic retry in visible Chrome on failure
- New --browser auto|headless|headed flag with --headless/--headed shortcuts
- Content cleaner module for HTML preprocessing (remove ads, base64 images, scripts)
- Media localizer now handles base64 data URIs alongside remote URLs
- Capture finalUrl from browser to track redirects for output path
- Agent quality gate documentation for post-capture validation
- Upgrade defuddle ^0.12.0 → ^0.14.0
- Add unit tests for content-cleaner, html-to-markdown, legacy-converter, media-localizer

.claude-plugin/marketplace.json

@@ -6,48 +6,34 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.74.1"
+    "version": "1.85.0"
   },
   "plugins": [
     {
-      "name": "content-skills",
-      "description": "Content generation and publishing skills",
+      "name": "baoyu-skills",
+      "description": "Content generation, AI backends, and utility tools for daily work efficiency",
       "source": "./",
       "strict": true,
       "skills": [
-        "./skills/baoyu-xhs-images",
-        "./skills/baoyu-post-to-x",
-        "./skills/baoyu-post-to-wechat",
-        "./skills/baoyu-post-to-weibo",
         "./skills/baoyu-article-illustrator",
-        "./skills/baoyu-cover-image",
-        "./skills/baoyu-slide-deck",
         "./skills/baoyu-comic",
-        "./skills/baoyu-infographic"
-      ]
-    },
-    {
-      "name": "ai-generation-skills",
-      "description": "AI-powered generation backends",
-      "source": "./",
-      "strict": true,
-      "skills": [
-        "./skills/baoyu-danger-gemini-web",
-        "./skills/baoyu-image-gen"
-      ]
-    },
-    {
-      "name": "utility-skills",
-      "description": "Utility tools for content processing",
-      "source": "./",
-      "strict": true,
-      "skills": [
-        "./skills/baoyu-danger-x-to-markdown",
         "./skills/baoyu-compress-image",
-        "./skills/baoyu-url-to-markdown",
+        "./skills/baoyu-cover-image",
+        "./skills/baoyu-danger-gemini-web",
+        "./skills/baoyu-danger-x-to-markdown",
         "./skills/baoyu-format-markdown",
+        "./skills/baoyu-image-gen",
+        "./skills/baoyu-imagine",
+        "./skills/baoyu-infographic",
         "./skills/baoyu-markdown-to-html",
-        "./skills/baoyu-translate"
+        "./skills/baoyu-post-to-weibo",
+        "./skills/baoyu-post-to-wechat",
+        "./skills/baoyu-post-to-x",
+        "./skills/baoyu-slide-deck",
+        "./skills/baoyu-translate",
+        "./skills/baoyu-url-to-markdown",
+        "./skills/baoyu-xhs-images",
+        "./skills/baoyu-youtube-transcript"
       ]
     }
   ]

.gitignore

@@ -166,3 +166,4 @@ posts/
 .clawdhub/
 .release-artifacts/
 .worktrees/
+youtube-transcript/

CHANGELOG.md

@@ -2,6 +2,116 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.85.0 - 2026-03-25
+
+### Features
+- `baoyu-imagine`: auto-migrate legacy `baoyu-image-gen` EXTEND.md config path at runtime
+- Add `baoyu-image-gen` deprecation redirect skill to guide users to install `baoyu-imagine` and remove the old skill
+
+## 1.84.0 - 2026-03-25
+
+### Features
+- Rename `baoyu-image-gen` skill to `baoyu-imagine` — shorter command name, all references updated across docs, configs, and dependent skills
+
+## 1.83.0 - 2026-03-25
+
+### Features
+- `baoyu-image-gen`: add MiniMax provider (`image-01` / `image-01-live`) with subject_reference for character/portrait consistency, custom sizes, and aspect ratio support
+
+## 1.82.0 - 2026-03-24
+
+### Features
+- `baoyu-url-to-markdown`: add browser fallback strategy — headless first, automatic retry in visible Chrome on technical failure; new `--browser auto|headless|headed` flag with `--headless`/`--headed` shortcuts
+- `baoyu-url-to-markdown`: add content cleaner module for HTML preprocessing before extraction (remove ads, base64 images, scripts, styles)
+- `baoyu-url-to-markdown`: support base64 data URI images in media localizer alongside remote URLs
+- `baoyu-url-to-markdown`: capture final URL from browser to track redirects for output path generation
+- `baoyu-url-to-markdown`: add agent quality gate documentation for post-capture content validation
+
+### Dependencies
+- `baoyu-url-to-markdown`: upgrade defuddle ^0.12.0 → ^0.14.0
+
+### Tests
+- `baoyu-url-to-markdown`: add unit tests for content-cleaner, html-to-markdown, legacy-converter, media-localizer
+
+## 1.81.0 - 2026-03-24
+
+### Features
+- `baoyu-youtube-transcript`: add yt-dlp fallback when YouTube blocks direct InnerTube API, with alternate client identity retry and cookie support via `YOUTUBE_TRANSCRIPT_COOKIES_FROM_BROWSER` env var
+
+### Refactor
+- `baoyu-youtube-transcript`: split monolithic script into typed modules (youtube, transcript, storage, shared, types) and add unit tests
+
+## 1.80.1 - 2026-03-24
+
+### Fixes
+- `baoyu-image-gen`: use correct `prompt` field name for Jimeng API request
+
+## 1.80.0 - 2026-03-24
+
+### Features
+- `baoyu-image-gen`: add Azure OpenAI as independent image generation provider with flexible endpoint parsing, deployment-name resolution, quality mapping, and reference image validation
+
+## 1.79.2 - 2026-03-23
+
+### Fixes
+- `baoyu-cover-image`: simplify reference image handling — use `--ref` when model supports it, only create description files for models without reference image support
+- `baoyu-post-to-weibo`: add no-theme rule for article markdown-to-HTML conversion
+
+### Tests
+- Fix Node-compatible parser tests and add parser test dependencies
+
+## 1.79.1 - 2026-03-23
+
+### Fixes
+- Consolidate to single plugin to prevent duplicate skill registration (by @TyrealQ)
+- `baoyu-article-illustrator`: remove opacity parameter from watermark prompt
+- `baoyu-comic`: fix Doraemon naming spacing and remove opacity from watermark prompt
+- `baoyu-xhs-images`: remove opacity from watermark prompt and fix CJK spacing
+
+### Documentation
+- Update project documentation to reflect single-plugin architecture
+
+## 1.79.0 - 2026-03-22
+
+### Features
+- `baoyu-post-to-wechat`: improve credential loading with multi-source resolution, priority ordering, and diagnostics for skipped incomplete sources
+
+## 1.78.0 - 2026-03-22
+
+### Features
+- `baoyu-url-to-markdown`: add URL-specific parser layer for X/Twitter and archive.ph sites
+- `baoyu-url-to-markdown`: improved slug generation with stop words removal and subdirectory output structure
+
+### Fixes
+- `baoyu-url-to-markdown`: preserve anchor elements containing media in legacy converter
+- `baoyu-url-to-markdown`: smarter title deduplication to avoid redundant headings
+
+## 1.77.0 - 2026-03-22
+
+### Features
+- `baoyu-youtube-transcript`: add end times to chapter data (by @jzOcb)
+
+### Fixes
+- `sync-clawhub`: skip failed skills instead of aborting
+
+## 1.76.1 - 2026-03-21
+
+### Documentation
+- `baoyu-youtube-transcript`: fix zsh glob issue — always single-quote YouTube URLs when running the script
+
+## 1.76.0 - 2026-03-21
+
+### Features
+- `baoyu-youtube-transcript`: add title heading, description summary, and cover image to markdown output
+
+### Fixes
+- `baoyu-markdown-to-html`: use process.execPath and tsx import in test runner
+
+## 1.75.0 - 2026-03-21
+
+### Features
+- `baoyu-youtube-transcript`: new skill — download YouTube video transcripts/subtitles and cover images with multi-language, chapters, and speaker identification support
+
 ## 1.74.1 - 2026-03-21
 
 ### Fixes

CHANGELOG.zh.md

@@ -2,6 +2,116 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.85.0 - 2026-03-25
+
+### 新功能
+- `baoyu-imagine`：运行时自动迁移旧版 `baoyu-image-gen` 的 EXTEND.md 配置路径
+- 新增 `baoyu-image-gen` 废弃重定向技能，引导用户安装 `baoyu-imagine` 并移除旧技能
+
+## 1.84.0 - 2026-03-25
+
+### 新功能
+- 将 `baoyu-image-gen` 技能重命名为 `baoyu-imagine` — 更简短的命令名，所有文档、配置和依赖技能中的引用已同步更新
+
+## 1.83.0 - 2026-03-25
+
+### 新功能
+- `baoyu-image-gen`：新增 MiniMax 服务商（`image-01` / `image-01-live`），支持 subject_reference 角色/肖像一致性、自定义尺寸和宽高比
+
+## 1.82.0 - 2026-03-24
+
+### 新功能
+- `baoyu-url-to-markdown`：新增浏览器回退策略 — 默认无头模式优先，技术故障时自动重试有头 Chrome；新增 `--browser auto|headless|headed` 参数及 `--headless`/`--headed` 快捷方式
+- `baoyu-url-to-markdown`：新增内容清理模块，提取前预处理 HTML（移除广告、base64 图片、脚本、样式）
+- `baoyu-url-to-markdown`：媒体本地化支持 base64 data URI 图片
+- `baoyu-url-to-markdown`：从浏览器捕获最终 URL 以跟踪重定向，用于输出路径生成
+- `baoyu-url-to-markdown`：新增 Agent 质量门控文档，规范捕获后的内容验证流程
+
+### 依赖
+- `baoyu-url-to-markdown`：升级 defuddle ^0.12.0 → ^0.14.0
+
+### 测试
+- `baoyu-url-to-markdown`：新增 content-cleaner、html-to-markdown、legacy-converter、media-localizer 单元测试
+
+## 1.81.0 - 2026-03-24
+
+### 新功能
+- `baoyu-youtube-transcript`：YouTube 封锁直连 InnerTube API 时自动回退到 yt-dlp，支持备用客户端身份重试及通过 `YOUTUBE_TRANSCRIPT_COOKIES_FROM_BROWSER` 环境变量传递浏览器 Cookie
+
+### 重构
+- `baoyu-youtube-transcript`：将单体脚本拆分为类型化模块（youtube、transcript、storage、shared、types）并添加单元测试
+
+## 1.80.1 - 2026-03-24
+
+### 修复
+- `baoyu-image-gen`：修正即梦 API 请求中的 `prompt` 字段名
+
+## 1.80.0 - 2026-03-24
+
+### 新功能
+- `baoyu-image-gen`：新增 Azure OpenAI 作为独立图像生成服务商，支持灵活的端点解析、部署名称推断、质量映射及参考图片格式校验
+
+## 1.79.2 - 2026-03-23
+
+### 修复
+- `baoyu-cover-image`：简化参考图片处理流程 — 模型支持 `--ref` 时直接传递，仅在模型不支持参考图时创建描述文件
+- `baoyu-post-to-weibo`：文章 Markdown 转 HTML 时不传递 --theme 参数
+
+### 测试
+- 修复 Node 兼容的解析器测试，添加解析器测试依赖
+
+## 1.79.1 - 2026-03-23
+
+### 修复
+- 合并为单一插件，防止 skill 重复注册 (by @TyrealQ)
+- `baoyu-article-illustrator`：移除水印提示词中的不透明度参数
+- `baoyu-comic`：修正哆啦 A 梦命名间距，移除水印不透明度参数
+- `baoyu-xhs-images`：移除水印不透明度参数，修正中英文间距
+
+### 文档
+- 更新项目文档以反映单一插件架构
+
+## 1.79.0 - 2026-03-22
+
+### 新功能
+- `baoyu-post-to-wechat`：改进凭据加载机制，支持多来源优先级解析，并提供不完整凭据来源的诊断信息
+
+## 1.78.0 - 2026-03-22
+
+### 新功能
+- `baoyu-url-to-markdown`：新增 URL 专用解析层，支持 X/Twitter 和 archive.ph 站点的定制化 HTML 提取
+- `baoyu-url-to-markdown`：改进 slug 生成算法，去除停用词并采用子目录输出结构
+
+### 修复
+- `baoyu-url-to-markdown`：旧版转换器保留包含媒体元素的锚标签
+- `baoyu-url-to-markdown`：更智能的标题去重，避免重复添加标题
+
+## 1.77.0 - 2026-03-22
+
+### 新功能
+- `baoyu-youtube-transcript`：为章节数据添加结束时间 (by @jzOcb)
+
+### 修复
+- `sync-clawhub`：跳过失败的技能而不是中止同步
+
+## 1.76.1 - 2026-03-21
+
+### 文档
+- `baoyu-youtube-transcript`：修复 zsh glob 问题 — 运行脚本时始终对 YouTube URL 使用单引号
+
+## 1.76.0 - 2026-03-21
+
+### 新功能
+- `baoyu-youtube-transcript`：Markdown 输出中新增标题、描述摘要和封面图片
+
+### 修复
+- `baoyu-markdown-to-html`：测试运行器改用 process.execPath 和 tsx import
+
+## 1.75.0 - 2026-03-21
+
+### 新功能
+- `baoyu-youtube-transcript`：新技能 — 下载 YouTube 视频字幕/转录文本和封面图片，支持多语言、章节分段和说话人识别
+
 ## 1.74.1 - 2026-03-21
 
 ### 修复

CLAUDE.md

@@ -1,16 +1,16 @@
 # CLAUDE.md
 
-Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.74.0**.
+Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.84.0**.
 
 ## Architecture
 
-Skills organized into three categories in `.claude-plugin/marketplace.json` (defines plugin metadata, version, and skill paths):
+Skills are exposed through the single `baoyu-skills` plugin in `.claude-plugin/marketplace.json` (which defines plugin metadata, version, and skill paths). The repo docs still group them into three logical areas:
 
-| Category | Description |
-|----------|-------------|
-| `content-skills` | Generate or publish content (images, slides, comics, posts) |
-| `ai-generation-skills` | AI generation backends |
-| `utility-skills` | Content processing (conversion, compression, translation) |
+| Group | Description |
+|-------|-------------|
+| Content Skills | Generate or publish content (images, slides, comics, posts) |
+| AI Generation Skills | AI generation backends |
+| Utility Skills | Content processing (conversion, compression, translation) |
 
 Each skill contains `SKILL.md` (YAML front matter + docs), optional `scripts/`, `references/`, `prompts/`.
 
@@ -31,7 +31,7 @@ Execute: `${BUN_X} skills/<skill>/scripts/main.ts [options]`
 
 - **Bun**: TypeScript runtime (`bun` preferred, fallback `npx -y bun`)
 - **Chrome**: Required for CDP-based skills (gemini-web, post-to-x/wechat/weibo, url-to-markdown). All CDP skills share a single profile, override via `BAOYU_CHROME_PROFILE_DIR` env var. Platform paths: [docs/chrome-profile.md](docs/chrome-profile.md)
-- **Image generation APIs**: `baoyu-image-gen` requires API key (OpenAI, Google, OpenRouter, DashScope, or Replicate) configured in EXTEND.md
+- **Image generation APIs**: `baoyu-imagine` requires API key (OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, or Replicate) configured in EXTEND.md
 - **Gemini Web auth**: Browser cookies (first run opens Chrome for login, `--login` to refresh)
 
 ## Security
@@ -46,7 +46,7 @@ Execute: `${BUN_X} skills/<skill>/scripts/main.ts [options]`
 | Rule | Description |
 |------|-------------|
 | **Load project skills first** | Project skills override system/user-level skills with same name |
-| **Default image generation** | Use `skills/baoyu-image-gen/SKILL.md` unless user specifies otherwise |
+| **Default image generation** | Use `skills/baoyu-imagine/SKILL.md` unless user specifies otherwise |
 
 Priority: project `skills/` → `$HOME/.baoyu-skills/` → system-level.
 

README.md

@@ -32,7 +32,7 @@ This repository now supports publishing each `skills/baoyu-*` directory as an in
 ClawHub installs skills individually, not as one marketplace bundle. After publishing, users can install specific skills such as:
 
 ```bash
-clawhub install baoyu-image-gen
+clawhub install baoyu-imagine
 clawhub install baoyu-markdown-to-html
 ```
 
@@ -52,16 +52,14 @@ Run the following command in Claude Code:
 
 1. Select **Browse and install plugins**
 2. Select **baoyu-skills**
-3. Select the plugin(s) you want to install
+3. Select the **baoyu-skills** plugin
 4. Select **Install now**
 
 **Option 2: Direct Install**
 
 ```bash
-# Install specific plugin
-/plugin install content-skills@baoyu-skills
-/plugin install ai-generation-skills@baoyu-skills
-/plugin install utility-skills@baoyu-skills
+# Install the marketplace's single plugin
+/plugin install baoyu-skills@baoyu-skills
 ```
 
 **Option 3: Ask the Agent**
@@ -70,13 +68,13 @@ Simply tell Claude Code:
 
 > Please install Skills from github.com/JimLiu/baoyu-skills
 
-### Available Plugins
+### Available Plugin
 
-| Plugin | Description | Skills |
-|--------|-------------|--------|
-| **content-skills** | Content generation and publishing | [xhs-images](#baoyu-xhs-images), [infographic](#baoyu-infographic), [cover-image](#baoyu-cover-image), [slide-deck](#baoyu-slide-deck), [comic](#baoyu-comic), [article-illustrator](#baoyu-article-illustrator), [post-to-x](#baoyu-post-to-x), [post-to-wechat](#baoyu-post-to-wechat), [post-to-weibo](#baoyu-post-to-weibo) |
-| **ai-generation-skills** | AI-powered generation backends | [image-gen](#baoyu-image-gen), [danger-gemini-web](#baoyu-danger-gemini-web) |
-| **utility-skills** | Utility tools for content processing | [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [markdown-to-html](#baoyu-markdown-to-html), [translate](#baoyu-translate) |
+The marketplace now exposes a single plugin so each skill is registered exactly once.
+
+| Plugin | Description | Includes |
+|--------|-------------|----------|
+| **baoyu-skills** | Content generation, AI backends, and utility tools for daily work efficiency | All skills in this repository, organized below as Content Skills, AI Generation Skills, and Utility Skills |
 
 ## Update Skills
 
@@ -663,40 +661,58 @@ Post content to Weibo (微博). Supports regular posts with text, images, and vi
 
 AI-powered generation backends.
 
-#### baoyu-image-gen
+#### baoyu-imagine
 
-AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyun Tongyi Wanxiang), Jimeng (即梦), Seedream (豆包), and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.
+AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (Aliyun Tongyi Wanxiang), MiniMax, Jimeng (即梦), Seedream (豆包), and Replicate APIs. Supports text-to-image, reference images, aspect ratios, custom sizes, batch generation, and quality presets.
 
 ```bash
 # Basic generation (auto-detect provider)
-/baoyu-image-gen --prompt "A cute cat" --image cat.png
+/baoyu-imagine --prompt "A cute cat" --image cat.png
 
 # With aspect ratio
-/baoyu-image-gen --prompt "A landscape" --image landscape.png --ar 16:9
+/baoyu-imagine --prompt "A landscape" --image landscape.png --ar 16:9
 
 # High quality (2k)
-/baoyu-image-gen --prompt "A banner" --image banner.png --quality 2k
+/baoyu-imagine --prompt "A banner" --image banner.png --quality 2k
 
 # Specific provider
-/baoyu-image-gen --prompt "A cat" --image cat.png --provider openai
+/baoyu-imagine --prompt "A cat" --image cat.png --provider openai
+
+# Azure OpenAI (model = deployment name)
+/baoyu-imagine --prompt "A cat" --image cat.png --provider azure --model gpt-image-1.5
 
 # OpenRouter
-/baoyu-image-gen --prompt "A cat" --image cat.png --provider openrouter
+/baoyu-imagine --prompt "A cat" --image cat.png --provider openrouter
+
+# OpenRouter with reference images
+/baoyu-imagine --prompt "Make it blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
 
 # DashScope (Aliyun Tongyi Wanxiang)
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider dashscope
+
+# DashScope with custom size
+/baoyu-imagine --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
+
+# MiniMax
+/baoyu-imagine --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
+
+# MiniMax with subject reference
+/baoyu-imagine --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
 
 # Replicate
-/baoyu-image-gen --prompt "A cat" --image cat.png --provider replicate
+/baoyu-imagine --prompt "A cat" --image cat.png --provider replicate
 
 # Jimeng (即梦)
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider jimeng
 
 # Seedream (豆包)
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider seedream
 
-# With reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 5.0/4.5/4.0)
-/baoyu-image-gen --prompt "Make it blue" --image out.png --ref source.png
+# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 5.0/4.5/4.0)
+/baoyu-imagine --prompt "Make it blue" --image out.png --ref source.png
+
+# Batch mode
+/baoyu-imagine --batchfile batch.json --jobs 4 --json
 ```
 
 **Options**:
@@ -705,44 +721,73 @@ AI SDK-based image generation using OpenAI, Google, OpenRouter, DashScope (Aliyu
 | `--prompt`, `-p` | Prompt text |
 | `--promptfiles` | Read prompt from files (concatenated) |
 | `--image` | Output image path (required) |
-| `--provider` | `google`, `openai`, `openrouter`, `dashscope`, `jimeng`, `seedream` or `replicate` (default: auto-detect; prefers google) |
-| `--model`, `-m` | Model ID |
+| `--batchfile` | JSON batch file for multi-image generation |
+| `--jobs` | Worker count for batch mode |
+| `--provider` | `google`, `openai`, `azure`, `openrouter`, `dashscope`, `minimax`, `jimeng`, `seedream`, or `replicate` |
+| `--model`, `-m` | Model ID or deployment name. Azure uses deployment name; OpenRouter uses full model IDs; MiniMax uses `image-01` / `image-01-live` |
 | `--ar` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
 | `--size` | Size (e.g., `1024x1024`) |
 | `--quality` | `normal` or `2k` (default: `2k`) |
-| `--ref` | Reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 5.0/4.5/4.0) |
+| `--imageSize` | `1K`, `2K`, or `4K` for Google/OpenRouter |
+| `--ref` | Reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 5.0/4.5/4.0) |
+| `--n` | Number of images per request |
+| `--json` | JSON output |
 
 **Environment Variables** (see [Environment Configuration](#environment-configuration) for setup):
 | Variable | Description | Default |
 |----------|-------------|---------|
 | `OPENAI_API_KEY` | OpenAI API key | - |
+| `AZURE_OPENAI_API_KEY` | Azure OpenAI API key | - |
 | `OPENROUTER_API_KEY` | OpenRouter API key | - |
 | `GOOGLE_API_KEY` | Google API key | - |
+| `GEMINI_API_KEY` | Alias for `GOOGLE_API_KEY` | - |
 | `DASHSCOPE_API_KEY` | DashScope API key (Aliyun) | - |
+| `MINIMAX_API_KEY` | MiniMax API key | - |
 | `REPLICATE_API_TOKEN` | Replicate API token | - |
 | `JIMENG_ACCESS_KEY_ID` | Jimeng Volcengine access key | - |
 | `JIMENG_SECRET_ACCESS_KEY` | Jimeng Volcengine secret key | - |
 | `ARK_API_KEY` | Seedream Volcengine ARK API key | - |
 | `OPENAI_IMAGE_MODEL` | OpenAI model | `gpt-image-1.5` |
+| `AZURE_OPENAI_DEPLOYMENT` | Azure default deployment name | - |
+| `AZURE_OPENAI_IMAGE_MODEL` | Backward-compatible Azure deployment/model alias | `gpt-image-1.5` |
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter model | `google/gemini-3.1-flash-image-preview` |
 | `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image-preview` |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope model | `qwen-image-2.0-pro` |
+| `MINIMAX_IMAGE_MODEL` | MiniMax model | `image-01` |
 | `REPLICATE_IMAGE_MODEL` | Replicate model | `google/nano-banana-pro` |
 | `JIMENG_IMAGE_MODEL` | Jimeng model | `jimeng_t2i_v40` |
 | `SEEDREAM_IMAGE_MODEL` | Seedream model | `doubao-seedream-5-0-260128` |
 | `OPENAI_BASE_URL` | Custom OpenAI endpoint | - |
+| `OPENAI_IMAGE_USE_CHAT` | Use `/chat/completions` for OpenAI image generation | `false` |
+| `AZURE_OPENAI_BASE_URL` | Azure resource or deployment endpoint | - |
+| `AZURE_API_VERSION` | Azure image API version | `2025-04-01-preview` |
 | `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint | `https://openrouter.ai/api/v1` |
+| `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution | - |
+| `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution | - |
 | `GOOGLE_BASE_URL` | Custom Google endpoint | - |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint | - |
+| `MINIMAX_BASE_URL` | Custom MiniMax endpoint | `https://api.minimax.io` |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint | - |
 | `JIMENG_BASE_URL` | Custom Jimeng endpoint | `https://visual.volcengineapi.com` |
 | `JIMENG_REGION` | Jimeng region | `cn-north-1` |
 | `SEEDREAM_BASE_URL` | Custom Seedream endpoint | `https://ark.cn-beijing.volces.com/api/v3` |
+| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap | `10` |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency | provider-specific |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider request start gap | provider-specific |
+
+**Provider Notes**:
+- Azure OpenAI: `--model` means Azure deployment name, not the underlying model family.
+- DashScope: `qwen-image-2.0-pro` is the recommended default for custom `--size`, `21:9`, and strong Chinese/English text rendering.
+- MiniMax: `image-01` supports documented custom `width` / `height`; `image-01-live` is lower latency and works best with `--ar`.
+- MiniMax reference images are sent as `subject_reference`; the current API is specialized toward character / portrait consistency.
+- Jimeng does not support reference images.
+- Seedream reference images are supported by Seedream 5.0 / 4.5 / 4.0, not Seedream 3.0.
 
 **Provider Auto-Selection**:
-1. If `--provider` specified → use it
-2. If only one API key available → use that provider
-3. If multiple available → default to Google
+1. If `--provider` is specified → use it
+2. If `--ref` is provided and no provider is specified → try Google, then OpenAI, Azure, OpenRouter, Replicate, Seedream, and finally MiniMax
+3. If only one API key is available → use that provider
+4. If multiple providers are available → default to Google
 
 #### baoyu-danger-gemini-web
 
@@ -766,6 +811,40 @@ Interacts with Gemini Web to generate text and images.
 
 Utility tools for content processing.
 
+#### baoyu-youtube-transcript
+
+Download YouTube video transcripts/subtitles and cover images. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting.
+
+```bash
+# Default: markdown with timestamps
+/baoyu-youtube-transcript https://www.youtube.com/watch?v=VIDEO_ID
+
+# Specify languages (priority order)
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --languages zh,en,ja
+
+# With chapters and speaker identification
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --chapters --speakers
+
+# SRT subtitle format
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --format srt
+
+# List available transcripts
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --list
+```
+
+**Options**:
+| Option | Description | Default |
+|--------|-------------|---------|
+| `<url-or-id>` | YouTube URL or video ID | Required |
+| `--languages <codes>` | Language codes, comma-separated | `en` |
+| `--format <fmt>` | Output format: `text`, `srt` | `text` |
+| `--translate <code>` | Translate to specified language | |
+| `--chapters` | Chapter segmentation from video description | |
+| `--speakers` | Speaker identification (requires AI post-processing) | |
+| `--no-timestamps` | Disable timestamps | |
+| `--list` | List available transcripts | |
+| `--refresh` | Force re-fetch, ignore cache | |
+
 #### baoyu-url-to-markdown
 
 Fetch any URL via Chrome CDP and convert to clean markdown. Saves rendered HTML snapshot alongside the markdown, and automatically falls back to a legacy extractor when Defuddle fails.
@@ -966,7 +1045,7 @@ Custom style descriptions are also accepted, e.g., `--style "poetic and lyrical"
 Some skills require API keys or custom configuration. Environment variables can be set in `.env` files:
 
 **Load Priority** (higher priority overrides lower):
-1. CLI environment variables (e.g., `OPENAI_API_KEY=xxx /baoyu-image-gen ...`)
+1. CLI environment variables (e.g., `OPENAI_API_KEY=xxx /baoyu-imagine ...`)
 2. `process.env` (system environment)
 3. `<cwd>/.baoyu-skills/.env` (project-level)
 4. `~/.baoyu-skills/.env` (user-level)
@@ -983,11 +1062,20 @@ cat > ~/.baoyu-skills/.env << 'EOF'
 OPENAI_API_KEY=sk-xxx
 OPENAI_IMAGE_MODEL=gpt-image-1.5
 # OPENAI_BASE_URL=https://api.openai.com/v1
+# OPENAI_IMAGE_USE_CHAT=false
+
+# Azure OpenAI
+AZURE_OPENAI_API_KEY=xxx
+AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
+AZURE_OPENAI_DEPLOYMENT=gpt-image-1.5
+# AZURE_API_VERSION=2025-04-01-preview
 
 # OpenRouter
 OPENROUTER_API_KEY=sk-or-xxx
 OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image-preview
 # OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
+# OPENROUTER_HTTP_REFERER=https://your-app.example.com
+# OPENROUTER_TITLE=Your App Name
 
 # Google
 GOOGLE_API_KEY=xxx
@@ -999,6 +1087,11 @@ DASHSCOPE_API_KEY=sk-xxx
 DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
 # DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
 
+# MiniMax
+MINIMAX_API_KEY=xxx
+MINIMAX_IMAGE_MODEL=image-01
+# MINIMAX_BASE_URL=https://api.minimax.io
+
 # Replicate
 REPLICATE_API_TOKEN=r8_xxx
 REPLICATE_IMAGE_MODEL=google/nano-banana-pro

README.zh.md

@@ -32,7 +32,7 @@ npx skills add jimliu/baoyu-skills
 ClawHub 按“单个 skill”安装，不是把整个 marketplace 一次性装进去。发布后，用户可以按需安装：
 
 ```bash
-clawhub install baoyu-image-gen
+clawhub install baoyu-imagine
 clawhub install baoyu-markdown-to-html
 ```
 
@@ -52,16 +52,14 @@ clawhub install baoyu-markdown-to-html
 
 1. 选择 **Browse and install plugins**
 2. 选择 **baoyu-skills**
-3. 选择要安装的插件
+3. 选择 **baoyu-skills** 插件
 4. 选择 **Install now**
 
 **方式二：直接安装**
 
 ```bash
-# 安装指定插件
-/plugin install content-skills@baoyu-skills
-/plugin install ai-generation-skills@baoyu-skills
-/plugin install utility-skills@baoyu-skills
+# 安装 marketplace 中唯一的插件
+/plugin install baoyu-skills@baoyu-skills
 ```
 
 **方式三：告诉 Agent**
@@ -72,11 +70,11 @@ clawhub install baoyu-markdown-to-html
 
 ### 可用插件
 
-| 插件 | 说明 | 包含技能 |
+现在 marketplace 只暴露一个插件，这样每个 skill 只会注册一次。
+
+| 插件 | 说明 | 包含内容 |
 |------|------|----------|
-| **content-skills** | 内容生成和发布 | [xhs-images](#baoyu-xhs-images), [infographic](#baoyu-infographic), [cover-image](#baoyu-cover-image), [slide-deck](#baoyu-slide-deck), [comic](#baoyu-comic), [article-illustrator](#baoyu-article-illustrator), [post-to-x](#baoyu-post-to-x), [post-to-wechat](#baoyu-post-to-wechat), [post-to-weibo](#baoyu-post-to-weibo) |
-| **ai-generation-skills** | AI 生成后端 | [image-gen](#baoyu-image-gen), [danger-gemini-web](#baoyu-danger-gemini-web) |
-| **utility-skills** | 内容处理工具 | [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [markdown-to-html](#baoyu-markdown-to-html), [translate](#baoyu-translate) |
+| **baoyu-skills** | 提供内容生成、AI 后端和日常效率工具技能 | 仓库中的全部 skills，仍按下方的内容技能、AI 生成技能、工具技能三个分类展示 |
 
 ## 更新技能
 
@@ -663,40 +661,58 @@ accounts:
 
 AI 驱动的生成后端。
 
-#### baoyu-image-gen
+#### baoyu-imagine
 
-基于 AI SDK 的图像生成，支持 OpenAI、Google、OpenRouter、DashScope（阿里通义万相）、即梦（Jimeng）、豆包（Seedream）和 Replicate API。支持文生图、参考图、宽高比和质量预设。
+基于 AI SDK 的图像生成，支持 OpenAI、Azure OpenAI、Google、OpenRouter、DashScope（阿里通义万相）、MiniMax、即梦（Jimeng）、豆包（Seedream）和 Replicate API。支持文生图、参考图、宽高比、自定义尺寸、批量生成和质量预设。
 
 ```bash
 # 基础生成（自动检测服务商）
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png
 
 # 指定宽高比
-/baoyu-image-gen --prompt "风景图" --image landscape.png --ar 16:9
+/baoyu-imagine --prompt "风景图" --image landscape.png --ar 16:9
 
 # 高质量（2k 分辨率）
-/baoyu-image-gen --prompt "横幅图" --image banner.png --quality 2k
+/baoyu-imagine --prompt "横幅图" --image banner.png --quality 2k
 
 # 指定服务商
-/baoyu-image-gen --prompt "一只猫" --image cat.png --provider openai
+/baoyu-imagine --prompt "一只猫" --image cat.png --provider openai
+
+# Azure OpenAI（model 为部署名称）
+/baoyu-imagine --prompt "一只猫" --image cat.png --provider azure --model gpt-image-1.5
 
 # OpenRouter
-/baoyu-image-gen --prompt "一只猫" --image cat.png --provider openrouter
+/baoyu-imagine --prompt "一只猫" --image cat.png --provider openrouter
+
+# OpenRouter + 参考图
+/baoyu-imagine --prompt "把它变成蓝色" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
 
 # DashScope（阿里通义万相）
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider dashscope
+
+# DashScope 自定义尺寸
+/baoyu-imagine --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
+
+# MiniMax
+/baoyu-imagine --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
+
+# MiniMax + 角色参考图
+/baoyu-imagine --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
 
 # Replicate
-/baoyu-image-gen --prompt "一只猫" --image cat.png --provider replicate
+/baoyu-imagine --prompt "一只猫" --image cat.png --provider replicate
 
 # 即梦（Jimeng）
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider jimeng
 
 # 豆包（Seedream）
-/baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
+/baoyu-imagine --prompt "一只可爱的猫" --image cat.png --provider seedream
 
-# 带参考图（Google、OpenAI、OpenRouter、Replicate 或 Seedream 5.0/4.5/4.0）
-/baoyu-image-gen --prompt "把它变成蓝色" --image out.png --ref source.png
+# 带参考图（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate、MiniMax 或 Seedream 5.0/4.5/4.0）
+/baoyu-imagine --prompt "把它变成蓝色" --image out.png --ref source.png
+
+# 批量模式
+/baoyu-imagine --batchfile batch.json --jobs 4 --json
 ```
 
 **选项**：
@@ -705,44 +721,73 @@ AI 驱动的生成后端。
 | `--prompt`, `-p` | 提示词文本 |
 | `--promptfiles` | 从文件读取提示词（多文件拼接） |
 | `--image` | 输出图片路径（必需） |
-| `--provider` | `google`、`openai`、`openrouter`、`dashscope`、`jimeng`、`seedream` 或 `replicate`（默认：自动检测，优先 google） |
-| `--model`, `-m` | 模型 ID |
+| `--batchfile` | 多图批量生成的 JSON 文件 |
+| `--jobs` | 批量模式的并发 worker 数 |
+| `--provider` | `google`、`openai`、`azure`、`openrouter`、`dashscope`、`minimax`、`jimeng`、`seedream` 或 `replicate` |
+| `--model`, `-m` | 模型 ID 或部署名。Azure 使用部署名；OpenRouter 使用完整模型 ID；MiniMax 使用 `image-01` / `image-01-live` |
 | `--ar` | 宽高比（如 `16:9`、`1:1`、`4:3`） |
 | `--size` | 尺寸（如 `1024x1024`） |
 | `--quality` | `normal` 或 `2k`（默认：`2k`） |
-| `--ref` | 参考图片（Google、OpenAI、OpenRouter、Replicate 或 Seedream 5.0/4.5/4.0） |
+| `--imageSize` | Google/OpenRouter 使用的 `1K`、`2K`、`4K` |
+| `--ref` | 参考图片（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate、MiniMax 或 Seedream 5.0/4.5/4.0） |
+| `--n` | 单次请求生成图片数量 |
+| `--json` | 输出 JSON 结果 |
 
 **环境变量**（配置方法见[环境配置](#环境配置)）：
 | 变量 | 说明 | 默认值 |
 |------|------|--------|
 | `OPENAI_API_KEY` | OpenAI API 密钥 | - |
+| `AZURE_OPENAI_API_KEY` | Azure OpenAI API 密钥 | - |
 | `OPENROUTER_API_KEY` | OpenRouter API 密钥 | - |
 | `GOOGLE_API_KEY` | Google API 密钥 | - |
+| `GEMINI_API_KEY` | `GOOGLE_API_KEY` 的别名 | - |
 | `DASHSCOPE_API_KEY` | DashScope API 密钥（阿里云） | - |
+| `MINIMAX_API_KEY` | MiniMax API 密钥 | - |
 | `REPLICATE_API_TOKEN` | Replicate API Token | - |
 | `JIMENG_ACCESS_KEY_ID` | 即梦火山引擎 Access Key | - |
 | `JIMENG_SECRET_ACCESS_KEY` | 即梦火山引擎 Secret Key | - |
 | `ARK_API_KEY` | 豆包火山引擎 ARK API 密钥 | - |
 | `OPENAI_IMAGE_MODEL` | OpenAI 模型 | `gpt-image-1.5` |
+| `AZURE_OPENAI_DEPLOYMENT` | Azure 默认部署名 | - |
+| `AZURE_OPENAI_IMAGE_MODEL` | 兼容旧配置的 Azure 部署/模型别名 | `gpt-image-1.5` |
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter 模型 | `google/gemini-3.1-flash-image-preview` |
 | `GOOGLE_IMAGE_MODEL` | Google 模型 | `gemini-3-pro-image-preview` |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope 模型 | `qwen-image-2.0-pro` |
+| `MINIMAX_IMAGE_MODEL` | MiniMax 模型 | `image-01` |
 | `REPLICATE_IMAGE_MODEL` | Replicate 模型 | `google/nano-banana-pro` |
 | `JIMENG_IMAGE_MODEL` | 即梦模型 | `jimeng_t2i_v40` |
 | `SEEDREAM_IMAGE_MODEL` | 豆包模型 | `doubao-seedream-5-0-260128` |
 | `OPENAI_BASE_URL` | 自定义 OpenAI 端点 | - |
+| `OPENAI_IMAGE_USE_CHAT` | OpenAI 改走 `/chat/completions` | `false` |
+| `AZURE_OPENAI_BASE_URL` | Azure 资源或部署端点 | - |
+| `AZURE_API_VERSION` | Azure 图像 API 版本 | `2025-04-01-preview` |
 | `OPENROUTER_BASE_URL` | 自定义 OpenRouter 端点 | `https://openrouter.ai/api/v1` |
+| `OPENROUTER_HTTP_REFERER` | OpenRouter 归因用站点 URL | - |
+| `OPENROUTER_TITLE` | OpenRouter 归因用应用名 | - |
 | `GOOGLE_BASE_URL` | 自定义 Google 端点 | - |
 | `DASHSCOPE_BASE_URL` | 自定义 DashScope 端点 | - |
+| `MINIMAX_BASE_URL` | 自定义 MiniMax 端点 | `https://api.minimax.io` |
 | `REPLICATE_BASE_URL` | 自定义 Replicate 端点 | - |
 | `JIMENG_BASE_URL` | 自定义即梦端点 | `https://visual.volcengineapi.com` |
 | `JIMENG_REGION` | 即梦区域 | `cn-north-1` |
 | `SEEDREAM_BASE_URL` | 自定义豆包端点 | `https://ark.cn-beijing.volces.com/api/v3` |
+| `BAOYU_IMAGE_GEN_MAX_WORKERS` | 批量模式最大 worker 数 | `10` |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | 覆盖 provider 并发数 | provider 默认值 |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | 覆盖 provider 请求启动间隔 | provider 默认值 |
+
+**Provider 说明**：
+- Azure OpenAI：`--model` 表示 Azure deployment name，不是底层模型家族名。
+- DashScope：`qwen-image-2.0-pro` 是自定义 `--size`、`21:9` 和中英文排版的推荐默认模型。
+- MiniMax：`image-01` 支持官方文档里的自定义 `width` / `height`；`image-01-live` 更偏低延迟，适合配合 `--ar` 使用。
+- MiniMax 参考图会走 `subject_reference`，当前能力更偏角色 / 人像一致性。
+- 即梦不支持参考图。
+- 豆包参考图能力仅适用于 Seedream 5.0 / 4.5 / 4.0，不适用于 Seedream 3.0。
 
 **服务商自动选择**：
 1. 如果指定了 `--provider` → 使用指定的
-2. 如果只有一个 API 密钥 → 使用对应服务商
-3. 如果多个可用 → 默认使用 Google
+2. 如果传了 `--ref` 且未指定 provider → 依次尝试 Google、OpenAI、Azure、OpenRouter、Replicate、Seedream，最后是 MiniMax
+3. 如果只有一个 API 密钥 → 使用对应服务商
+4. 如果多个可用 → 默认使用 Google
 
 #### baoyu-danger-gemini-web
 
@@ -766,6 +811,40 @@ AI 驱动的生成后端。
 
 内容处理工具。
 
+#### baoyu-youtube-transcript
+
+下载 YouTube 视频字幕/转录文本和封面图片。支持多语言、翻译、章节分段和说话人识别。缓存原始数据以便快速重新格式化。
+
+```bash
+# 默认：带时间戳的 Markdown
+/baoyu-youtube-transcript https://www.youtube.com/watch?v=VIDEO_ID
+
+# 指定语言（按优先级排列）
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --languages zh,en,ja
+
+# 章节分段 + 说话人识别
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --chapters --speakers
+
+# SRT 字幕格式
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --format srt
+
+# 列出可用字幕
+/baoyu-youtube-transcript https://youtu.be/VIDEO_ID --list
+```
+
+**选项**：
+| 选项 | 说明 | 默认值 |
+|------|------|--------|
+| `<url-or-id>` | YouTube URL 或视频 ID | 必填 |
+| `--languages <codes>` | 语言代码，逗号分隔 | `en` |
+| `--format <fmt>` | 输出格式：`text`、`srt` | `text` |
+| `--translate <code>` | 翻译为指定语言 | |
+| `--chapters` | 根据视频描述进行章节分段 | |
+| `--speakers` | 说话人识别（需 AI 后处理） | |
+| `--no-timestamps` | 禁用时间戳 | |
+| `--list` | 列出可用字幕 | |
+| `--refresh` | 强制重新获取，忽略缓存 | |
+
 #### baoyu-url-to-markdown
 
 通过 Chrome CDP 抓取任意 URL 并转换为 Markdown。同时保存渲染后的 HTML 快照，Defuddle 失败时自动回退到旧版提取器。
@@ -966,7 +1045,7 @@ AI 驱动的生成后端。
 部分技能需要 API 密钥或自定义配置。环境变量可以在 `.env` 文件中设置：
 
 **加载优先级**（高优先级覆盖低优先级）：
-1. 命令行环境变量（如 `OPENAI_API_KEY=xxx /baoyu-image-gen ...`）
+1. 命令行环境变量（如 `OPENAI_API_KEY=xxx /baoyu-imagine ...`）
 2. `process.env`（系统环境变量）
 3. `<cwd>/.baoyu-skills/.env`（项目级）
 4. `~/.baoyu-skills/.env`（用户级）
@@ -983,11 +1062,20 @@ cat > ~/.baoyu-skills/.env << 'EOF'
 OPENAI_API_KEY=sk-xxx
 OPENAI_IMAGE_MODEL=gpt-image-1.5
 # OPENAI_BASE_URL=https://api.openai.com/v1
+# OPENAI_IMAGE_USE_CHAT=false
+
+# Azure OpenAI
+AZURE_OPENAI_API_KEY=xxx
+AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
+AZURE_OPENAI_DEPLOYMENT=gpt-image-1.5
+# AZURE_API_VERSION=2025-04-01-preview
 
 # OpenRouter
 OPENROUTER_API_KEY=sk-or-xxx
 OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image-preview
 # OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
+# OPENROUTER_HTTP_REFERER=https://your-app.example.com
+# OPENROUTER_TITLE=你的应用名
 
 # Google
 GOOGLE_API_KEY=xxx
@@ -999,6 +1087,11 @@ DASHSCOPE_API_KEY=sk-xxx
 DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
 # DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
 
+# MiniMax
+MINIMAX_API_KEY=xxx
+MINIMAX_IMAGE_MODEL=image-01
+# MINIMAX_BASE_URL=https://api.minimax.io
+
 # Replicate
 REPLICATE_API_TOKEN=r8_xxx
 REPLICATE_IMAGE_MODEL=google/nano-banana-pro

docs/creating-skills.md

@@ -34,20 +34,22 @@ metadata:
 1. Create `skills/baoyu-<name>/SKILL.md` with YAML front matter
 2. Add TypeScript in `skills/baoyu-<name>/scripts/` (if applicable)
 3. Add prompt templates in `skills/baoyu-<name>/prompts/` if needed
-4. Register in `marketplace.json` under appropriate category
+4. Register the skill in `.claude-plugin/marketplace.json` under the `baoyu-skills` plugin entry
 5. Add Script Directory section to SKILL.md if skill has scripts
 6. Add openclaw metadata to frontmatter
 
-## Category Selection
+## Skill Grouping
 
-| If your skill... | Use category |
-|------------------|--------------|
-| Generates visual content (images, slides, comics) | `content-skills` |
-| Publishes to platforms (X, WeChat, Weibo) | `content-skills` |
-| Provides AI generation backend | `ai-generation-skills` |
-| Converts or processes content | `utility-skills` |
+All skills are registered under the single `baoyu-skills` plugin. Use these logical groups when deciding where the skill should appear in the docs:
 
-New category: add plugin object to `marketplace.json` with `name`, `description`, `skills[]`.
+| If your skill... | Use group |
+|------------------|-----------|
+| Generates visual content (images, slides, comics) | Content Skills |
+| Publishes to platforms (X, WeChat, Weibo) | Content Skills |
+| Provides AI generation backend | AI Generation Skills |
+| Converts or processes content | Utility Skills |
+
+If you add a new logical group, update the docs that present grouped skills, but keep the skill registered under the single `baoyu-skills` plugin entry.
 
 ## Writing Descriptions
 

docs/image-generation.md

@@ -4,7 +4,7 @@ Skills that require image generation MUST delegate to available image generation
 
 ## Skill Selection
 
-**Default**: `skills/baoyu-image-gen/SKILL.md` (unless user specifies otherwise).
+**Default**: `skills/baoyu-imagine/SKILL.md` (unless user specifies otherwise).
 
 1. Read skill's SKILL.md for parameters and capabilities
 2. If user requests different skill, check `skills/` for alternatives
@@ -16,7 +16,7 @@ Skills that require image generation MUST delegate to available image generation
 ### Step N: Generate Images
 
 **Skill Selection**:
-1. Check available skills (`baoyu-image-gen` default, or `baoyu-danger-gemini-web`)
+1. Check available skills (`baoyu-imagine` default, or `baoyu-danger-gemini-web`)
 2. Read selected skill's SKILL.md for parameters
 3. If multiple skills available, ask user to choose
 
@@ -27,7 +27,7 @@ Skills that require image generation MUST delegate to available image generation
 4. On failure, auto-retry once before reporting error
 ```
 
-**Batch Parallel** (`baoyu-image-gen` only): concurrent workers with per-provider throttling via `batch.max_workers` in EXTEND.md.
+**Batch Parallel** (`baoyu-imagine` only): concurrent workers with per-provider throttling via `batch.max_workers` in EXTEND.md.
 
 ## Output Path Convention
 

package-lock.json

@@ -9,7 +9,11 @@
         "packages/*"
       ],
       "devDependencies": {
-        "tsx": "^4.20.5"
+        "@mozilla/readability": "^0.6.0",
+        "linkedom": "^0.18.12",
+        "tsx": "^4.20.5",
+        "turndown": "^7.2.2",
+        "turndown-plugin-gfm": "^1.0.2"
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
@@ -454,6 +458,23 @@
         "node": ">=18"
       }
     },
+    "node_modules/@mixmark-io/domino": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/@mixmark-io/domino/-/domino-2.2.0.tgz",
+      "integrity": "sha512-Y28PR25bHXUg88kCV7nivXrP2Nj2RueZ3/l/jdx6J9f8J4nsEGcgX0Qe6lt7Pa+J79+kPiJU3LguR6O/6zrLOw==",
+      "dev": true,
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/@mozilla/readability": {
+      "version": "0.6.0",
+      "resolved": "https://registry.npmjs.org/@mozilla/readability/-/readability-0.6.0.tgz",
+      "integrity": "sha512-juG5VWh4qAivzTAeMzvY9xs9HY5rAcr2E4I7tiSSCokRFi7XIZCAu92ZkSTsIj1OPceCifL3cpfteP3pDT9/QQ==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=14.0.0"
+      }
+    },
     "node_modules/@types/debug": {
       "version": "4.1.12",
       "resolved": "https://registry.npmjs.org/@types/debug/-/debug-4.1.12.tgz",
@@ -615,6 +636,13 @@
         "url": "https://github.com/sponsors/fb55"
       }
     },
+    "node_modules/cssom": {
+      "version": "0.5.0",
+      "resolved": "https://registry.npmjs.org/cssom/-/cssom-0.5.0.tgz",
+      "integrity": "sha512-iKuQcq+NdHqlAcwUY0o/HL69XQrUaQdMjmStJ8JFmUaiiQErlhrmuigkg/CU4E2J0IyUKUrMAgl36TvN67MqTw==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/debug": {
       "version": "4.4.3",
       "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz",
@@ -896,6 +924,13 @@
         "node": ">=12.0.0"
       }
     },
+    "node_modules/html-escaper": {
+      "version": "3.0.3",
+      "resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-3.0.3.tgz",
+      "integrity": "sha512-RuMffC89BOWQoY0WKGpIhn5gX3iI54O6nRA0yC124NYVtzjmFWBIiFd8M0x+ZdX0P9R4lADg1mgP8C7PxGOWuQ==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/htmlparser2": {
       "version": "9.1.0",
       "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-9.1.0.tgz",
@@ -984,6 +1019,51 @@
         "node": ">=18.17"
       }
     },
+    "node_modules/linkedom": {
+      "version": "0.18.12",
+      "resolved": "https://registry.npmjs.org/linkedom/-/linkedom-0.18.12.tgz",
+      "integrity": "sha512-jalJsOwIKuQJSeTvsgzPe9iJzyfVaEJiEXl+25EkKevsULHvMJzpNqwvj1jOESWdmgKDiXObyjOYwlUqG7wo1Q==",
+      "dev": true,
+      "license": "ISC",
+      "dependencies": {
+        "css-select": "^5.1.0",
+        "cssom": "^0.5.0",
+        "html-escaper": "^3.0.3",
+        "htmlparser2": "^10.0.0",
+        "uhyphen": "^0.2.0"
+      },
+      "engines": {
+        "node": ">=16"
+      },
+      "peerDependencies": {
+        "canvas": ">= 2"
+      },
+      "peerDependenciesMeta": {
+        "canvas": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/linkedom/node_modules/htmlparser2": {
+      "version": "10.1.0",
+      "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.1.0.tgz",
+      "integrity": "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ==",
+      "dev": true,
+      "funding": [
+        "https://github.com/fb55/htmlparser2?sponsor=1",
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3",
+        "domutils": "^3.2.2",
+        "entities": "^7.0.1"
+      }
+    },
     "node_modules/longest-streak": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/longest-streak/-/longest-streak-3.1.0.tgz",
@@ -1768,6 +1848,30 @@
         "fsevents": "~2.3.3"
       }
     },
+    "node_modules/turndown": {
+      "version": "7.2.2",
+      "resolved": "https://registry.npmjs.org/turndown/-/turndown-7.2.2.tgz",
+      "integrity": "sha512-1F7db8BiExOKxjSMU2b7if62D/XOyQyZbPKq/nUwopfgnHlqXHqQ0lvfUTeUIr1lZJzOPFn43dODyMSIfvWRKQ==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@mixmark-io/domino": "^2.2.0"
+      }
+    },
+    "node_modules/turndown-plugin-gfm": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/turndown-plugin-gfm/-/turndown-plugin-gfm-1.0.2.tgz",
+      "integrity": "sha512-vwz9tfvF7XN/jE0dGoBei3FXWuvll78ohzCZQuOb+ZjWrs3a0XhQVomJEb2Qh4VHTPNRO4GPZh0V7VRbiWwkRg==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/uhyphen": {
+      "version": "0.2.0",
+      "resolved": "https://registry.npmjs.org/uhyphen/-/uhyphen-0.2.0.tgz",
+      "integrity": "sha512-qz3o9CHXmJJPGBdqzab7qAYuW8kQGKNEuoHFYrBwV6hWIMcpAmxDLXojcHfFr9US1Pe6zUswEIJIbLI610fuqA==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/undici": {
       "version": "6.24.0",
       "resolved": "https://registry.npmjs.org/undici/-/undici-6.24.0.tgz",

package.json

@@ -10,6 +10,10 @@
     "test:coverage": "node --import tsx --experimental-test-coverage --test"
   },
   "devDependencies": {
+    "@mozilla/readability": "^0.6.0",
+    "linkedom": "^0.18.12",
+    "turndown": "^7.2.2",
+    "turndown-plugin-gfm": "^1.0.2",
     "tsx": "^4.20.5"
   }
 }

scripts/sync-clawhub.mjs

@@ -151,6 +151,9 @@ async function main() {
     .map((tag) => tag.trim())
     .filter(Boolean);
 
+  let succeeded = 0;
+  const failed = [];
+
   for (const candidate of actionable) {
     const version =
       candidate.status === "new"
@@ -158,20 +161,30 @@ async function main() {
         : bumpSemver(candidate.latestVersion, options.bump);
 
     console.log(`Publishing ${candidate.slug}@${version}`);
-    const files = await listTextFiles(candidate.folder);
-    await publishSkill({
-      registry,
-      token: config.token,
-      skill: candidate,
-      files,
-      version,
-      changelog: options.changelog,
-      tags,
-    });
+    try {
+      const files = await listTextFiles(candidate.folder);
+      await publishSkill({
+        registry,
+        token: config.token,
+        skill: candidate,
+        files,
+        version,
+        changelog: options.changelog,
+        tags,
+      });
+      succeeded++;
+    } catch (err) {
+      const msg = err instanceof Error ? err.message : String(err);
+      console.error(`SKIPPED ${candidate.slug}: ${msg}`);
+      failed.push(candidate.slug);
+    }
   }
 
   console.log("");
-  console.log(`Uploaded ${actionable.length} skill(s).`);
+  console.log(`Uploaded ${succeeded}/${actionable.length} skill(s).`);
+  if (failed.length > 0) {
+    console.log(`Failed (${failed.length}): ${failed.join(", ")}`);
+  }
 }
 
 function parseArgs(argv) {

skills/baoyu-article-illustrator/SKILL.md

@@ -118,7 +118,7 @@ Full template: [references/workflow.md](references/workflow.md#step-4-generate-o
 
 ⛔ **BLOCKING: Prompt files MUST be saved before ANY image generation.**
 
-**Execution strategy**: When multiple illustrations have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` → `--batchfile`) over spawning subagents. Use subagents only when each image still needs separate prompt iteration or creative exploration.
+**Execution strategy**: When multiple illustrations have saved prompt files and the task is now plain generation, prefer `baoyu-imagine` batch mode (`build-batch.ts` → `--batchfile`) over spawning subagents. Use subagents only when each image still needs separate prompt iteration or creative exploration.
 
 1. For each illustration, create a prompt file per [references/prompt-construction.md](references/prompt-construction.md)
 2. Save to `prompts/NN-{type}-{slug}.md` with YAML frontmatter

skills/baoyu-article-illustrator/references/prompt-construction.md

@@ -280,5 +280,5 @@ TEXTURE: Halftone transitions between sides
 If watermark enabled in preferences, append:
 
 ```
-Include a subtle watermark "[content]" positioned at [position] with approximately [opacity*100]% visibility.
+Include a subtle watermark "[content]" positioned at [position].
 ```

skills/baoyu-article-illustrator/references/workflow.md

@@ -316,7 +316,7 @@ Prompt Files:
 **DO NOT** pass ad-hoc inline text to `--prompt` without first saving prompt files. The generation command should either use `--promptfiles prompts/NN-{type}-{slug}.md` or read the saved file content for `--prompt`.
 
 **Execution choice**:
-- If multiple illustrations already have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` -> `main.ts --batchfile`)
+- If multiple illustrations already have saved prompt files and the task is now plain generation, prefer `baoyu-imagine` batch mode (`build-batch.ts` -> `main.ts --batchfile`)
 - Use subagents only when each illustration still needs separate prompt rewriting, style exploration, or other per-image reasoning before generation
 
 **CRITICAL - References in Frontmatter**:
@@ -352,7 +352,7 @@ Check available skills. If multiple, ask user.
 
 | Skill Supports `--ref` | Action |
 |------------------------|--------|
-| Yes (e.g., baoyu-image-gen with Google) | Pass reference images via `--ref` |
+| Yes (e.g., baoyu-imagine with Google) | Pass reference images via `--ref` |
 | No | Convert to text description, append to prompt |
 
 **Verification**: Before generating, confirm reference processing:

skills/baoyu-article-illustrator/scripts/build-batch.ts

@@ -29,8 +29,8 @@ Options:
   --prompts <path>     Path to prompts directory
   --output <path>      Path to output batch.json
   --images-dir <path>  Directory for generated images
-  --provider <name>    Provider for baoyu-image-gen batch tasks (default: replicate)
-  --model <id>         Model for baoyu-image-gen batch tasks (default: google/nano-banana-pro)
+  --provider <name>    Provider for baoyu-imagine batch tasks (default: replicate)
+  --model <id>         Model for baoyu-imagine batch tasks (default: google/nano-banana-pro)
   --ar <ratio>         Aspect ratio for all tasks (default: 16:9)
   --quality <level>    Quality for all tasks (default: 2k)
   --jobs <count>       Recommended worker count metadata (optional)

skills/baoyu-comic/SKILL.md

@@ -216,7 +216,7 @@ Analyze → [Check Existing?] → [Confirm: Style + Reviews] → Storyboard →
 
 **7.1 Generate character sheet first**:
 - **Backup rule**: If `characters/characters.png` exists, rename to `characters/characters-backup-YYYYMMDD-HHMMSS.png`
-- Invoke an installed image generation skill such as `baoyu-image-gen`
+- Invoke an installed image generation skill such as `baoyu-imagine`
 - Read that skill's `SKILL.md` and follow its documented interface rather than calling its scripts directly
 - Use `characters/characters.md` as the prompt-file input
 - Save output to `characters/characters.png`

skills/baoyu-comic/references/workflow.md

@@ -278,7 +278,7 @@ Create storyboard and character definitions using the confirmed style from Step
 | Role | Character | Visual Description |
 |------|-----------|-------------------|
 | Student | 大雄 (Nobita) | Japanese boy, 10yo, round glasses, black hair parted in middle, yellow shirt, navy shorts |
-| Mentor | 哆啦A梦 (Doraemon) | Round blue robot cat, big white eyes, red nose, whiskers, white belly with 4D pocket, golden bell, no ears |
+| Mentor | 哆啦 A 梦 (Doraemon) | Round blue robot cat, big white eyes, red nose, whiskers, white belly with 4D pocket, golden bell, no ears |
 | Challenge | 胖虎 (Gian) | Stocky boy, rough features, small eyes, orange shirt |
 | Support | 静香 (Shizuka) | Cute girl, black short hair, pink dress, gentle expression |
 
@@ -359,8 +359,7 @@ Art: [art style] | Tone: [tone] | Layout: [layout type]
 **Watermark Application** (if enabled in preferences):
 Add to each prompt:
 ```
-Include a subtle watermark "[content]" positioned at [position]
-with approximately [opacity*100]% visibility. The watermark should
+Include a subtle watermark "[content]" positioned at [position]. The watermark should
 be legible but not distracting from the comic panels and storytelling.
 Ensure watermark does not overlap speech bubbles or key action.
 ```
@@ -434,7 +433,7 @@ With confirmed prompts from Step 5/6:
 | Supports `--ref` | **Strategy A** | Pass `characters/characters.png` with EVERY page |
 | Does NOT support `--ref` | **Strategy B** | Prepend character descriptions to EVERY prompt |
 
-**Strategy A: Using `--ref` parameter** (e.g., baoyu-image-gen)
+**Strategy A: Using `--ref` parameter** (e.g., baoyu-imagine)
 
 - Read the chosen image generation skill's `SKILL.md`
 - Invoke that installed skill via its documented interface, not by calling its scripts directly
@@ -452,8 +451,8 @@ When skill does NOT support reference images, create combined prompt files:
 
 ## Character Reference (maintain consistency)
 [Copy relevant sections from characters/characters.md here]
-- 大雄: Japanese boy, round glasses, yellow shirt, navy shorts...
-- 哆啦A梦: Round blue robot cat, white belly, red nose, golden bell...
+- 大雄：Japanese boy, round glasses, yellow shirt, navy shorts...
+- 哆啦 A 梦：Round blue robot cat, white belly, red nose, golden bell...
 
 ## Page Content
 [Original page prompt here]

skills/baoyu-cover-image/SKILL.md

@@ -162,15 +162,14 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }
 5. **Detect language**: Compare source, user input, EXTEND.md preference
 6. **Determine output directory**: Per File Structure rules
 
-**⚠️ People in Reference Images — MUST follow all 3 rules:**
+**⚠️ People in Reference Images:**
 
 If reference images contain **people** who should appear in the cover:
 
-1. **`usage: direct`** — MUST set in refs description file. NEVER use `style` or `palette` when people need to appear
-2. **Per-character description** — MUST describe each person's distinctive features (hair, glasses, skin tone, clothing) in `refs/ref-NN-{slug}.md`. Vague descriptions like "a man" will fail
-3. **`--ref` flag** — MUST pass reference image via `--ref` in Step 4 so the model sees actual faces
+- **Model supports `--ref`** (default): Copy image to `refs/`, pass via `--ref` at generation. No description file needed — the model sees the face directly.
+- **Model does NOT support `--ref`** (Jimeng, Seedream 3.0): Create `refs/ref-NN-{slug}.md` with per-character description (hair, glasses, skin tone, clothing). Embed as MUST/REQUIRED instructions in prompt text.
 
-See [reference-images.md § Character Analysis](references/workflow/reference-images.md) for description format.
+See [reference-images.md](references/workflow/reference-images.md) for full decision table.
 
 ### Step 2: Confirm Options ⚠️
 

skills/baoyu-cover-image/references/workflow/reference-images.md

@@ -16,17 +16,24 @@ Guide for processing user-provided reference images in cover generation.
 
 **If user provides file path**:
 1. Copy to `refs/ref-NN-{slug}.{ext}` (NN = 01, 02, ...)
-2. Create description: `refs/ref-NN-{slug}.md`
-3. Verify files exist before proceeding
+2. **Only** create description file `refs/ref-NN-{slug}.md` when model does NOT support `--ref` (see below)
+3. Verify image file exists before proceeding
 
-**Description File Format**:
+**When to create description file**:
+
+| Situation | Action |
+|-----------|--------|
+| Model supports `--ref` (Google, OpenAI, OpenRouter, Replicate, Seedream 4.0+) | Copy image only. **No description file needed.** Pass via `--ref` at generation. |
+| Model does NOT support `--ref` (Jimeng, Seedream 3.0) | Copy image + create description file. Embed description in prompt text. |
+
+**Description File Format** (only when needed):
 ```yaml
 ---
 ref_id: NN
 filename: ref-NN-{slug}.{ext}
 usage: direct | style | palette
 ---
-[User's description or auto-generated description]
+[Character or style description to embed in prompt]
 ```
 
 | Usage | When to Use |

skills/baoyu-image-gen/SKILL.md

@@ -1,355 +1,19 @@
 ---
 name: baoyu-image-gen
-description: AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
-version: 1.56.3
-metadata:
-  openclaw:
-    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-image-gen
-    requires:
-      anyBins:
-        - bun
-        - npx
+description: "[DEPRECATED] This skill has been renamed to baoyu-imagine. Triggers on any reference to 'baoyu-image-gen' so users can be guided to upgrade. Use this whenever you detect the old skill name in user prompts, EXTEND.md, or installed skill lists."
 ---
 
-# Image Generation (AI SDK)
+# baoyu-image-gen is now baoyu-imagine
 
-Official API-based image generation. Supports OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Jimeng (即梦), Seedream (豆包) and Replicate providers.
+This skill has been renamed to **baoyu-imagine** with new features and providers.
 
-## Script Directory
+## What to do
 
-**Agent Execution**:
-1. `{baseDir}` = this SKILL.md file's directory
-2. Script path = `{baseDir}/scripts/main.ts`
-3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
+When this skill is triggered, inform the user that `baoyu-image-gen` has been renamed to `baoyu-imagine` with new features and providers, and ask for their confirmation to:
 
-## Step 0: Load Preferences ⛔ BLOCKING
+1. **Install the new skill** from: `https://github.com/JimLiu/baoyu-skills/blob/main/skills/baoyu-imagine/SKILL.md`
+2. **Remove the old `baoyu-image-gen` skill**
 
-**CRITICAL**: This step MUST complete BEFORE any image generation. Do NOT skip or defer.
+No config changes are needed — `baoyu-imagine` reads the same EXTEND.md settings (API keys, default provider, etc.).
 
-Check EXTEND.md existence (priority: project → user):
-
-```bash
-# macOS, Linux, WSL, Git Bash
-test -f .baoyu-skills/baoyu-image-gen/EXTEND.md && echo "project"
-test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "xdg"
-test -f "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "user"
-```
-
-```powershell
-# PowerShell (Windows)
-if (Test-Path .baoyu-skills/baoyu-image-gen/EXTEND.md) { "project" }
-$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
-if (Test-Path "$xdg/baoyu-skills/baoyu-image-gen/EXTEND.md") { "xdg" }
-if (Test-Path "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md") { "user" }
-```
-
-| Result | Action |
-|--------|--------|
-| Found | Load, parse, apply settings. If `default_model.[provider]` is null → ask model only (Flow 2) |
-| Not found | ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save EXTEND.md → Then continue |
-
-**CRITICAL**: If not found, complete the full setup (provider + model + quality + save location) using AskUserQuestion BEFORE generating any images. Generation is BLOCKED until EXTEND.md is created.
-
-| Path | Location |
-|------|----------|
-| `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Project directory |
-| `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | User home |
-
-**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits
-
-Schema: `references/config/preferences-schema.md`
-
-## Usage
-
-```bash
-# Basic
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image cat.png
-
-# With aspect ratio
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9
-
-# High quality
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
-
-# From prompt files
-${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
-
-# With reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0)
-${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
-
-# With reference images (explicit provider/model)
-${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
-
-# OpenRouter (recommended default model)
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openrouter
-
-# OpenRouter with reference images
-${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
-
-# Specific provider
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
-
-# DashScope (阿里通义万象)
-${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
-
-# DashScope Qwen-Image 2.0 Pro (recommended for custom sizes and text rendering)
-${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image out.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
-
-# DashScope legacy Qwen fixed-size model
-${BUN_X} {baseDir}/scripts/main.ts --prompt "一张电影感海报" --image out.png --provider dashscope --model qwen-image-max --size 1664x928
-
-# Replicate (google/nano-banana-pro)
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
-
-# Replicate with specific model
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
-
-# Batch mode with saved prompt files
-${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
-
-# Batch mode with explicit worker count
-${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
-```
-
-### Batch File Format
-
-```json
-{
-  "jobs": 4,
-  "tasks": [
-    {
-      "id": "hero",
-      "promptFiles": ["prompts/hero.md"],
-      "image": "out/hero.png",
-      "provider": "replicate",
-      "model": "google/nano-banana-pro",
-      "ar": "16:9",
-      "quality": "2k"
-    },
-    {
-      "id": "diagram",
-      "promptFiles": ["prompts/diagram.md"],
-      "image": "out/diagram.png",
-      "ref": ["references/original.png"]
-    }
-  ]
-}
-```
-
-Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch file's directory. `jobs` is optional (overridden by CLI `--jobs`). Top-level array format (without `jobs` wrapper) is also accepted.
-
-## Options
-
-| Option | Description |
-|--------|-------------|
-| `--prompt <text>`, `-p` | Prompt text |
-| `--promptfiles <files...>` | Read prompt from files (concatenated) |
-| `--image <path>` | Output image path (required in single-image mode) |
-| `--batchfile <path>` | JSON batch file for multi-image generation |
-| `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |
-| `--provider google\|openai\|openrouter\|dashscope\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
-| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; OpenRouter: `google/gemini-3.1-flash-image-preview`; DashScope: `qwen-image-2.0-pro`) |
-| `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
-| `--size <WxH>` | Size (e.g., `1024x1024`) |
-| `--quality normal\|2k` | Quality preset (default: `2k`) |
-| `--imageSize 1K\|2K\|4K` | Image size for Google/OpenRouter (default: from quality) |
-| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, OpenRouter multimodal models, Replicate, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
-| `--n <count>` | Number of images |
-| `--json` | JSON output |
-
-## Environment Variables
-
-| Variable | Description |
-|----------|-------------|
-| `OPENAI_API_KEY` | OpenAI API key |
-| `OPENROUTER_API_KEY` | OpenRouter API key |
-| `GOOGLE_API_KEY` | Google API key |
-| `DASHSCOPE_API_KEY` | DashScope API key (阿里云) |
-| `REPLICATE_API_TOKEN` | Replicate API token |
-| `JIMENG_ACCESS_KEY_ID` | Jimeng (即梦) Volcengine access key |
-| `JIMENG_SECRET_ACCESS_KEY` | Jimeng (即梦) Volcengine secret key |
-| `ARK_API_KEY` | Seedream (豆包) Volcengine ARK API key |
-| `OPENAI_IMAGE_MODEL` | OpenAI model override |
-| `OPENROUTER_IMAGE_MODEL` | OpenRouter model override (default: `google/gemini-3.1-flash-image-preview`) |
-| `GOOGLE_IMAGE_MODEL` | Google model override |
-| `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: `qwen-image-2.0-pro`) |
-| `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-pro) |
-| `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
-| `SEEDREAM_IMAGE_MODEL` | Seedream model override (default: doubao-seedream-5-0-260128) |
-| `OPENAI_BASE_URL` | Custom OpenAI endpoint |
-| `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint (default: `https://openrouter.ai/api/v1`) |
-| `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution |
-| `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution |
-| `GOOGLE_BASE_URL` | Custom Google endpoint |
-| `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
-| `REPLICATE_BASE_URL` | Custom Replicate endpoint |
-| `JIMENG_BASE_URL` | Custom Jimeng endpoint (default: `https://visual.volcengineapi.com`) |
-| `JIMENG_REGION` | Jimeng region (default: `cn-north-1`) |
-| `SEEDREAM_BASE_URL` | Custom Seedream endpoint (default: `https://ark.cn-beijing.volces.com/api/v3`) |
-| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
-| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
-| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |
-
-**Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`
-
-## Model Resolution
-
-Model priority (highest → lowest), applies to all providers:
-
-1. CLI flag: `--model <id>`
-2. EXTEND.md: `default_model.[provider]`
-3. Env var: `<PROVIDER>_IMAGE_MODEL` (e.g., `GOOGLE_IMAGE_MODEL`)
-4. Built-in default
-
-**EXTEND.md overrides env vars**. If both EXTEND.md `default_model.google: "gemini-3-pro-image-preview"` and env var `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview` exist, EXTEND.md wins.
-
-**Agent MUST display model info** before each generation:
-- Show: `Using [provider] / [model]`
-- Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
-
-### DashScope Models
-
-Use `--model qwen-image-2.0-pro` or set `default_model.dashscope` / `DASHSCOPE_IMAGE_MODEL` when the user wants official Qwen-Image behavior.
-
-Official DashScope model families:
-
-- `qwen-image-2.0-pro`, `qwen-image-2.0-pro-2026-03-03`, `qwen-image-2.0`, `qwen-image-2.0-2026-03-03`
-  - Free-form `size` in `宽*高` format
-  - Total pixels must stay between `512*512` and `2048*2048`
-  - Default size is approximately `1024*1024`
-  - Best choice for custom ratios such as `21:9` and text-heavy Chinese/English layouts
-- `qwen-image-max`, `qwen-image-max-2025-12-30`, `qwen-image-plus`, `qwen-image-plus-2026-01-09`, `qwen-image`
-  - Fixed sizes only: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`
-  - Default size is `1664*928`
-  - `qwen-image` currently has the same capability as `qwen-image-plus`
-- Legacy DashScope models such as `z-image-turbo`, `z-image-ultra`, `wanx-v1`
-  - Keep using them only when the user explicitly asks for legacy behavior or compatibility
-
-When translating CLI args into DashScope behavior:
-
-- `--size` wins over `--ar`
-- For `qwen-image-2.0*`, prefer explicit `--size`; otherwise infer from `--ar` and use the official recommended resolutions below
-- For `qwen-image-max/plus/image`, only use the five official fixed sizes; if the requested ratio is not covered, switch to `qwen-image-2.0-pro`
-- `--quality` is a baoyu-image-gen compatibility preset, not a native DashScope API field. Mapping `normal` / `2k` onto the `qwen-image-2.0*` table below is an implementation inference, not an official API guarantee
-
-Recommended `qwen-image-2.0*` sizes for common aspect ratios:
-
-| Ratio | `normal` | `2k` |
-|-------|----------|------|
-| `1:1` | `1024*1024` | `1536*1536` |
-| `2:3` | `768*1152` | `1024*1536` |
-| `3:2` | `1152*768` | `1536*1024` |
-| `3:4` | `960*1280` | `1080*1440` |
-| `4:3` | `1280*960` | `1440*1080` |
-| `9:16` | `720*1280` | `1080*1920` |
-| `16:9` | `1280*720` | `1920*1080` |
-| `21:9` | `1344*576` | `2048*872` |
-
-DashScope official APIs also expose `negative_prompt`, `prompt_extend`, and `watermark`, but `baoyu-image-gen` does not expose them as dedicated CLI flags today.
-
-Official references:
-
-- [Qwen-Image API](https://help.aliyun.com/zh/model-studio/qwen-image-api)
-- [Text-to-image guide](https://help.aliyun.com/zh/model-studio/text-to-image)
-- [Qwen-Image Edit API](https://help.aliyun.com/zh/model-studio/qwen-image-edit-api)
-
-### OpenRouter Models
-
-Use full OpenRouter model IDs, e.g.:
-
-- `google/gemini-3.1-flash-image-preview` (recommended, supports image output and reference-image workflows)
-- `google/gemini-2.5-flash-image-preview`
-- `black-forest-labs/flux.2-pro`
-- Other OpenRouter image-capable model IDs
-
-Notes:
-
-- OpenRouter image generation uses `/chat/completions`, not the OpenAI `/images` endpoints
-- If `--ref` is used, choose a multimodal model that supports image input and image output
-- `--imageSize` maps to OpenRouter `imageGenerationOptions.size`; `--size <WxH>` is converted to the nearest OpenRouter size and inferred aspect ratio when possible
-
-### Replicate Models
-
-Supported model formats:
-
-- `owner/name` (recommended for official models), e.g. `google/nano-banana-pro`
-- `owner/name:version` (community models by version), e.g. `stability-ai/sdxl:<version>`
-
-Examples:
-
-```bash
-# Use Replicate default model
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
-
-# Override model explicitly
-${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
-```
-
-## Provider Selection
-
-1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI, then OpenRouter, then Replicate (Jimeng and Seedream do not support reference images)
-2. `--provider` specified → use it (if `--ref`, must be `google`, `openai`, `openrouter`, or `replicate`)
-3. Only one API key available → use that provider
-4. Multiple available → default to Google
-
-## Quality Presets
-
-| Preset | Google imageSize | OpenAI Size | OpenRouter size | Replicate resolution | Use Case |
-|--------|------------------|-------------|-----------------|----------------------|----------|
-| `normal` | 1K | 1024px | 1K | 1K | Quick previews |
-| `2k` (default) | 2K | 2048px | 2K | 2K | Covers, illustrations, infographics |
-
-**Google/OpenRouter imageSize**: Can be overridden with `--imageSize 1K|2K|4K`
-
-## Aspect Ratios
-
-Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
-
-- Google multimodal: uses `imageConfig.aspectRatio`
-- OpenAI: maps to closest supported size
-- OpenRouter: sends `imageGenerationOptions.aspect_ratio`; if only `--size <WxH>` is given, aspect ratio is inferred automatically
-- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`
-
-## Generation Mode
-
-**Default**: Sequential generation.
-
-**Batch Parallel Generation**: When `--batchfile` contains 2 or more pending tasks, the script automatically enables parallel generation.
-
-| Mode | When to Use |
-|------|-------------|
-| Sequential (default) | Normal usage, single images, small batches |
-| Parallel batch | Batch mode with 2+ tasks |
-
-Execution choice:
-
-| Situation | Preferred approach | Why |
-|-----------|--------------------|-----|
-| One image, or 1-2 simple images | Sequential | Lower coordination overhead and easier debugging |
-| Multiple images already have saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, and gives predictable throughput |
-| Each image still needs separate reasoning, prompt writing, or style exploration | Subagents | The work is still exploratory, so each image may need independent analysis before generation |
-| Output comes from `baoyu-article-illustrator` with `outline.md` + `prompts/` | Batch (`build-batch.ts` -> `--batchfile`) | That workflow already produces prompt files, so direct batch execution is the intended path |
-
-Rule of thumb:
-
-- Prefer batch over subagents once prompt files are already saved and the task is "generate all of these"
-- Use subagents only when generation is coupled with per-image thinking, rewriting, or divergent creative exploration
-
-Parallel behavior:
-
-- Default worker count is automatic, capped by config, built-in default 10
-- Provider-specific throttling is applied only in batch mode, and the built-in defaults are tuned for faster throughput while still avoiding obvious RPM bursts
-- You can override worker count with `--jobs <count>`
-- Each image retries automatically up to 3 attempts
-- Final output includes success count, failure count, and per-image failure reasons
-
-## Error Handling
-
-- Missing API key → error with setup instructions
-- Generation failure → auto-retry up to 3 attempts per image
-- Invalid aspect ratio → warning, proceed with default
-- Reference images with unsupported provider/model → error with fix hint
-
-## Extension Support
-
-Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.
+Once the user confirms, help them complete the installation and removal using whatever mechanism the current environment supports. If the user also has an image generation request, proceed with `baoyu-imagine` after migration.

skills/baoyu-imagine/SKILL.md

@@ -0,0 +1,408 @@
+---
+name: baoyu-imagine
+description: AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
+version: 1.56.4
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-imagine
+    requires:
+      anyBins:
+        - bun
+        - npx
+---
+
+# Image Generation (AI SDK)
+
+Official API-based image generation. Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate providers.
+
+## Script Directory
+
+**Agent Execution**:
+1. `{baseDir}` = this SKILL.md file's directory
+2. Script path = `{baseDir}/scripts/main.ts`
+3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
+
+## Step 0: Load Preferences ⛔ BLOCKING
+
+**CRITICAL**: This step MUST complete BEFORE any image generation. Do NOT skip or defer.
+
+Check EXTEND.md existence (priority: project → user):
+
+```bash
+# macOS, Linux, WSL, Git Bash
+test -f .baoyu-skills/baoyu-imagine/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-imagine/EXTEND.md" && echo "xdg"
+test -f "$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md" && echo "user"
+```
+
+```powershell
+# PowerShell (Windows)
+if (Test-Path .baoyu-skills/baoyu-imagine/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-imagine/EXTEND.md") { "xdg" }
+if (Test-Path "$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md") { "user" }
+```
+
+| Result | Action |
+|--------|--------|
+| Found | Load, parse, apply settings. If `default_model.[provider]` is null → ask model only (Flow 2) |
+| Not found | ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save EXTEND.md → Then continue |
+
+**CRITICAL**: If not found, complete the full setup (provider + model + quality + save location) using AskUserQuestion BEFORE generating any images. Generation is BLOCKED until EXTEND.md is created.
+
+| Path | Location |
+|------|----------|
+| `.baoyu-skills/baoyu-imagine/EXTEND.md` | Project directory |
+| `$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md` | User home |
+
+Legacy compatibility: if `.baoyu-skills/baoyu-image-gen/EXTEND.md` exists and the new path does not, runtime renames it to `baoyu-imagine`. If both files exist, runtime leaves them unchanged and uses the new path.
+
+**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits
+
+Schema: `references/config/preferences-schema.md`
+
+## Usage
+
+```bash
+# Basic
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image cat.png
+
+# With aspect ratio
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9
+
+# High quality
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
+
+# From prompt files
+${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
+
+# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
+
+# With reference images (explicit provider/model)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
+
+# Azure OpenAI (model means deployment name)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider azure --model gpt-image-1.5
+
+# OpenRouter (recommended default model)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openrouter
+
+# OpenRouter with reference images
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image-preview --ref source.png
+
+# Specific provider
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
+
+# DashScope (阿里通义万象)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
+
+# DashScope Qwen-Image 2.0 Pro (recommended for custom sizes and text rendering)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image out.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
+
+# DashScope legacy Qwen fixed-size model
+${BUN_X} {baseDir}/scripts/main.ts --prompt "一张电影感海报" --image out.png --provider dashscope --model qwen-image-max --size 1664x928
+
+# MiniMax
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
+
+# MiniMax with subject reference (best for character/portrait consistency)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
+
+# MiniMax with custom size (documented for image-01)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cinematic poster" --image out.jpg --provider minimax --model image-01 --size 1536x1024
+
+# Replicate (google/nano-banana-pro)
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
+
+# Replicate with specific model
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+
+# Batch mode with saved prompt files
+${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
+
+# Batch mode with explicit worker count
+${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
+```
+
+### Batch File Format
+
+```json
+{
+  "jobs": 4,
+  "tasks": [
+    {
+      "id": "hero",
+      "promptFiles": ["prompts/hero.md"],
+      "image": "out/hero.png",
+      "provider": "replicate",
+      "model": "google/nano-banana-pro",
+      "ar": "16:9",
+      "quality": "2k"
+    },
+    {
+      "id": "diagram",
+      "promptFiles": ["prompts/diagram.md"],
+      "image": "out/diagram.png",
+      "ref": ["references/original.png"]
+    }
+  ]
+}
+```
+
+Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch file's directory. `jobs` is optional (overridden by CLI `--jobs`). Top-level array format (without `jobs` wrapper) is also accepted.
+
+## Options
+
+| Option | Description |
+|--------|-------------|
+| `--prompt <text>`, `-p` | Prompt text |
+| `--promptfiles <files...>` | Read prompt from files (concatenated) |
+| `--image <path>` | Output image path (required in single-image mode) |
+| `--batchfile <path>` | JSON batch file for multi-image generation |
+| `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |
+| `--provider google\|openai\|azure\|openrouter\|dashscope\|minimax\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
+| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; Azure: deployment name such as `gpt-image-1.5` or `image-prod`; OpenRouter: `google/gemini-3.1-flash-image-preview`; DashScope: `qwen-image-2.0-pro`; MiniMax: `image-01`) |
+| `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
+| `--size <WxH>` | Size (e.g., `1024x1024`) |
+| `--quality normal\|2k` | Quality preset (default: `2k`) |
+| `--imageSize 1K\|2K\|4K` | Image size for Google/OpenRouter (default: from quality) |
+| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits (PNG/JPG only), OpenRouter multimodal models, Replicate, MiniMax subject-reference, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
+| `--n <count>` | Number of images |
+| `--json` | JSON output |
+
+## Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `OPENAI_API_KEY` | OpenAI API key |
+| `AZURE_OPENAI_API_KEY` | Azure OpenAI API key |
+| `OPENROUTER_API_KEY` | OpenRouter API key |
+| `GOOGLE_API_KEY` | Google API key |
+| `DASHSCOPE_API_KEY` | DashScope API key (阿里云) |
+| `MINIMAX_API_KEY` | MiniMax API key |
+| `REPLICATE_API_TOKEN` | Replicate API token |
+| `JIMENG_ACCESS_KEY_ID` | Jimeng (即梦) Volcengine access key |
+| `JIMENG_SECRET_ACCESS_KEY` | Jimeng (即梦) Volcengine secret key |
+| `ARK_API_KEY` | Seedream (豆包) Volcengine ARK API key |
+| `OPENAI_IMAGE_MODEL` | OpenAI model override |
+| `AZURE_OPENAI_DEPLOYMENT` | Azure default deployment name |
+| `AZURE_OPENAI_IMAGE_MODEL` | Backward-compatible alias for Azure default deployment/model name |
+| `OPENROUTER_IMAGE_MODEL` | OpenRouter model override (default: `google/gemini-3.1-flash-image-preview`) |
+| `GOOGLE_IMAGE_MODEL` | Google model override |
+| `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: `qwen-image-2.0-pro`) |
+| `MINIMAX_IMAGE_MODEL` | MiniMax model override (default: `image-01`) |
+| `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-pro) |
+| `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
+| `SEEDREAM_IMAGE_MODEL` | Seedream model override (default: doubao-seedream-5-0-260128) |
+| `OPENAI_BASE_URL` | Custom OpenAI endpoint |
+| `AZURE_OPENAI_BASE_URL` | Azure resource endpoint or deployment endpoint |
+| `AZURE_API_VERSION` | Azure image API version (default: `2025-04-01-preview`) |
+| `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint (default: `https://openrouter.ai/api/v1`) |
+| `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution |
+| `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution |
+| `GOOGLE_BASE_URL` | Custom Google endpoint |
+| `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
+| `MINIMAX_BASE_URL` | Custom MiniMax endpoint (default: `https://api.minimax.io`) |
+| `REPLICATE_BASE_URL` | Custom Replicate endpoint |
+| `JIMENG_BASE_URL` | Custom Jimeng endpoint (default: `https://visual.volcengineapi.com`) |
+| `JIMENG_REGION` | Jimeng region (default: `cn-north-1`) |
+| `SEEDREAM_BASE_URL` | Custom Seedream endpoint (default: `https://ark.cn-beijing.volces.com/api/v3`) |
+| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |
+
+**Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`
+
+## Model Resolution
+
+Model priority (highest → lowest), applies to all providers:
+
+1. CLI flag: `--model <id>`
+2. EXTEND.md: `default_model.[provider]`
+3. Env var: `<PROVIDER>_IMAGE_MODEL` (e.g., `GOOGLE_IMAGE_MODEL`)
+4. Built-in default
+
+For Azure, `--model` / `default_model.azure` should be the Azure deployment name. `AZURE_OPENAI_DEPLOYMENT` is the preferred env var, and `AZURE_OPENAI_IMAGE_MODEL` remains as a backward-compatible alias.
+
+**EXTEND.md overrides env vars**. If both EXTEND.md `default_model.google: "gemini-3-pro-image-preview"` and env var `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview` exist, EXTEND.md wins.
+
+**Agent MUST display model info** before each generation:
+- Show: `Using [provider] / [model]`
+- Show switch hint: `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`
+
+### DashScope Models
+
+Use `--model qwen-image-2.0-pro` or set `default_model.dashscope` / `DASHSCOPE_IMAGE_MODEL` when the user wants official Qwen-Image behavior.
+
+Official DashScope model families:
+
+- `qwen-image-2.0-pro`, `qwen-image-2.0-pro-2026-03-03`, `qwen-image-2.0`, `qwen-image-2.0-2026-03-03`
+  - Free-form `size` in `宽*高` format
+  - Total pixels must stay between `512*512` and `2048*2048`
+  - Default size is approximately `1024*1024`
+  - Best choice for custom ratios such as `21:9` and text-heavy Chinese/English layouts
+- `qwen-image-max`, `qwen-image-max-2025-12-30`, `qwen-image-plus`, `qwen-image-plus-2026-01-09`, `qwen-image`
+  - Fixed sizes only: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`
+  - Default size is `1664*928`
+  - `qwen-image` currently has the same capability as `qwen-image-plus`
+- Legacy DashScope models such as `z-image-turbo`, `z-image-ultra`, `wanx-v1`
+  - Keep using them only when the user explicitly asks for legacy behavior or compatibility
+
+When translating CLI args into DashScope behavior:
+
+- `--size` wins over `--ar`
+- For `qwen-image-2.0*`, prefer explicit `--size`; otherwise infer from `--ar` and use the official recommended resolutions below
+- For `qwen-image-max/plus/image`, only use the five official fixed sizes; if the requested ratio is not covered, switch to `qwen-image-2.0-pro`
+- `--quality` is a baoyu-imagine compatibility preset, not a native DashScope API field. Mapping `normal` / `2k` onto the `qwen-image-2.0*` table below is an implementation inference, not an official API guarantee
+
+Recommended `qwen-image-2.0*` sizes for common aspect ratios:
+
+| Ratio | `normal` | `2k` |
+|-------|----------|------|
+| `1:1` | `1024*1024` | `1536*1536` |
+| `2:3` | `768*1152` | `1024*1536` |
+| `3:2` | `1152*768` | `1536*1024` |
+| `3:4` | `960*1280` | `1080*1440` |
+| `4:3` | `1280*960` | `1440*1080` |
+| `9:16` | `720*1280` | `1080*1920` |
+| `16:9` | `1280*720` | `1920*1080` |
+| `21:9` | `1344*576` | `2048*872` |
+
+DashScope official APIs also expose `negative_prompt`, `prompt_extend`, and `watermark`, but `baoyu-imagine` does not expose them as dedicated CLI flags today.
+
+Official references:
+
+- [Qwen-Image API](https://help.aliyun.com/zh/model-studio/qwen-image-api)
+- [Text-to-image guide](https://help.aliyun.com/zh/model-studio/text-to-image)
+- [Qwen-Image Edit API](https://help.aliyun.com/zh/model-studio/qwen-image-edit-api)
+
+### MiniMax Models
+
+Use `--model image-01` or set `default_model.minimax` / `MINIMAX_IMAGE_MODEL` when the user wants MiniMax image generation.
+
+Official MiniMax image model options currently documented in the API reference:
+
+- `image-01` (recommended default)
+  - Supports text-to-image and subject-reference image generation
+  - Supports official `aspect_ratio` values: `1:1`, `16:9`, `4:3`, `3:2`, `2:3`, `3:4`, `9:16`, `21:9`
+  - Supports documented custom `width` / `height` output sizes when using `--size <WxH>`
+  - `width` and `height` must both be between `512` and `2048`, and both must be divisible by `8`
+- `image-01-live`
+  - Lower-latency variant
+  - Use `--ar` for sizing; MiniMax documents custom `width` / `height` as only effective for `image-01`
+
+MiniMax subject reference notes:
+
+- `--ref` files are sent as MiniMax `subject_reference`
+- MiniMax docs currently describe `subject_reference[].type` as `character`
+- Official docs say `image_file` supports public URLs or Base64 Data URLs; `baoyu-imagine` sends local refs as Data URLs
+- Official docs recommend front-facing portrait references in JPG/JPEG/PNG under 10MB
+
+Official references:
+
+- [MiniMax Image Generation Guide](https://platform.minimax.io/docs/guides/image-generation)
+- [MiniMax Text-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-t2i)
+- [MiniMax Image-to-Image API](https://platform.minimax.io/docs/api-reference/image-generation-i2i)
+
+### OpenRouter Models
+
+Use full OpenRouter model IDs, e.g.:
+
+- `google/gemini-3.1-flash-image-preview` (recommended, supports image output and reference-image workflows)
+- `google/gemini-2.5-flash-image-preview`
+- `black-forest-labs/flux.2-pro`
+- Other OpenRouter image-capable model IDs
+
+Notes:
+
+- OpenRouter image generation uses `/chat/completions`, not the OpenAI `/images` endpoints
+- If `--ref` is used, choose a multimodal model that supports image input and image output
+- `--imageSize` maps to OpenRouter `imageGenerationOptions.size`; `--size <WxH>` is converted to the nearest OpenRouter size and inferred aspect ratio when possible
+
+### Replicate Models
+
+Supported model formats:
+
+- `owner/name` (recommended for official models), e.g. `google/nano-banana-pro`
+- `owner/name:version` (community models by version), e.g. `stability-ai/sdxl:<version>`
+
+Examples:
+
+```bash
+# Use Replicate default model
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
+
+# Override model explicitly
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+```
+
+## Provider Selection
+
+1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI, then Azure, then OpenRouter, then Replicate, then Seedream, then MiniMax (MiniMax subject reference is more specialized toward character/portrait consistency)
+2. `--provider` specified → use it (if `--ref`, must be `google`, `openai`, `azure`, `openrouter`, `replicate`, `seedream`, or `minimax`)
+3. Only one API key available → use that provider
+4. Multiple available → default to Google
+
+## Quality Presets
+
+| Preset | Google imageSize | OpenAI Size | OpenRouter size | Replicate resolution | Use Case |
+|--------|------------------|-------------|-----------------|----------------------|----------|
+| `normal` | 1K | 1024px | 1K | 1K | Quick previews |
+| `2k` (default) | 2K | 2048px | 2K | 2K | Covers, illustrations, infographics |
+
+**Google/OpenRouter imageSize**: Can be overridden with `--imageSize 1K|2K|4K`
+
+## Aspect Ratios
+
+Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
+
+- Google multimodal: uses `imageConfig.aspectRatio`
+- OpenAI: maps to closest supported size
+- OpenRouter: sends `imageGenerationOptions.aspect_ratio`; if only `--size <WxH>` is given, aspect ratio is inferred automatically
+- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`
+- MiniMax: sends official `aspect_ratio` values directly; if `--size <WxH>` is given without `--ar`, `width` / `height` are sent for `image-01`
+
+## Generation Mode
+
+**Default**: Sequential generation.
+
+**Batch Parallel Generation**: When `--batchfile` contains 2 or more pending tasks, the script automatically enables parallel generation.
+
+| Mode | When to Use |
+|------|-------------|
+| Sequential (default) | Normal usage, single images, small batches |
+| Parallel batch | Batch mode with 2+ tasks |
+
+Execution choice:
+
+| Situation | Preferred approach | Why |
+|-----------|--------------------|-----|
+| One image, or 1-2 simple images | Sequential | Lower coordination overhead and easier debugging |
+| Multiple images already have saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, and gives predictable throughput |
+| Each image still needs separate reasoning, prompt writing, or style exploration | Subagents | The work is still exploratory, so each image may need independent analysis before generation |
+| Output comes from `baoyu-article-illustrator` with `outline.md` + `prompts/` | Batch (`build-batch.ts` -> `--batchfile`) | That workflow already produces prompt files, so direct batch execution is the intended path |
+
+Rule of thumb:
+
+- Prefer batch over subagents once prompt files are already saved and the task is "generate all of these"
+- Use subagents only when generation is coupled with per-image thinking, rewriting, or divergent creative exploration
+
+Parallel behavior:
+
+- Default worker count is automatic, capped by config, built-in default 10
+- Provider-specific throttling is applied only in batch mode, and the built-in defaults are tuned for faster throughput while still avoiding obvious RPM bursts
+- You can override worker count with `--jobs <count>`
+- Each image retries automatically up to 3 attempts
+- Final output includes success count, failure count, and per-image failure reasons
+
+## Error Handling
+
+- Missing API key → error with setup instructions
+- Generation failure → auto-retry up to 3 attempts per image
+- Invalid aspect ratio → warning, proceed with default
+- Reference images with unsupported provider/model → error with fix hint
+
+## Extension Support
+
+Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.

skills/baoyu-imagine/references/config/first-time-setup.md

@@ -1,6 +1,6 @@
 ---
 name: first-time-setup
-description: First-time setup and default model selection flow for baoyu-image-gen
+description: First-time setup and default model selection flow for baoyu-imagine
 ---
 
 # First-Time Setup
@@ -47,10 +47,14 @@ options:
     description: "Gemini multimodal - high quality, reference images, flexible sizes"
   - label: "OpenAI"
     description: "GPT Image - consistent quality, reliable output"
+  - label: "Azure OpenAI"
+    description: "Azure-hosted GPT Image deployments with resource-specific routing"
   - label: "OpenRouter"
     description: "Router for Gemini/FLUX/OpenAI-compatible image models"
   - label: "DashScope"
     description: "Alibaba Cloud - Qwen-Image, strong Chinese/English text rendering"
+  - label: "MiniMax"
+    description: "MiniMax image generation with subject-reference character workflows"
   - label: "Replicate"
     description: "Community models - nano-banana-pro, flexible model selection"
 ```
@@ -87,6 +91,34 @@ options:
     description: "Strong text-to-image quality through OpenRouter"
 ```
 
+### Question 2c: Default Azure Deployment
+
+Only show if user selected Azure OpenAI.
+
+```yaml
+header: "Azure Deploy"
+question: "Default Azure image deployment name?"
+options:
+  - label: "gpt-image-1.5 (Recommended)"
+    description: "Best default if your Azure deployment uses the same name"
+  - label: "gpt-image-1"
+    description: "Previous GPT Image deployment name"
+```
+
+### Question 2d: Default MiniMax Model
+
+Only show if user selected MiniMax.
+
+```yaml
+header: "MiniMax Model"
+question: "Default MiniMax image generation model?"
+options:
+  - label: "image-01 (Recommended)"
+    description: "Best default, supports aspect ratios and custom width/height"
+  - label: "image-01-live"
+    description: "Faster variant, use aspect ratio instead of custom size"
+```
+
 ### Question 3: Default Quality
 
 ```yaml
@@ -115,8 +147,8 @@ options:
 
 | Choice | Path | Scope |
 |--------|------|-------|
-| Project | `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Current project |
-| User | `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | All projects |
+| Project | `.baoyu-skills/baoyu-imagine/EXTEND.md` | Current project |
+| User | `$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md` | All projects |
 
 ### EXTEND.md Template
 
@@ -130,8 +162,10 @@ default_image_size: null
 default_model:
   google: [selected google model or null]
   openai: null
+  azure: [selected azure deployment or null]
   openrouter: [selected openrouter model or null]
   dashscope: null
+  minimax: [selected minimax model or null]
   replicate: null
 ---
 ```
@@ -166,6 +200,23 @@ options:
     description: "Previous generation GPT Image model"
 ```
 
+### Azure Deployment Selection
+
+```yaml
+header: "Azure Deploy"
+question: "Choose a default Azure image deployment name?"
+options:
+  - label: "gpt-image-1.5 (Recommended)"
+    description: "Use when your Azure deployment name matches the GPT-image-1.5 model"
+  - label: "gpt-image-1"
+    description: "Use when your Azure deployment name matches GPT-image-1"
+```
+
+Notes for Azure setup:
+
+- In `baoyu-imagine`, Azure `--model` / `default_model.azure` should be the Azure deployment name, not just the underlying model family.
+- If the deployment name is custom, save that exact deployment name in `default_model.azure`.
+
 ### OpenRouter Model Selection
 
 ```yaml
@@ -204,7 +255,7 @@ Notes for DashScope setup:
 
 - Prefer `qwen-image-2.0-pro` when the user needs custom `--size`, uncommon ratios like `21:9`, or strong Chinese/English text rendering.
 - `qwen-image-max` / `qwen-image-plus` / `qwen-image` only support five fixed sizes: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`.
-- In `baoyu-image-gen`, `quality` is a compatibility preset. It is not a native DashScope parameter.
+- In `baoyu-imagine`, `quality` is a compatibility preset. It is not a native DashScope parameter.
 
 ### Replicate Model Selection
 
@@ -218,6 +269,24 @@ options:
     description: "Google's base image model on Replicate"
 ```
 
+### MiniMax Model Selection
+
+```yaml
+header: "MiniMax Model"
+question: "Choose a default MiniMax image generation model?"
+options:
+  - label: "image-01 (Recommended)"
+    description: "Best general-purpose MiniMax image model with custom width/height support"
+  - label: "image-01-live"
+    description: "Lower-latency MiniMax image model using aspect ratios"
+```
+
+Notes for MiniMax setup:
+
+- `image-01` is the safest default. It supports official `aspect_ratio` values and documented custom `width` / `height` output sizes.
+- `image-01-live` is useful when the user prefers faster generation and can work with aspect-ratio-based sizing.
+- MiniMax subject reference currently uses `subject_reference[].type = character`; docs recommend front-facing portrait references in JPG/JPEG/PNG under 10MB.
+
 ### Update EXTEND.md
 
 After user selects a model:
@@ -230,8 +299,10 @@ After user selects a model:
 default_model:
   google: [value or null]
   openai: [value or null]
+  azure: [value or null]
   openrouter: [value or null]
   dashscope: [value or null]
+  minimax: [value or null]
   replicate: [value or null]
 ```
 

skills/baoyu-imagine/references/config/preferences-schema.md

@@ -1,6 +1,6 @@
 ---
 name: preferences-schema
-description: EXTEND.md YAML schema for baoyu-image-gen user preferences
+description: EXTEND.md YAML schema for baoyu-imagine user preferences
 ---
 
 # Preferences Schema
@@ -11,7 +11,7 @@ description: EXTEND.md YAML schema for baoyu-image-gen user preferences
 ---
 version: 1
 
-default_provider: null      # google|openai|openrouter|dashscope|replicate|null (null = auto-detect)
+default_provider: null      # google|openai|azure|openrouter|dashscope|minimax|replicate|null (null = auto-detect)
 
 default_quality: null       # normal|2k|null (null = use default: 2k)
 
@@ -22,8 +22,10 @@ default_image_size: null    # 1K|2K|4K|null (Google/OpenRouter, overrides qualit
 default_model:
   google: null              # e.g., "gemini-3-pro-image-preview", "gemini-3.1-flash-image-preview"
   openai: null              # e.g., "gpt-image-1.5", "gpt-image-1"
+  azure: null               # Azure deployment name, e.g., "gpt-image-1.5" or "image-prod"
   openrouter: null          # e.g., "google/gemini-3.1-flash-image-preview"
   dashscope: null           # e.g., "qwen-image-2.0-pro"
+  minimax: null             # e.g., "image-01"
   replicate: null           # e.g., "google/nano-banana-pro"
 
 batch:
@@ -38,12 +40,18 @@ batch:
     openai:
       concurrency: 3
       start_interval_ms: 1100
+    azure:
+      concurrency: 3
+      start_interval_ms: 1100
     openrouter:
       concurrency: 3
       start_interval_ms: 1100
     dashscope:
       concurrency: 3
       start_interval_ms: 1100
+    minimax:
+      concurrency: 3
+      start_interval_ms: 1100
 ---
 ```
 
@@ -58,8 +66,10 @@ batch:
 | `default_image_size` | string\|null | null | Google/OpenRouter image size (overrides quality) |
 | `default_model.google` | string\|null | null | Google default model |
 | `default_model.openai` | string\|null | null | OpenAI default model |
+| `default_model.azure` | string\|null | null | Azure default deployment name |
 | `default_model.openrouter` | string\|null | null | OpenRouter default model |
 | `default_model.dashscope` | string\|null | null | DashScope default model |
+| `default_model.minimax` | string\|null | null | MiniMax default model |
 | `default_model.replicate` | string\|null | null | Replicate default model |
 | `batch.max_workers` | int\|null | 10 | Batch worker cap |
 | `batch.provider_limits.<provider>.concurrency` | int\|null | provider default | Max simultaneous requests per provider |
@@ -87,8 +97,10 @@ default_image_size: 2K
 default_model:
   google: "gemini-3-pro-image-preview"
   openai: "gpt-image-1.5"
+  azure: "gpt-image-1.5"
   openrouter: "google/gemini-3.1-flash-image-preview"
   dashscope: "qwen-image-2.0-pro"
+  minimax: "image-01"
   replicate: "google/nano-banana-pro"
 batch:
   max_workers: 10
@@ -96,8 +108,14 @@ batch:
     replicate:
       concurrency: 5
       start_interval_ms: 700
+    azure:
+      concurrency: 3
+      start_interval_ms: 1100
     openrouter:
       concurrency: 3
       start_interval_ms: 1100
+    minimax:
+      concurrency: 3
+      start_interval_ms: 1100
 ---
 ```

skills/baoyu-imagine/scripts/main.test.ts

@@ -13,6 +13,7 @@ import {
   getWorkerCount,
   isRetryableGenerationError,
   loadBatchTasks,
+  loadExtendConfig,
   mergeConfig,
   normalizeOutputImagePath,
   parseArgs,
@@ -69,7 +70,7 @@ async function makeTempDir(prefix: string): Promise<string> {
   return fs.mkdtemp(path.join(os.tmpdir(), prefix));
 }
 
-test("parseArgs parses the main image-gen CLI flags", () => {
+test("parseArgs parses the main baoyu-imagine CLI flags", () => {
   const args = parseArgs([
     "--promptfiles",
     "prompts/system.md",
@@ -123,6 +124,8 @@ default_image_size: 2K
 default_model:
   google: gemini-3-pro-image-preview
   openai: gpt-image-1.5
+  azure: image-prod
+  minimax: image-01
 batch:
   max_workers: 8
   provider_limits:
@@ -131,6 +134,12 @@ batch:
       start_interval_ms: 900
     openai:
       concurrency: 4
+    minimax:
+      concurrency: 2
+      start_interval_ms: 1400
+    azure:
+      concurrency: 1
+      start_interval_ms: 1500
 `;
 
   const config = parseSimpleYaml(yaml);
@@ -142,6 +151,8 @@ batch:
   assert.equal(config.default_image_size, "2K");
   assert.equal(config.default_model?.google, "gemini-3-pro-image-preview");
   assert.equal(config.default_model?.openai, "gpt-image-1.5");
+  assert.equal(config.default_model?.azure, "image-prod");
+  assert.equal(config.default_model?.minimax, "image-01");
   assert.equal(config.batch?.max_workers, 8);
   assert.deepEqual(config.batch?.provider_limits?.google, {
     concurrency: 2,
@@ -150,6 +161,69 @@ batch:
   assert.deepEqual(config.batch?.provider_limits?.openai, {
     concurrency: 4,
   });
+  assert.deepEqual(config.batch?.provider_limits?.minimax, {
+    concurrency: 2,
+    start_interval_ms: 1400,
+  });
+  assert.deepEqual(config.batch?.provider_limits?.azure, {
+    concurrency: 1,
+    start_interval_ms: 1500,
+  });
+});
+
+test("loadExtendConfig renames legacy EXTEND.md when the new path is missing", async () => {
+  const root = await makeTempDir("baoyu-imagine-extend-");
+  const cwd = path.join(root, "project");
+  const home = path.join(root, "home");
+  const legacyPath = path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md");
+  const currentPath = path.join(cwd, ".baoyu-skills", "baoyu-imagine", "EXTEND.md");
+
+  await fs.mkdir(path.dirname(legacyPath), { recursive: true });
+  await fs.mkdir(home, { recursive: true });
+  await fs.writeFile(legacyPath, `---
+default_provider: google
+default_quality: 2k
+---
+`);
+
+  const config = await loadExtendConfig(cwd, home);
+
+  assert.equal(config.default_provider, "google");
+  assert.equal(config.default_quality, "2k");
+  await fs.access(currentPath);
+  await assert.rejects(() => fs.access(legacyPath));
+});
+
+test("loadExtendConfig leaves legacy EXTEND.md untouched when both paths exist", async () => {
+  const root = await makeTempDir("baoyu-imagine-extend-dual-");
+  const cwd = path.join(root, "project");
+  const home = path.join(root, "home");
+  const legacyPath = path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md");
+  const currentPath = path.join(cwd, ".baoyu-skills", "baoyu-imagine", "EXTEND.md");
+
+  await fs.mkdir(path.dirname(legacyPath), { recursive: true });
+  await fs.mkdir(path.dirname(currentPath), { recursive: true });
+  await fs.mkdir(home, { recursive: true });
+  await fs.writeFile(legacyPath, `---
+default_provider: google
+---
+`);
+  await fs.writeFile(currentPath, `---
+default_provider: openai
+---
+`);
+
+  const config = await loadExtendConfig(cwd, home);
+
+  assert.equal(config.default_provider, "openai");
+  assert.equal(await fs.readFile(legacyPath, "utf8"), `---
+default_provider: google
+---
+`);
+  assert.equal(await fs.readFile(currentPath, "utf8"), `---
+default_provider: openai
+---
+`);
 });
 
 test("mergeConfig only fills values missing from CLI args", () => {
@@ -191,6 +265,7 @@ test("detectProvider rejects non-ref-capable providers and prefers Google first
     OPENAI_API_KEY: "openai-key",
     OPENROUTER_API_KEY: null,
     DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
     REPLICATE_API_TOKEN: null,
     JIMENG_ACCESS_KEY_ID: null,
     JIMENG_SECRET_ACCESS_KEY: null,
@@ -203,8 +278,11 @@ test("detectProvider selects an available ref-capable provider for reference-ima
   useEnv(t, {
     GOOGLE_API_KEY: null,
     OPENAI_API_KEY: "openai-key",
+    AZURE_OPENAI_API_KEY: null,
+    AZURE_OPENAI_BASE_URL: null,
     OPENROUTER_API_KEY: null,
     DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
     REPLICATE_API_TOKEN: null,
     JIMENG_ACCESS_KEY_ID: null,
     JIMENG_SECRET_ACCESS_KEY: null,
@@ -216,12 +294,35 @@ test("detectProvider selects an available ref-capable provider for reference-ima
   );
 });
 
+test("detectProvider selects Azure when only Azure credentials are configured", (t) => {
+  useEnv(t, {
+    GOOGLE_API_KEY: null,
+    OPENAI_API_KEY: null,
+    AZURE_OPENAI_API_KEY: "azure-key",
+    AZURE_OPENAI_BASE_URL: "https://example.openai.azure.com",
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: null,
+  });
+
+  assert.equal(detectProvider(makeArgs()), "azure");
+  assert.equal(
+    detectProvider(makeArgs({ referenceImages: ["ref.png"] })),
+    "azure",
+  );
+});
+
 test("detectProvider infers Seedream from model id and allows Seedream reference-image workflows", (t) => {
   useEnv(t, {
     GOOGLE_API_KEY: null,
     OPENAI_API_KEY: null,
     OPENROUTER_API_KEY: null,
     DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: null,
     REPLICATE_API_TOKEN: null,
     JIMENG_ACCESS_KEY_ID: null,
     JIMENG_SECRET_ACCESS_KEY: null,
@@ -249,6 +350,26 @@ test("detectProvider infers Seedream from model id and allows Seedream reference
   );
 });
 
+test("detectProvider selects MiniMax when only MiniMax credentials are configured or the model id matches", (t) => {
+  useEnv(t, {
+    GOOGLE_API_KEY: null,
+    OPENAI_API_KEY: null,
+    AZURE_OPENAI_API_KEY: null,
+    AZURE_OPENAI_BASE_URL: null,
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    MINIMAX_API_KEY: "minimax-key",
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: null,
+  });
+
+  assert.equal(detectProvider(makeArgs()), "minimax");
+  assert.equal(detectProvider(makeArgs({ referenceImages: ["ref.png"] })), "minimax");
+  assert.equal(detectProvider(makeArgs({ model: "image-01-live" })), "minimax");
+});
+
 test("batch worker and provider-rate-limit configuration prefer env over EXTEND config", (t) => {
   useEnv(t, {
     BAOYU_IMAGE_GEN_MAX_WORKERS: "12",
@@ -264,6 +385,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
           concurrency: 2,
           start_interval_ms: 900,
         },
+        minimax: {
+          concurrency: 1,
+          start_interval_ms: 1500,
+        },
       },
     },
   };
@@ -273,10 +398,14 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
     concurrency: 5,
     startIntervalMs: 450,
   });
+  assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).minimax, {
+    concurrency: 1,
+    startIntervalMs: 1500,
+  });
 });
 
 test("loadBatchTasks and createTaskArgs resolve batch-relative paths", async (t) => {
-  const root = await makeTempDir("baoyu-image-gen-batch-");
+  const root = await makeTempDir("baoyu-imagine-batch-");
   t.after(() => fs.rm(root, { recursive: true, force: true }));
 
   const batchFile = path.join(root, "jobs", "batch.json");

skills/baoyu-imagine/scripts/main.ts

@@ -2,7 +2,7 @@ import path from "node:path";
 import process from "node:process";
 import { homedir } from "node:os";
 import { fileURLToPath } from "node:url";
-import { access, mkdir, readFile, writeFile } from "node:fs/promises";
+import { access, mkdir, readFile, rename, writeFile } from "node:fs/promises";
 import type {
   BatchFile,
   BatchTaskInput,
@@ -58,8 +58,10 @@ const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
   openai: { concurrency: 3, startIntervalMs: 1100 },
   openrouter: { concurrency: 3, startIntervalMs: 1100 },
   dashscope: { concurrency: 3, startIntervalMs: 1100 },
+  minimax: { concurrency: 3, startIntervalMs: 1100 },
   jimeng: { concurrency: 3, startIntervalMs: 1100 },
   seedream: { concurrency: 3, startIntervalMs: 1100 },
+  azure: { concurrency: 3, startIntervalMs: 1100 },
 };
 
 function printUsage(): void {
@@ -74,13 +76,13 @@ Options:
   --image <path>            Output image path (required in single-image mode)
   --batchfile <path>        JSON batch file for multi-image generation
   --jobs <count>            Worker count for batch mode (default: auto, max from config, built-in default 10)
-  --provider google|openai|openrouter|dashscope|replicate|jimeng|seedream  Force provider (auto-detect by default)
+  --provider google|openai|openrouter|dashscope|minimax|replicate|jimeng|seedream|azure  Force provider (auto-detect by default)
   -m, --model <id>          Model ID
   --ar <ratio>              Aspect ratio (e.g., 16:9, 1:1, 4:3)
   --size <WxH>              Size (e.g., 1024x1024)
   --quality normal|2k       Quality preset (default: 2k)
   --imageSize 1K|2K|4K      Image size for Google/OpenRouter (default: from quality)
-  --ref <files...>          Reference images (Google, OpenAI, OpenRouter, Replicate, or Seedream 4.0/4.5/5.0)
+  --ref <files...>          Reference images (Google, OpenAI, Azure, OpenRouter, Replicate, MiniMax, or Seedream 4.0/4.5/5.0)
   --n <count>               Number of images for the current task (default: 1)
   --json                    JSON output
   -h, --help                Show help
@@ -111,6 +113,7 @@ Environment variables:
   GOOGLE_API_KEY            Google API key
   GEMINI_API_KEY            Gemini API key (alias for GOOGLE_API_KEY)
   DASHSCOPE_API_KEY         DashScope API key
+  MINIMAX_API_KEY           MiniMax API key
   REPLICATE_API_TOKEN       Replicate API token
   JIMENG_ACCESS_KEY_ID      Jimeng Access Key ID
   JIMENG_SECRET_ACCESS_KEY  Jimeng Secret Access Key
@@ -119,6 +122,7 @@ Environment variables:
   OPENROUTER_IMAGE_MODEL    Default OpenRouter model (google/gemini-3.1-flash-image-preview)
   GOOGLE_IMAGE_MODEL        Default Google model (gemini-3-pro-image-preview)
   DASHSCOPE_IMAGE_MODEL     Default DashScope model (qwen-image-2.0-pro)
+  MINIMAX_IMAGE_MODEL       Default MiniMax model (image-01)
   REPLICATE_IMAGE_MODEL     Default Replicate model (google/nano-banana-pro)
   JIMENG_IMAGE_MODEL        Default Jimeng model (jimeng_t2i_v40)
   SEEDREAM_IMAGE_MODEL      Default Seedream model (doubao-seedream-5-0-260128)
@@ -129,8 +133,14 @@ Environment variables:
   OPENROUTER_TITLE          Optional app name for OpenRouter attribution
   GOOGLE_BASE_URL           Custom Google endpoint
   DASHSCOPE_BASE_URL        Custom DashScope endpoint
+  MINIMAX_BASE_URL          Custom MiniMax endpoint
   REPLICATE_BASE_URL        Custom Replicate endpoint
   JIMENG_BASE_URL           Custom Jimeng endpoint
+  AZURE_OPENAI_API_KEY      Azure OpenAI API key
+  AZURE_OPENAI_BASE_URL     Azure OpenAI resource or deployment endpoint
+  AZURE_OPENAI_DEPLOYMENT   Default Azure deployment name
+  AZURE_API_VERSION         Azure API version (default: 2025-04-01-preview)
+  AZURE_OPENAI_IMAGE_MODEL  Backward-compatible Azure deployment/model alias (defaults to gpt-image-1.5)
   SEEDREAM_BASE_URL         Custom Seedream endpoint
   BAOYU_IMAGE_GEN_MAX_WORKERS  Override batch worker cap
   BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY  Override provider concurrency
@@ -229,9 +239,11 @@ export function parseArgs(argv: string[]): CliArgs {
         v !== "openai" &&
         v !== "openrouter" &&
         v !== "dashscope" &&
+        v !== "minimax" &&
         v !== "replicate" &&
         v !== "jimeng" &&
-        v !== "seedream"
+        v !== "seedream" &&
+        v !== "azure"
       ) {
         throw new Error(`Invalid provider: ${v}`);
       }
@@ -383,9 +395,11 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           openai: null,
           openrouter: null,
           dashscope: null,
+          minimax: null,
           replicate: null,
           jimeng: null,
           seedream: null,
+          azure: null,
         };
         currentKey = "default_model";
         currentProvider = null;
@@ -409,9 +423,11 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
+          key === "minimax" ||
           key === "replicate" ||
           key === "jimeng" ||
-          key === "seedream"
+          key === "seedream" ||
+          key === "azure"
         )
       ) {
         config.batch ??= {};
@@ -425,9 +441,11 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
+          key === "minimax" ||
           key === "replicate" ||
           key === "jimeng" ||
-          key === "seedream"
+          key === "seedream" ||
+          key === "azure"
         )
       ) {
         const cleaned = value.replace(/['"]/g, "");
@@ -453,14 +471,49 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
   return config;
 }
 
-async function loadExtendConfig(): Promise<Partial<ExtendConfig>> {
-  const home = homedir();
-  const cwd = process.cwd();
+type ExtendConfigPathPair = {
+  current: string;
+  legacy: string;
+};
 
-  const paths = [
-    path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
-    path.join(home, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
+function getExtendConfigPathPairs(cwd: string, home: string): ExtendConfigPathPair[] {
+  return [
+    {
+      current: path.join(cwd, ".baoyu-skills", "baoyu-imagine", "EXTEND.md"),
+      legacy: path.join(cwd, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
+    },
+    {
+      current: path.join(home, ".baoyu-skills", "baoyu-imagine", "EXTEND.md"),
+      legacy: path.join(home, ".baoyu-skills", "baoyu-image-gen", "EXTEND.md"),
+    },
   ];
+}
+
+async function exists(filePath: string): Promise<boolean> {
+  try {
+    await access(filePath);
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+async function migrateLegacyExtendConfig(cwd: string, home: string): Promise<void> {
+  for (const { current, legacy } of getExtendConfigPathPairs(cwd, home)) {
+    const [hasCurrent, hasLegacy] = await Promise.all([exists(current), exists(legacy)]);
+    if (hasCurrent || !hasLegacy) continue;
+    await mkdir(path.dirname(current), { recursive: true });
+    await rename(legacy, current);
+  }
+}
+
+export async function loadExtendConfig(
+  cwd = process.cwd(),
+  home = homedir(),
+): Promise<Partial<ExtendConfig>> {
+  await migrateLegacyExtendConfig(cwd, home);
+
+  const paths = getExtendConfigPathPairs(cwd, home).map(({ current }) => current);
 
   for (const p of paths) {
     try {
@@ -518,11 +571,13 @@ export function getConfiguredProviderRateLimits(
     openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
     openrouter: { ...DEFAULT_PROVIDER_RATE_LIMITS.openrouter },
     dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
+    minimax: { ...DEFAULT_PROVIDER_RATE_LIMITS.minimax },
     jimeng: { ...DEFAULT_PROVIDER_RATE_LIMITS.jimeng },
     seedream: { ...DEFAULT_PROVIDER_RATE_LIMITS.seedream },
+    azure: { ...DEFAULT_PROVIDER_RATE_LIMITS.azure },
   };
 
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
     const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
     const extendLimit = extendConfig.batch?.provider_limits?.[provider];
     configured[provider] = {
@@ -571,7 +626,9 @@ export function normalizeOutputImagePath(p: string, defaultExtension = ".png"):
 
 function inferProviderFromModel(model: string | null): Provider | null {
   if (!model) return null;
-  if (model.includes("seedream") || model.includes("seededit")) return "seedream";
+  const normalized = model.trim();
+  if (normalized.includes("seedream") || normalized.includes("seededit")) return "seedream";
+  if (normalized === "image-01" || normalized === "image-01-live") return "minimax";
   return null;
 }
 
@@ -581,21 +638,25 @@ export function detectProvider(args: CliArgs): Provider {
     args.provider &&
     args.provider !== "google" &&
     args.provider !== "openai" &&
+    args.provider !== "azure" &&
     args.provider !== "openrouter" &&
     args.provider !== "replicate" &&
-    args.provider !== "seedream"
+    args.provider !== "seedream" &&
+    args.provider !== "minimax"
   ) {
     throw new Error(
-      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider openrouter (OpenRouter multimodal), --provider replicate, or --provider seedream for supported Seedream models."
+      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), --provider azure (Azure OpenAI), --provider openrouter (OpenRouter multimodal), --provider replicate, --provider seedream for supported Seedream models, or --provider minimax for MiniMax subject-reference workflows."
     );
   }
 
   if (args.provider) return args.provider;
 
   const hasGoogle = !!(process.env.GOOGLE_API_KEY || process.env.GEMINI_API_KEY);
+  const hasAzure = !!(process.env.AZURE_OPENAI_API_KEY && process.env.AZURE_OPENAI_BASE_URL);
   const hasOpenai = !!process.env.OPENAI_API_KEY;
   const hasOpenrouter = !!process.env.OPENROUTER_API_KEY;
   const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
+  const hasMinimax = !!process.env.MINIMAX_API_KEY;
   const hasReplicate = !!process.env.REPLICATE_API_TOKEN;
   const hasJimeng = !!(process.env.JIMENG_ACCESS_KEY_ID && process.env.JIMENG_SECRET_ACCESS_KEY);
   const hasSeedream = !!process.env.ARK_API_KEY;
@@ -608,22 +669,33 @@ export function detectProvider(args: CliArgs): Provider {
     return "seedream";
   }
 
+  if (modelProvider === "minimax") {
+    if (!hasMinimax) {
+      throw new Error("Model looks like a MiniMax image model, but MINIMAX_API_KEY is not set.");
+    }
+    return "minimax";
+  }
+
   if (args.referenceImages.length > 0) {
     if (hasGoogle) return "google";
     if (hasOpenai) return "openai";
+    if (hasAzure) return "azure";
     if (hasOpenrouter) return "openrouter";
     if (hasReplicate) return "replicate";
     if (hasSeedream) return "seedream";
+    if (hasMinimax) return "minimax";
     throw new Error(
-      "Reference images require Google, OpenAI, OpenRouter, Replicate, or supported Seedream models. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, or ARK_API_KEY, or remove --ref."
+      "Reference images require Google, OpenAI, Azure, OpenRouter, Replicate, supported Seedream models, or MiniMax. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, REPLICATE_API_TOKEN, ARK_API_KEY, or MINIMAX_API_KEY, or remove --ref."
     );
   }
 
   const available = [
     hasGoogle && "google",
     hasOpenai && "openai",
+    hasAzure && "azure",
     hasOpenrouter && "openrouter",
     hasDashscope && "dashscope",
+    hasMinimax && "minimax",
     hasReplicate && "replicate",
     hasJimeng && "jimeng",
     hasSeedream && "seedream",
@@ -633,7 +705,7 @@ export function detectProvider(args: CliArgs): Provider {
   if (available.length > 1) return available[0]!;
 
   throw new Error(
-    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
+    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, MINIMAX_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
       "Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
   );
 }
@@ -672,10 +744,12 @@ export function isRetryableGenerationError(error: unknown): boolean {
 async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
   if (provider === "google") return (await import("./providers/google")) as ProviderModule;
   if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
+  if (provider === "minimax") return (await import("./providers/minimax")) as ProviderModule;
   if (provider === "replicate") return (await import("./providers/replicate")) as ProviderModule;
   if (provider === "openrouter") return (await import("./providers/openrouter")) as ProviderModule;
   if (provider === "jimeng") return (await import("./providers/jimeng")) as ProviderModule;
   if (provider === "seedream") return (await import("./providers/seedream")) as ProviderModule;
+  if (provider === "azure") return (await import("./providers/azure")) as ProviderModule;
   return (await import("./providers/openai")) as ProviderModule;
 }
 
@@ -701,9 +775,11 @@ function getModelForProvider(
       return extendConfig.default_model.openrouter;
     }
     if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
+    if (provider === "minimax" && extendConfig.default_model.minimax) return extendConfig.default_model.minimax;
     if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
     if (provider === "jimeng" && extendConfig.default_model.jimeng) return extendConfig.default_model.jimeng;
     if (provider === "seedream" && extendConfig.default_model.seedream) return extendConfig.default_model.seedream;
+    if (provider === "azure" && extendConfig.default_model.azure) return extendConfig.default_model.azure;
   }
   return providerModule.getDefaultModel();
 }
@@ -923,7 +999,7 @@ async function runBatchTasks(
   const acquireProvider = createProviderGate(providerRateLimits);
   const workerCount = getWorkerCount(tasks.length, jobs, maxWorkers);
   console.error(`Batch mode: ${tasks.length} tasks, ${workerCount} workers, parallel mode enabled.`);
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream", "azure"] as Provider[]) {
     const limit = providerRateLimits[provider];
     console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
   }

skills/baoyu-imagine/scripts/providers/azure.test.ts

@@ -0,0 +1,188 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test, { type TestContext } from "node:test";
+
+import type { CliArgs } from "../types.ts";
+import {
+  generateImage,
+  getDefaultModel,
+  parseAzureBaseURL,
+  validateArgs,
+} from "./azure.ts";
+
+function useEnv(
+  t: TestContext,
+  values: Record<string, string | null>,
+): void {
+  const previous = new Map<string, string | undefined>();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
+  return {
+    prompt: null,
+    promptFiles: [],
+    imagePath: null,
+    provider: null,
+    model: null,
+    aspectRatio: null,
+    size: null,
+    quality: null,
+    imageSize: null,
+    referenceImages: [],
+    n: 1,
+    batchFile: null,
+    jobs: null,
+    json: false,
+    help: false,
+    ...overrides,
+  };
+}
+
+async function makeTempDir(prefix: string): Promise<string> {
+  return fs.mkdtemp(path.join(os.tmpdir(), prefix));
+}
+
+test("Azure endpoint parsing and default deployment selection follow env precedence", (t) => {
+  assert.deepEqual(parseAzureBaseURL("https://example.openai.azure.com"), {
+    resourceBaseURL: "https://example.openai.azure.com/openai",
+    deployment: null,
+  });
+  assert.deepEqual(
+    parseAzureBaseURL("https://example.openai.azure.com/openai/deployments/from-url"),
+    {
+      resourceBaseURL: "https://example.openai.azure.com/openai",
+      deployment: "from-url",
+    },
+  );
+
+  useEnv(t, {
+    AZURE_OPENAI_BASE_URL: "https://example.openai.azure.com/openai/deployments/from-url",
+    AZURE_OPENAI_DEPLOYMENT: "explicit-deploy",
+    AZURE_OPENAI_IMAGE_MODEL: "env-fallback",
+  });
+  assert.equal(getDefaultModel(), "explicit-deploy");
+});
+
+test("Azure validateArgs rejects unsupported edit input formats before the API call", () => {
+  assert.doesNotThrow(() =>
+    validateArgs("demo-deployment", makeArgs({ referenceImages: ["hero.png", "photo.jpeg"] })),
+  );
+  assert.throws(
+    () => validateArgs("demo-deployment", makeArgs({ referenceImages: ["hero.webp"] })),
+    /PNG or JPG\/JPEG/,
+  );
+});
+
+test("Azure image generation routes model to deployment and sends mapped quality", async (t) => {
+  useEnv(t, {
+    AZURE_OPENAI_API_KEY: "azure-key",
+    AZURE_OPENAI_BASE_URL: "https://example.openai.azure.com/openai/deployments/default-deploy",
+    AZURE_API_VERSION: null,
+    AZURE_OPENAI_DEPLOYMENT: null,
+    AZURE_OPENAI_IMAGE_MODEL: null,
+  });
+
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const calls: Array<{ url: string; body: string }> = [];
+  globalThis.fetch = async (input, init) => {
+    calls.push({
+      url: String(input),
+      body: String(init?.body ?? ""),
+    });
+    return Response.json({
+      data: [{ b64_json: Buffer.from("azure-image").toString("base64") }],
+    });
+  };
+
+  const bytes = await generateImage(
+    "A calm lake at sunset",
+    "custom-deploy",
+    makeArgs({ quality: "normal" }),
+  );
+
+  assert.equal(Buffer.from(bytes).toString("utf8"), "azure-image");
+  assert.equal(
+    calls[0]?.url,
+    "https://example.openai.azure.com/openai/deployments/custom-deploy/images/generations?api-version=2025-04-01-preview",
+  );
+
+  const body = JSON.parse(calls[0]!.body) as Record<string, string>;
+  assert.equal(body.quality, "medium");
+  assert.equal(body.size, "1024x1024");
+});
+
+test("Azure image edits include quality in multipart requests", async (t) => {
+  const root = await makeTempDir("baoyu-imagine-azure-");
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+
+  const pngPath = path.join(root, "ref.png");
+  const jpgPath = path.join(root, "ref.jpg");
+  await fs.writeFile(pngPath, "png-bytes");
+  await fs.writeFile(jpgPath, "jpg-bytes");
+
+  useEnv(t, {
+    AZURE_OPENAI_API_KEY: "azure-key",
+    AZURE_OPENAI_BASE_URL: "https://example.openai.azure.com",
+    AZURE_API_VERSION: "2025-04-01-preview",
+    AZURE_OPENAI_DEPLOYMENT: null,
+    AZURE_OPENAI_IMAGE_MODEL: null,
+  });
+
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const calls: Array<{ url: string; form: FormData }> = [];
+  globalThis.fetch = async (input, init) => {
+    calls.push({
+      url: String(input),
+      form: init?.body as FormData,
+    });
+    return Response.json({
+      data: [{ b64_json: Buffer.from("edited-image").toString("base64") }],
+    });
+  };
+
+  const bytes = await generateImage(
+    "Add warm lighting",
+    "edit-deploy",
+    makeArgs({
+      quality: "2k",
+      referenceImages: [pngPath, jpgPath],
+    }),
+  );
+
+  assert.equal(Buffer.from(bytes).toString("utf8"), "edited-image");
+  assert.equal(
+    calls[0]?.url,
+    "https://example.openai.azure.com/openai/deployments/edit-deploy/images/edits?api-version=2025-04-01-preview",
+  );
+  assert.equal(calls[0]?.form.get("quality"), "high");
+  assert.equal(calls[0]?.form.get("size"), "1024x1024");
+  assert.equal(calls[0]?.form.getAll("image[]").length, 2);
+});

skills/baoyu-imagine/scripts/providers/azure.ts

@@ -0,0 +1,192 @@
+import path from "node:path";
+import { readFile } from "node:fs/promises";
+import type { CliArgs } from "../types";
+import { getOpenAISize, extractImageFromResponse } from "./openai.ts";
+
+type OpenAIImageResponse = { data: Array<{ url?: string; b64_json?: string }> };
+type AzureEndpoint = {
+  resourceBaseURL: string;
+  deployment: string | null;
+};
+
+const DEFAULT_AZURE_API_VERSION = "2025-04-01-preview";
+const AZURE_EDIT_IMAGE_EXTENSIONS = new Set([".png", ".jpg", ".jpeg"]);
+
+export function parseAzureBaseURL(url: string): AzureEndpoint {
+  const parsed = new URL(url);
+  const trimmedPath = parsed.pathname.replace(/\/+$/, "");
+  const deploymentMatch = trimmedPath.match(/^(.*?)(?:\/openai)?\/deployments\/([^/]+)$/);
+
+  if (deploymentMatch) {
+    parsed.pathname = `${deploymentMatch[1] || ""}/openai`;
+    return {
+      resourceBaseURL: parsed.toString().replace(/\/+$/, ""),
+      deployment: decodeURIComponent(deploymentMatch[2]!),
+    };
+  }
+
+  parsed.pathname = trimmedPath.endsWith("/openai") ? trimmedPath : `${trimmedPath}/openai`;
+  return {
+    resourceBaseURL: parsed.toString().replace(/\/+$/, ""),
+    deployment: null,
+  };
+}
+
+export function getDefaultModel(): string {
+  const explicitDeployment = process.env.AZURE_OPENAI_DEPLOYMENT?.trim();
+  if (explicitDeployment) return explicitDeployment;
+
+  const baseURL = process.env.AZURE_OPENAI_BASE_URL;
+  if (baseURL) {
+    try {
+      const { deployment } = parseAzureBaseURL(baseURL);
+      if (deployment) return deployment;
+    } catch {
+      // Ignore invalid URLs here so the required-env check can raise the user-facing error later.
+    }
+  }
+
+  return process.env.AZURE_OPENAI_IMAGE_MODEL || "gpt-image-1.5";
+}
+
+function getEndpoint(): AzureEndpoint {
+  const url = process.env.AZURE_OPENAI_BASE_URL;
+  if (!url) {
+    throw new Error(
+      "AZURE_OPENAI_BASE_URL is required. Set it to your Azure resource or deployment endpoint, e.g.: https://your-resource.openai.azure.com or https://your-resource.openai.azure.com/openai/deployments/your-deployment"
+    );
+  }
+  return parseAzureBaseURL(url);
+}
+
+function getApiKey(): string {
+  const key = process.env.AZURE_OPENAI_API_KEY;
+  if (!key) {
+    throw new Error(
+      "AZURE_OPENAI_API_KEY is required. Get it from Azure Portal → your OpenAI resource → Keys and Endpoint."
+    );
+  }
+  return key;
+}
+
+function getApiVersion(): string {
+  return process.env.AZURE_API_VERSION || DEFAULT_AZURE_API_VERSION;
+}
+
+function getDeployment(model: string): string {
+  const deployment = model.trim();
+  if (!deployment) {
+    throw new Error(
+      "Azure deployment name is required. Use --model <deployment>, AZURE_OPENAI_DEPLOYMENT, AZURE_OPENAI_IMAGE_MODEL, or embed the deployment in AZURE_OPENAI_BASE_URL."
+    );
+  }
+  return deployment;
+}
+
+function buildURL(deployment: string, pathSuffix: string): string {
+  const { resourceBaseURL } = getEndpoint();
+  return `${resourceBaseURL}/deployments/${encodeURIComponent(deployment)}${pathSuffix}?api-version=${getApiVersion()}`;
+}
+
+function authHeaders(): Record<string, string> {
+  return { "api-key": getApiKey() };
+}
+
+function getAzureQuality(quality: CliArgs["quality"]): "medium" | "high" {
+  return quality === "2k" ? "high" : "medium";
+}
+
+export function validateArgs(_model: string, args: CliArgs): void {
+  for (const refPath of args.referenceImages) {
+    const ext = path.extname(refPath).toLowerCase();
+    if (!AZURE_EDIT_IMAGE_EXTENSIONS.has(ext)) {
+      throw new Error(
+        `Azure OpenAI reference images must be PNG or JPG/JPEG. Unsupported file: ${refPath}`
+      );
+    }
+  }
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  const deployment = getDeployment(model);
+  const size = args.size || getOpenAISize(model, args.aspectRatio, args.quality);
+
+  if (args.referenceImages.length > 0) {
+    return generateWithAzureEdits(prompt, deployment, size, args.referenceImages, args.quality);
+  }
+
+  return generateWithAzureGenerations(prompt, deployment, size, args.quality);
+}
+
+async function generateWithAzureGenerations(
+  prompt: string,
+  deployment: string,
+  size: string,
+  quality: CliArgs["quality"]
+): Promise<Uint8Array> {
+  const body: Record<string, any> = {
+    prompt,
+    size,
+    n: 1,
+    quality: getAzureQuality(quality),
+  };
+
+  const res = await fetch(buildURL(deployment, "/images/generations"), {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      ...authHeaders(),
+    },
+    body: JSON.stringify(body),
+  });
+
+  if (!res.ok) {
+    const err = await res.text();
+    throw new Error(`Azure OpenAI API error: ${err}`);
+  }
+
+  const result = (await res.json()) as OpenAIImageResponse;
+  return extractImageFromResponse(result);
+}
+
+async function generateWithAzureEdits(
+  prompt: string,
+  deployment: string,
+  size: string,
+  referenceImages: string[],
+  quality: CliArgs["quality"]
+): Promise<Uint8Array> {
+  const form = new FormData();
+  form.append("prompt", prompt);
+  form.append("size", size);
+  form.append("n", "1");
+  form.append("quality", getAzureQuality(quality));
+
+  for (const refPath of referenceImages) {
+    const bytes = await readFile(refPath);
+    const filename = path.basename(refPath);
+    const mimeType = path.extname(filename).toLowerCase() === ".png" ? "image/png" : "image/jpeg";
+    const blob = new Blob([bytes], { type: mimeType });
+    form.append("image[]", blob, filename);
+  }
+
+  const res = await fetch(buildURL(deployment, "/images/edits"), {
+    method: "POST",
+    headers: {
+      ...authHeaders(),
+    },
+    body: form,
+  });
+
+  if (!res.ok) {
+    const err = await res.text();
+    throw new Error(`Azure OpenAI edits API error: ${err}`);
+  }
+
+  const result = (await res.json()) as OpenAIImageResponse;
+  return extractImageFromResponse(result);
+}

skills/baoyu-imagine/scripts/providers/dashscope.ts

@@ -421,7 +421,7 @@ export async function generateImage(
 
   if (args.referenceImages.length > 0) {
     throw new Error(
-      "Reference images are not supported with DashScope provider in baoyu-image-gen. Use --provider google with a Gemini multimodal model."
+      "Reference images are not supported with DashScope provider in baoyu-imagine. Use --provider google with a Gemini multimodal model."
     );
   }
 

skills/baoyu-imagine/scripts/providers/jimeng.test.ts

@@ -0,0 +1,114 @@
+import assert from "node:assert/strict";
+import test, { type TestContext } from "node:test";
+
+import type { CliArgs } from "../types.ts";
+import { generateImage } from "./jimeng.ts";
+
+function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
+  return {
+    prompt: null,
+    promptFiles: [],
+    imagePath: null,
+    provider: null,
+    model: null,
+    aspectRatio: null,
+    size: null,
+    quality: null,
+    imageSize: null,
+    referenceImages: [],
+    n: 1,
+    batchFile: null,
+    jobs: null,
+    json: false,
+    help: false,
+    ...overrides,
+  };
+}
+
+function useEnv(
+  t: TestContext,
+  values: Record<string, string | null>,
+): void {
+  const previous = new Map<string, string | undefined>();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+test("Jimeng submit request uses prompt field expected by current API", async (t) => {
+  useEnv(t, {
+    JIMENG_ACCESS_KEY_ID: "test-access-key",
+    JIMENG_SECRET_ACCESS_KEY: "test-secret-key",
+    JIMENG_BASE_URL: null,
+    JIMENG_REGION: null,
+  });
+
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const calls: Array<{
+    input: string;
+    init?: RequestInit;
+  }> = [];
+
+  globalThis.fetch = async (input, init) => {
+    calls.push({
+      input: String(input),
+      init,
+    });
+
+    if (calls.length === 1) {
+      return Response.json({
+        code: 10000,
+        data: {
+          task_id: "task-123",
+        },
+      });
+    }
+
+    return Response.json({
+      code: 10000,
+      data: {
+        status: "done",
+        binary_data_base64: [Buffer.from("jimeng-image").toString("base64")],
+      },
+    });
+  };
+
+  const image = await generateImage(
+    "A quiet bamboo forest",
+    "jimeng_t2i_v40",
+    makeArgs({ quality: "normal" }),
+  );
+
+  assert.equal(Buffer.from(image).toString("utf8"), "jimeng-image");
+  assert.equal(calls.length, 2);
+  assert.equal(
+    calls[0]?.input,
+    "https://visual.volcengineapi.com/?Action=CVSync2AsyncSubmitTask&Version=2022-08-31",
+  );
+
+  const submitBody = JSON.parse(String(calls[0]?.init?.body)) as Record<string, unknown>;
+  assert.equal(submitBody.req_key, "jimeng_t2i_v40");
+  assert.equal(submitBody.prompt, "A quiet bamboo forest");
+  assert.ok(!("prompt_text" in submitBody));
+  assert.equal(submitBody.width, 1024);
+  assert.equal(submitBody.height, 1024);
+});

skills/baoyu-imagine/scripts/providers/jimeng.ts

@@ -246,7 +246,7 @@ async function submitTask(
   const [width, height] = size.split("x").map(Number);
   const bodyObj = {
     req_key: model,
-    prompt_text: prompt,
+    prompt,
     // Use separate width and height parameters instead of size string
     width: width,
     height: height,

skills/baoyu-imagine/scripts/providers/minimax.test.ts

@@ -0,0 +1,171 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test, { type TestContext } from "node:test";
+
+import type { CliArgs } from "../types.ts";
+import {
+  buildMinimaxUrl,
+  buildRequestBody,
+  buildSubjectReference,
+  extractImageFromResponse,
+  parsePixelSize,
+  validateArgs,
+} from "./minimax.ts";
+
+function useEnv(
+  t: TestContext,
+  values: Record<string, string | null>,
+): void {
+  const previous = new Map<string, string | undefined>();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
+  return {
+    prompt: null,
+    promptFiles: [],
+    imagePath: null,
+    provider: null,
+    model: null,
+    aspectRatio: null,
+    size: null,
+    quality: null,
+    imageSize: null,
+    referenceImages: [],
+    n: 1,
+    batchFile: null,
+    jobs: null,
+    json: false,
+    help: false,
+    ...overrides,
+  };
+}
+
+test("MiniMax URL builder normalizes /v1 suffixes", (t) => {
+  useEnv(t, { MINIMAX_BASE_URL: "https://api.minimax.io" });
+  assert.equal(buildMinimaxUrl(), "https://api.minimax.io/v1/image_generation");
+
+  process.env.MINIMAX_BASE_URL = "https://proxy.example.com/custom/v1/";
+  assert.equal(buildMinimaxUrl(), "https://proxy.example.com/custom/v1/image_generation");
+});
+
+test("MiniMax size parsing and validation follow documented constraints", () => {
+  assert.deepEqual(parsePixelSize("1536x1024"), { width: 1536, height: 1024 });
+  assert.deepEqual(parsePixelSize("1536*1024"), { width: 1536, height: 1024 });
+  assert.equal(parsePixelSize("wide"), null);
+
+  validateArgs("image-01", makeArgs({ size: "1536x1024", n: 9 }));
+
+  assert.throws(
+    () => validateArgs("image-01-live", makeArgs({ size: "1536x1024" })),
+    /only supported with model image-01/,
+  );
+  assert.throws(
+    () => validateArgs("image-01", makeArgs({ size: "1537x1024" })),
+    /divisible by 8/,
+  );
+  assert.throws(
+    () => validateArgs("image-01", makeArgs({ aspectRatio: "2.35:1" })),
+    /aspect_ratio must be one of/,
+  );
+  assert.throws(
+    () => validateArgs("image-01", makeArgs({ n: 10 })),
+    /at most 9 images/,
+  );
+});
+
+test("MiniMax request body maps aspect ratio, size, n, and subject references", async (t) => {
+  const dir = await fs.mkdtemp(path.join(os.tmpdir(), "minimax-test-"));
+  t.after(() => fs.rm(dir, { recursive: true, force: true }));
+
+  const refPath = path.join(dir, "portrait.png");
+  await fs.writeFile(refPath, Buffer.from("portrait"));
+
+  const ratioBody = await buildRequestBody(
+    "A portrait by the window",
+    "image-01",
+    makeArgs({ aspectRatio: "16:9", n: 2, referenceImages: [refPath] }),
+  );
+  assert.equal(ratioBody.aspect_ratio, "16:9");
+  assert.equal(ratioBody.n, 2);
+  assert.equal(ratioBody.response_format, "base64");
+  assert.match(ratioBody.subject_reference?.[0]?.image_file || "", /^data:image\/png;base64,/);
+
+  const sizeBody = await buildRequestBody(
+    "A portrait by the window",
+    "image-01",
+    makeArgs({ size: "1536x1024" }),
+  );
+  assert.equal(sizeBody.width, 1536);
+  assert.equal(sizeBody.height, 1024);
+  assert.equal(sizeBody.aspect_ratio, undefined);
+});
+
+test("MiniMax subject references require supported file types", async (t) => {
+  const dir = await fs.mkdtemp(path.join(os.tmpdir(), "minimax-ref-"));
+  t.after(() => fs.rm(dir, { recursive: true, force: true }));
+
+  const good = path.join(dir, "portrait.jpg");
+  const bad = path.join(dir, "portrait.webp");
+  await fs.writeFile(good, Buffer.from("portrait"));
+  await fs.writeFile(bad, Buffer.from("portrait"));
+
+  const subjectReference = await buildSubjectReference([good]);
+  assert.equal(subjectReference?.[0]?.type, "character");
+
+  await assert.rejects(
+    () => buildSubjectReference([bad]),
+    /only supports JPG, JPEG, or PNG/,
+  );
+});
+
+test("MiniMax response extraction supports base64 and URL payloads", async (t) => {
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const fromBase64 = await extractImageFromResponse({
+    data: {
+      image_base64: [Buffer.from("hello").toString("base64")],
+    },
+  });
+  assert.equal(Buffer.from(fromBase64).toString("utf8"), "hello");
+
+  globalThis.fetch = async () =>
+    new Response(Uint8Array.from([1, 2, 3]), {
+      status: 200,
+      headers: { "Content-Type": "image/jpeg" },
+    });
+
+  const fromUrl = await extractImageFromResponse({
+    data: {
+      image_urls: ["https://example.com/output.jpg"],
+    },
+  });
+  assert.deepEqual([...fromUrl], [1, 2, 3]);
+
+  await assert.rejects(
+    () => extractImageFromResponse({ base_resp: { status_code: 1001, status_msg: "blocked" } }),
+    /blocked/,
+  );
+});

skills/baoyu-imagine/scripts/providers/minimax.ts

@@ -0,0 +1,220 @@
+import path from "node:path";
+import { readFile } from "node:fs/promises";
+
+import type { CliArgs } from "../types";
+
+const DEFAULT_MODEL = "image-01";
+const MAX_REFERENCE_IMAGE_BYTES = 10 * 1024 * 1024;
+const SUPPORTED_ASPECT_RATIOS = new Set(["1:1", "16:9", "4:3", "3:2", "2:3", "3:4", "9:16", "21:9"]);
+
+type MinimaxSubjectReference = {
+  type: "character";
+  image_file: string;
+};
+
+type MinimaxRequestBody = {
+  model: string;
+  prompt: string;
+  response_format: "base64";
+  aspect_ratio?: string;
+  width?: number;
+  height?: number;
+  n?: number;
+  subject_reference?: MinimaxSubjectReference[];
+};
+
+type MinimaxResponse = {
+  id?: string;
+  data?: {
+    image_urls?: string[];
+    image_base64?: string[];
+  };
+  base_resp?: {
+    status_code?: number;
+    status_msg?: string;
+  };
+};
+
+export function getDefaultModel(): string {
+  return process.env.MINIMAX_IMAGE_MODEL || DEFAULT_MODEL;
+}
+
+function getApiKey(): string | null {
+  return process.env.MINIMAX_API_KEY || null;
+}
+
+export function buildMinimaxUrl(): string {
+  const base = (process.env.MINIMAX_BASE_URL || "https://api.minimax.io").replace(/\/+$/g, "");
+  return base.endsWith("/v1") ? `${base}/image_generation` : `${base}/v1/image_generation`;
+}
+
+function getMimeType(filename: string): "image/jpeg" | "image/png" {
+  const ext = path.extname(filename).toLowerCase();
+  if (ext === ".jpg" || ext === ".jpeg") return "image/jpeg";
+  if (ext === ".png") return "image/png";
+  throw new Error(
+    `MiniMax subject_reference only supports JPG, JPEG, or PNG files: ${filename}`
+  );
+}
+
+export function parsePixelSize(size: string): { width: number; height: number } | null {
+  const match = size.trim().match(/^(\d+)\s*[xX*]\s*(\d+)$/);
+  if (!match) return null;
+
+  const width = parseInt(match[1]!, 10);
+  const height = parseInt(match[2]!, 10);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+
+  return { width, height };
+}
+
+function validatePixelSize(width: number, height: number): void {
+  if (width < 512 || width > 2048 || height < 512 || height > 2048) {
+    throw new Error("MiniMax custom size must keep width and height between 512 and 2048.");
+  }
+  if (width % 8 !== 0 || height % 8 !== 0) {
+    throw new Error("MiniMax custom size requires width and height divisible by 8.");
+  }
+}
+
+export function validateArgs(model: string, args: CliArgs): void {
+  if (args.n > 9) {
+    throw new Error("MiniMax supports at most 9 images per request.");
+  }
+
+  if (args.aspectRatio && !SUPPORTED_ASPECT_RATIOS.has(args.aspectRatio)) {
+    throw new Error(
+      `MiniMax aspect_ratio must be one of: ${Array.from(SUPPORTED_ASPECT_RATIOS).join(", ")}.`
+    );
+  }
+
+  if (args.size && !args.aspectRatio) {
+    if (model !== "image-01") {
+      throw new Error("MiniMax custom --size is only supported with model image-01. Use --model image-01 or pass --ar instead.");
+    }
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("MiniMax --size must be in WxH format, for example 1536x1024.");
+    }
+    validatePixelSize(parsed.width, parsed.height);
+  }
+}
+
+export async function buildSubjectReference(
+  referenceImages: string[],
+): Promise<MinimaxSubjectReference[] | undefined> {
+  if (referenceImages.length === 0) return undefined;
+
+  const subjectReference: MinimaxSubjectReference[] = [];
+  for (const refPath of referenceImages) {
+    const bytes = await readFile(refPath);
+    if (bytes.length > MAX_REFERENCE_IMAGE_BYTES) {
+      throw new Error(`MiniMax subject_reference images must be smaller than 10MB: ${refPath}`);
+    }
+
+    subjectReference.push({
+      type: "character",
+      image_file: `data:${getMimeType(refPath)};base64,${bytes.toString("base64")}`,
+    });
+  }
+
+  return subjectReference;
+}
+
+export async function buildRequestBody(
+  prompt: string,
+  model: string,
+  args: CliArgs,
+): Promise<MinimaxRequestBody> {
+  validateArgs(model, args);
+
+  const body: MinimaxRequestBody = {
+    model,
+    prompt,
+    response_format: "base64",
+  };
+
+  if (args.aspectRatio) {
+    body.aspect_ratio = args.aspectRatio;
+  } else if (args.size) {
+    const parsed = parsePixelSize(args.size);
+    if (!parsed) {
+      throw new Error("MiniMax --size must be in WxH format, for example 1536x1024.");
+    }
+    body.width = parsed.width;
+    body.height = parsed.height;
+  }
+
+  if (args.n > 1) {
+    body.n = args.n;
+  }
+
+  const subjectReference = await buildSubjectReference(args.referenceImages);
+  if (subjectReference) {
+    body.subject_reference = subjectReference;
+  }
+
+  return body;
+}
+
+async function downloadImage(url: string): Promise<Uint8Array> {
+  const response = await fetch(url);
+  if (!response.ok) {
+    throw new Error(`Failed to download image from MiniMax: ${response.status}`);
+  }
+  return new Uint8Array(await response.arrayBuffer());
+}
+
+export async function extractImageFromResponse(result: MinimaxResponse): Promise<Uint8Array> {
+  const baseResp = result.base_resp;
+  if (baseResp && baseResp.status_code !== undefined && baseResp.status_code !== 0) {
+    throw new Error(baseResp.status_msg || `MiniMax API returned status_code=${baseResp.status_code}`);
+  }
+
+  const base64Image = result.data?.image_base64?.[0];
+  if (base64Image) {
+    return Uint8Array.from(Buffer.from(base64Image, "base64"));
+  }
+
+  const url = result.data?.image_urls?.[0];
+  if (url) {
+    return downloadImage(url);
+  }
+
+  throw new Error("No image data in MiniMax response");
+}
+
+export function getDefaultOutputExtension(): ".jpg" {
+  return ".jpg";
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs
+): Promise<Uint8Array> {
+  const apiKey = getApiKey();
+  if (!apiKey) {
+    throw new Error("MINIMAX_API_KEY is required. Get one from https://platform.minimax.io/");
+  }
+
+  const body = await buildRequestBody(prompt, model, args);
+  const response = await fetch(buildMinimaxUrl(), {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${apiKey}`,
+    },
+    body: JSON.stringify(body),
+  });
+
+  if (!response.ok) {
+    const err = await response.text();
+    throw new Error(`MiniMax API error (${response.status}): ${err}`);
+  }
+
+  const result = (await response.json()) as MinimaxResponse;
+  return extractImageFromResponse(result);
+}

skills/baoyu-imagine/scripts/types.ts

@@ -1,4 +1,13 @@
-export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate" | "jimeng" | "seedream";
+export type Provider =
+  | "google"
+  | "openai"
+  | "openrouter"
+  | "dashscope"
+  | "minimax"
+  | "replicate"
+  | "jimeng"
+  | "seedream"
+  | "azure";
 export type Quality = "normal" | "2k";
 
 export type CliArgs = {
@@ -52,9 +61,11 @@ export type ExtendConfig = {
     openai: string | null;
     openrouter: string | null;
     dashscope: string | null;
+    minimax: string | null;
     replicate: string | null;
     jimeng: string | null;
     seedream: string | null;
+    azure: string | null;
   };
   batch?: {
     max_workers?: number | null;

skills/baoyu-markdown-to-html/scripts/main.test.ts

@@ -3,6 +3,7 @@ import { execFile } from "node:child_process";
 import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
+import process from "node:process";
 import test from "node:test";
 import { fileURLToPath } from "node:url";
 import { promisify } from "node:util";
@@ -21,8 +22,10 @@ test("CLI forwards wrapper title and vendor render options", async () => {
   await fs.writeFile(markdownPath, "## Section\n\nParagraph with **bold** text.\n", "utf-8");
 
   const { stdout } = await execFileAsync(
-    "bun",
+    process.execPath,
     [
+      "--import",
+      "tsx",
       SCRIPT_PATH,
       markdownPath,
       "--theme", "grace",

skills/baoyu-post-to-wechat/scripts/wechat-api.ts

@@ -694,6 +694,10 @@ async function main(): Promise<void> {
   }
 
   const creds = loadCredentials(resolved);
+  for (const skippedSource of creds.skippedSources) {
+    console.error(`[wechat-api] Skipped incomplete credential source: ${skippedSource}`);
+  }
+  console.error(`[wechat-api] Credentials source: ${creds.source}`);
   console.error("[wechat-api] Fetching access token...");
   const accessToken = await fetchAccessToken(creds.appId, creds.appSecret);
 

skills/baoyu-post-to-wechat/scripts/wechat-extend-config.test.ts

@@ -0,0 +1,139 @@
+import assert from "node:assert/strict";
+import fs from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import process from "node:process";
+import test, { type TestContext } from "node:test";
+
+import { loadCredentials } from "./wechat-extend-config.ts";
+
+function useCwd(t: TestContext, cwd: string): void {
+  const previous = process.cwd();
+  process.chdir(cwd);
+  t.after(() => {
+    process.chdir(previous);
+  });
+}
+
+function useHome(t: TestContext, home: string): void {
+  const previous = process.env.HOME;
+  process.env.HOME = home;
+  t.after(() => {
+    if (previous === undefined) {
+      delete process.env.HOME;
+      return;
+    }
+    process.env.HOME = previous;
+  });
+}
+
+function useWechatEnv(
+  t: TestContext,
+  values: Partial<Record<"WECHAT_APP_ID" | "WECHAT_APP_SECRET", string | undefined>>,
+): void {
+  const previous = {
+    WECHAT_APP_ID: process.env.WECHAT_APP_ID,
+    WECHAT_APP_SECRET: process.env.WECHAT_APP_SECRET,
+  };
+
+  if (values.WECHAT_APP_ID === undefined) {
+    delete process.env.WECHAT_APP_ID;
+  } else {
+    process.env.WECHAT_APP_ID = values.WECHAT_APP_ID;
+  }
+
+  if (values.WECHAT_APP_SECRET === undefined) {
+    delete process.env.WECHAT_APP_SECRET;
+  } else {
+    process.env.WECHAT_APP_SECRET = values.WECHAT_APP_SECRET;
+  }
+
+  t.after(() => {
+    if (previous.WECHAT_APP_ID === undefined) {
+      delete process.env.WECHAT_APP_ID;
+    } else {
+      process.env.WECHAT_APP_ID = previous.WECHAT_APP_ID;
+    }
+
+    if (previous.WECHAT_APP_SECRET === undefined) {
+      delete process.env.WECHAT_APP_SECRET;
+    } else {
+      process.env.WECHAT_APP_SECRET = previous.WECHAT_APP_SECRET;
+    }
+  });
+}
+
+async function makeTempDir(prefix: string): Promise<string> {
+  return fs.mkdtemp(path.join(os.tmpdir(), prefix));
+}
+
+async function writeEnvFile(root: string, content: string): Promise<void> {
+  const envPath = path.join(root, ".baoyu-skills", ".env");
+  await fs.mkdir(path.dirname(envPath), { recursive: true });
+  await fs.writeFile(envPath, content);
+}
+
+test("loadCredentials selects the first complete source without mixing values across sources", async (t) => {
+  const cwdRoot = await makeTempDir("wechat-creds-cwd-");
+  const homeRoot = await makeTempDir("wechat-creds-home-");
+
+  useCwd(t, cwdRoot);
+  useHome(t, homeRoot);
+  useWechatEnv(t, {
+    WECHAT_APP_ID: undefined,
+    WECHAT_APP_SECRET: "stale-secret-from-process-env",
+  });
+
+  await writeEnvFile(cwdRoot, "WECHAT_APP_ID=cwd-app-id\nWECHAT_APP_SECRET=cwd-app-secret\n");
+  await writeEnvFile(homeRoot, "WECHAT_APP_ID=home-app-id\nWECHAT_APP_SECRET=home-app-secret\n");
+
+  const credentials = loadCredentials();
+
+  assert.equal(credentials.appId, "cwd-app-id");
+  assert.equal(credentials.appSecret, "cwd-app-secret");
+  assert.equal(credentials.source, "<cwd>/.baoyu-skills/.env");
+  assert.deepEqual(credentials.skippedSources, [
+    "process.env missing WECHAT_APP_ID",
+  ]);
+});
+
+test("loadCredentials prefers a complete process.env pair over lower-priority files", async (t) => {
+  const cwdRoot = await makeTempDir("wechat-creds-cwd-");
+  const homeRoot = await makeTempDir("wechat-creds-home-");
+
+  useCwd(t, cwdRoot);
+  useHome(t, homeRoot);
+  useWechatEnv(t, {
+    WECHAT_APP_ID: "env-app-id",
+    WECHAT_APP_SECRET: "env-app-secret",
+  });
+
+  await writeEnvFile(cwdRoot, "WECHAT_APP_ID=cwd-app-id\nWECHAT_APP_SECRET=cwd-app-secret\n");
+  await writeEnvFile(homeRoot, "WECHAT_APP_ID=home-app-id\nWECHAT_APP_SECRET=home-app-secret\n");
+
+  const credentials = loadCredentials();
+
+  assert.equal(credentials.appId, "env-app-id");
+  assert.equal(credentials.appSecret, "env-app-secret");
+  assert.equal(credentials.source, "process.env");
+  assert.deepEqual(credentials.skippedSources, []);
+});
+
+test("loadCredentials reports skipped incomplete sources when no complete pair exists", async (t) => {
+  const cwdRoot = await makeTempDir("wechat-creds-cwd-");
+  const homeRoot = await makeTempDir("wechat-creds-home-");
+
+  useCwd(t, cwdRoot);
+  useHome(t, homeRoot);
+  useWechatEnv(t, {
+    WECHAT_APP_ID: "env-app-id",
+    WECHAT_APP_SECRET: undefined,
+  });
+
+  await writeEnvFile(cwdRoot, "WECHAT_APP_SECRET=cwd-app-secret\n");
+
+  assert.throws(
+    () => loadCredentials(),
+    /Incomplete credential sources skipped:\n- process\.env missing WECHAT_APP_SECRET\n- <cwd>\/\.baoyu-skills\/\.env missing WECHAT_APP_ID/,
+  );
+});

skills/baoyu-post-to-wechat/scripts/wechat-extend-config.ts

@@ -196,48 +196,116 @@ function aliasToEnvKey(alias: string): string {
   return alias.toUpperCase().replace(/-/g, "_");
 }
 
-export function loadCredentials(account?: ResolvedAccount): { appId: string; appSecret: string } {
-  if (account?.app_id && account?.app_secret) {
-    return { appId: account.app_id, appSecret: account.app_secret };
+interface CredentialSource {
+  name: string;
+  appIdKey: string;
+  appSecretKey: string;
+  appId?: string;
+  appSecret?: string;
+}
+
+export interface LoadedCredentials {
+  appId: string;
+  appSecret: string;
+  source: string;
+  skippedSources: string[];
+}
+
+function normalizeCredentialValue(value?: string): string | undefined {
+  const trimmed = value?.trim();
+  return trimmed ? trimmed : undefined;
+}
+
+function describeMissingKeys(source: CredentialSource): string {
+  const missingKeys: string[] = [];
+  if (!source.appId) missingKeys.push(source.appIdKey);
+  if (!source.appSecret) missingKeys.push(source.appSecretKey);
+  return `${source.name} missing ${missingKeys.join(" and ")}`;
+}
+
+function buildCredentialSource(
+  name: string,
+  values: Record<string, string | undefined>,
+  appIdKey: string,
+  appSecretKey: string,
+): CredentialSource {
+  return {
+    name,
+    appIdKey,
+    appSecretKey,
+    appId: normalizeCredentialValue(values[appIdKey]),
+    appSecret: normalizeCredentialValue(values[appSecretKey]),
+  };
+}
+
+function resolveCredentialSource(
+  sources: CredentialSource[],
+  account?: ResolvedAccount,
+): LoadedCredentials {
+  const skippedSources: string[] = [];
+
+  for (const source of sources) {
+    if (source.appId && source.appSecret) {
+      return {
+        appId: source.appId,
+        appSecret: source.appSecret,
+        source: source.name,
+        skippedSources,
+      };
+    }
+
+    if (source.appId || source.appSecret) {
+      skippedSources.push(describeMissingKeys(source));
+    }
   }
 
+  const hint = account?.alias ? ` (account: ${account.alias})` : "";
+  const partialHint = skippedSources.length > 0
+    ? `\nIncomplete credential sources skipped:\n- ${skippedSources.join("\n- ")}`
+    : "";
+
+  throw new Error(
+    `Missing WECHAT_APP_ID or WECHAT_APP_SECRET${hint}.\n` +
+    "Set via EXTEND.md account config, environment variables, or .baoyu-skills/.env file." +
+    partialHint
+  );
+}
+
+export function loadCredentials(account?: ResolvedAccount): LoadedCredentials {
   const cwdEnvPath = path.join(process.cwd(), ".baoyu-skills", ".env");
   const homeEnvPath = path.join(os.homedir(), ".baoyu-skills", ".env");
   const cwdEnv = loadEnvFile(cwdEnvPath);
   const homeEnv = loadEnvFile(homeEnvPath);
 
+  const sources: CredentialSource[] = [];
+
+  if (account?.app_id || account?.app_secret) {
+    sources.push({
+      name: account.alias ? `EXTEND.md account "${account.alias}"` : "EXTEND.md account config",
+      appIdKey: "app_id",
+      appSecretKey: "app_secret",
+      appId: normalizeCredentialValue(account.app_id),
+      appSecret: normalizeCredentialValue(account.app_secret),
+    });
+  }
+
   const prefix = account?.alias ? `WECHAT_${aliasToEnvKey(account.alias)}_` : "";
-
-  let appId = "";
-  let appSecret = "";
-
   if (prefix) {
-    appId = process.env[`${prefix}APP_ID`]
-      || cwdEnv[`${prefix}APP_ID`]
-      || homeEnv[`${prefix}APP_ID`]
-      || "";
-    appSecret = process.env[`${prefix}APP_SECRET`]
-      || cwdEnv[`${prefix}APP_SECRET`]
-      || homeEnv[`${prefix}APP_SECRET`]
-      || "";
-  }
-
-  if (!appId) {
-    appId = process.env.WECHAT_APP_ID || cwdEnv.WECHAT_APP_ID || homeEnv.WECHAT_APP_ID || "";
-  }
-  if (!appSecret) {
-    appSecret = process.env.WECHAT_APP_SECRET || cwdEnv.WECHAT_APP_SECRET || homeEnv.WECHAT_APP_SECRET || "";
-  }
-
-  if (!appId || !appSecret) {
-    const hint = account?.alias ? ` (account: ${account.alias})` : "";
-    throw new Error(
-      `Missing WECHAT_APP_ID or WECHAT_APP_SECRET${hint}.\n` +
-      "Set via EXTEND.md account config, environment variables, or .baoyu-skills/.env file."
+    const prefixedKeyLabel = `${prefix}APP_ID/${prefix}APP_SECRET`;
+    sources.push(
+      buildCredentialSource(`process.env (${prefixedKeyLabel})`, process.env, `${prefix}APP_ID`, `${prefix}APP_SECRET`),
+      buildCredentialSource(`<cwd>/.baoyu-skills/.env (${prefixedKeyLabel})`, cwdEnv, `${prefix}APP_ID`, `${prefix}APP_SECRET`),
+      buildCredentialSource(`~/.baoyu-skills/.env (${prefixedKeyLabel})`, homeEnv, `${prefix}APP_ID`, `${prefix}APP_SECRET`),
     );
   }
 
-  return { appId, appSecret };
+  sources.push(
+    buildCredentialSource("process.env", process.env, "WECHAT_APP_ID", "WECHAT_APP_SECRET"),
+    buildCredentialSource("<cwd>/.baoyu-skills/.env", cwdEnv, "WECHAT_APP_ID", "WECHAT_APP_SECRET"),
+    buildCredentialSource("~/.baoyu-skills/.env", homeEnv, "WECHAT_APP_ID", "WECHAT_APP_SECRET"),
+  );
+
+  return resolveCredentialSource(sources, account);
 }
 
 export function listAccounts(config: WechatExtendConfig): string[] {

skills/baoyu-post-to-weibo/SKILL.md

@@ -123,6 +123,8 @@ ${BUN_X} {baseDir}/scripts/weibo-article.ts article.md --cover ./cover.jpg
 - Title: 32 characters max (truncated with warning if longer)
 - Summary/导语: 44 characters max (auto-regenerated from content if longer)
 
+**Markdown-to-HTML**: Do NOT pass any `--theme` parameter when converting markdown to HTML. Use the default theme (no theme argument).
+
 **Article Workflow**:
 1. Opens `https://card.weibo.com/article/v3/editor`
 2. Clicks "写文章" button, waits for editor to become editable

skills/baoyu-url-to-markdown/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: baoyu-url-to-markdown
 description: Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, uses an upgraded Defuddle pipeline with better web-component handling and YouTube transcript extraction, and automatically falls back to the pre-Defuddle HTML-to-Markdown pipeline when needed. If local browser capture fails entirely, it can fall back to the hosted defuddle.md API. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
-version: 1.58.1
+version: 1.59.0
 metadata:
   openclaw:
     homepage: https://github.com/JimLiu/baoyu-skills#baoyu-url-to-markdown
@@ -30,6 +30,9 @@ Fetches any URL via Chrome CDP, saves the rendered HTML snapshot, and converts i
 |--------|---------|
 | `scripts/main.ts` | CLI entry point for URL fetching |
 | `scripts/html-to-markdown.ts` | Markdown conversion entry point and converter selection |
+| `scripts/parsers/index.ts` | Unified parser entry: dispatches URL-specific rules before generic converters |
+| `scripts/parsers/types.ts` | Unified parser interface shared by all rule files |
+| `scripts/parsers/rules/*.ts` | One file per URL rule, for example X status and X article |
 | `scripts/defuddle-converter.ts` | Defuddle-based conversion |
 | `scripts/legacy-converter.ts` | Pre-Defuddle legacy extraction and markdown conversion |
 | `scripts/markdown-conversion-shared.ts` | Shared metadata parsing and markdown document helpers |
@@ -115,10 +118,14 @@ Full reference: [references/config/first-time-setup.md](references/config/first-
 ## Features
 
 - Chrome CDP for full JavaScript rendering
+- Browser strategy fallback: default headless first, then visible Chrome on technical failure
+- URL-specific parser layer for sites that need custom HTML rules before generic extraction
 - Two capture modes: auto or wait-for-user
 - Save rendered HTML as a sibling `-captured.html` file
 - Clean markdown output with metadata
 - Upgraded Defuddle-first markdown conversion with automatic fallback to the pre-Defuddle extractor from git history
+- X/Twitter pages can use HTML-specific parsing for Tweets and Articles, which improves title/body/media extraction on `x.com` / `twitter.com`
+- `archive.ph` / related archive mirrors can restore the original URL from `input[name=q]` and prefer `#CONTENT` before falling back to the page body
 - Materializes shadow DOM content before conversion so web-component pages survive serialization better
 - YouTube pages can include transcript/caption text in the markdown when YouTube exposes a caption track
 - If local browser capture fails completely, can fall back to `defuddle.md/<url>` and still save markdown
@@ -131,6 +138,12 @@ Full reference: [references/config/first-time-setup.md](references/config/first-
 # Auto mode (default) - capture when page loads
 ${BUN_X} {baseDir}/scripts/main.ts <url>
 
+# Force headless only
+${BUN_X} {baseDir}/scripts/main.ts <url> --browser headless
+
+# Force visible browser
+${BUN_X} {baseDir}/scripts/main.ts <url> --browser headed
+
 # Wait mode - wait for user signal before capture
 ${BUN_X} {baseDir}/scripts/main.ts <url> --wait
 
@@ -152,6 +165,9 @@ ${BUN_X} {baseDir}/scripts/main.ts <url> --download-media
 | `-o <path>` | Output file path — must be a **file** path, not directory (default: auto-generated) |
 | `--output-dir <dir>` | Base output directory — auto-generates `{dir}/{domain}/{slug}.md` (default: `./url-to-markdown/`) |
 | `--wait` | Wait for user signal before capturing |
+| `--browser <mode>` | Browser strategy: `auto` (default), `headless`, or `headed` |
+| `--headless` | Shortcut for `--browser headless` |
+| `--headed` | Shortcut for `--browser headed` |
 | `--timeout <ms>` | Page load timeout (default: 30000) |
 | `--download-media` | Download image/video assets to local `imgs/` and `videos/`, and rewrite markdown links to local relative paths |
 
@@ -159,7 +175,7 @@ ${BUN_X} {baseDir}/scripts/main.ts <url> --download-media
 
 | Mode | Behavior | Use When |
 |------|----------|----------|
-| Auto (default) | Capture on network idle | Public pages, static content |
+| Auto (default) | Try headless first, then retry in visible Chrome if needed | Public pages, static content, unknown pages |
 | Wait (`--wait`) | User signals when ready | Login-required, lazy loading, paywalls |
 
 **Wait mode workflow**:
@@ -167,6 +183,43 @@ ${BUN_X} {baseDir}/scripts/main.ts <url> --download-media
 2. Ask user to confirm page is ready
 3. Send newline to stdin to trigger capture
 
+**Default browser fallback**:
+1. Auto mode starts with headless Chrome and captures on network idle
+2. If headless capture fails technically, retry with visible Chrome
+3. If a shared Chrome session for this profile already exists, reuse it instead of launching a new browser
+4. The script does not hard-code login or paywall detection; the agent must inspect the captured markdown or HTML and decide whether to rerun with `--browser headed --wait`
+
+## Agent Quality Gate
+
+**CRITICAL**: The agent must treat headless capture as provisional. Some sites render differently in headless mode and can silently return an error shell, partially hydrated page, or low-quality extraction **without** causing the CLI to fail.
+
+After every run that used `--browser auto` or `--browser headless`, the agent **MUST** inspect the saved markdown first, and inspect the saved `-captured.html` when the markdown looks suspicious.
+
+### Quality checks the agent must perform
+
+1. Confirm the markdown title matches the target page, not a generic site shell
+2. Confirm the body contains the expected article or page content, not just navigation, footer, or a generic error
+3. Watch for obvious failure signs such as:
+   - `Application error`
+   - `This page could not be found`
+   - login, signup, subscribe, or verification shells
+   - extremely short markdown for a page that should be long-form
+   - raw framework payloads or mostly boilerplate content
+4. If the result is low quality, incomplete, or clearly wrong, do **not** accept the run as successful just because the CLI exited with code 0
+
+### Recovery workflow the agent must follow
+
+1. First run with default `auto` unless there is already a clear reason to use wait mode
+2. Review markdown quality immediately after the run
+3. If the content is low quality, rerun locally with visible Chrome:
+   - `--browser headed` for ordinary rendering issues
+   - `--browser headed --wait` when the page may need login, anti-bot interaction, cookie acceptance, or extra hydration time
+4. If `--wait` is used, tell the user exactly what to do:
+   - if login is required, ask them to sign in
+   - if the page needs time to hydrate, ask them to wait until the full content is visible
+   - once ready, ask them to press Enter so capture can continue
+5. Only fall back to hosted `defuddle.md` after the local browser strategies have failed or are clearly lower fidelity
+
 ## Output Format
 
 Each run saves two files side by side:
@@ -201,14 +254,17 @@ When `--download-media` is enabled:
 
 Conversion order:
 
-1. Try Defuddle first
-2. For rich pages such as YouTube, prefer Defuddle's extractor-specific output (including transcripts when available) instead of replacing it with the legacy pipeline
-3. If Defuddle throws, cannot load, returns obviously incomplete markdown, or captures lower-quality content than the legacy pipeline, automatically fall back to the pre-Defuddle extractor
-4. If the entire local browser capture flow fails before markdown can be produced, try the hosted `https://defuddle.md/<url>` API and save its markdown output directly
-5. The legacy fallback path uses the older Readability/selector/Next.js-data based HTML-to-Markdown implementation recovered from git history
+1. Try the URL-specific parser layer first when a site rule matches
+2. If no specialized parser matches, try Defuddle
+3. For rich pages such as YouTube, prefer Defuddle's extractor-specific output (including transcripts when available) instead of replacing it with the legacy pipeline
+4. If Defuddle throws, cannot load, returns obviously incomplete markdown, or captures lower-quality content than the legacy pipeline, automatically fall back to the pre-Defuddle extractor
+5. If the agent determines the captured result is a login screen, verification screen, or paywall shell, rerun locally with `--browser headed --wait` and ask the user to complete access before capture
+6. If the entire local browser capture flow still fails before markdown can be produced, try the hosted `https://defuddle.md/<url>` API and save its markdown output directly
+7. The legacy fallback path uses the older Readability/selector/Next.js-data based HTML-to-Markdown implementation recovered from git history
 
 CLI output will show:
 
+- `Converter: parser:...` when a URL-specific parser succeeded
 - `Converter: defuddle` when Defuddle succeeds
 - `Converter: legacy:...` plus `Fallback used: ...` when fallback was needed
 - `Converter: defuddle-api` when local browser capture failed and the hosted API was used instead

skills/baoyu-url-to-markdown/scripts/bun.lock

@@ -6,7 +6,7 @@
       "dependencies": {
         "@mozilla/readability": "^0.6.0",
         "baoyu-chrome-cdp": "file:./vendor/baoyu-chrome-cdp",
-        "defuddle": "^0.12.0",
+        "defuddle": "^0.14.0",
         "jsdom": "^24.1.3",
         "linkedom": "^0.18.12",
         "turndown": "^7.2.2",
@@ -61,7 +61,7 @@
 
     "decimal.js": ["decimal.js@10.6.0", "", {}, "sha512-YpgQiITW3JXGntzdUmyUR1V812Hn8T1YVXhCu+wO3OpS4eU9l4YdD3qjyiKdV6mvV29zapkMeD390UVEf2lkUg=="],
 
-    "defuddle": ["defuddle@0.12.0", "", { "dependencies": { "commander": "^12.1.0" }, "optionalDependencies": { "mathml-to-latex": "^1.5.0", "temml": "^0.13.1", "turndown": "^7.2.0" }, "peerDependencies": { "jsdom": "^24.0.0" }, "bin": { "defuddle": "dist/cli.js" } }, "sha512-Y/WgyGKBxwxFir+hWNth4nmWDDDb8BzQi3qASS2NWYPXsKU42Ku49/3M5yFYefnRef9prynnmasfnXjk99EWgA=="],
+    "defuddle": ["defuddle@0.14.0", "", { "dependencies": { "commander": "^12.1.0" }, "optionalDependencies": { "linkedom": "^0.18.12", "mathml-to-latex": "^1.5.0", "temml": "^0.13.1", "turndown": "^7.2.0" }, "bin": { "defuddle": "dist/cli.js" } }, "sha512-btavZGd1WgiVqrVM62WGRXMUi/aU7ckTZiq0xXWLZMHvzIqNZjwIFQEDRx8MarD7fIgsB90NXZ9xHJkKtapt2Q=="],
 
     "delayed-stream": ["delayed-stream@1.0.0", "", {}, "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ=="],
 

skills/baoyu-url-to-markdown/scripts/content-cleaner.test.ts

@@ -0,0 +1,55 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import { cleanContent } from "./content-cleaner.js";
+
+const SAMPLE_HTML = `<!doctype html>
+<html>
+  <head>
+    <title>Example Story</title>
+    <style>.cookie-banner { position: fixed; }</style>
+    <script>window.__noise = true;</script>
+  </head>
+  <body>
+    <!-- comment that should be removed -->
+    <header>
+      <nav>
+        <a href="/home">Home</a>
+        <a href="/topics">Topics</a>
+      </nav>
+    </header>
+    <div class="cookie-banner">Accept cookies</div>
+    <aside>Sidebar links</aside>
+    <main>
+      <article class="content">
+        <h1>Actual Story Title</h1>
+        <p>
+          This is the first paragraph of the real story body, and it is intentionally long enough
+          to survive the cleaner's main-content heuristics without being mistaken for navigation.
+        </p>
+        <p>
+          This is the second paragraph with more useful detail, a
+          <a href="/read-more">supporting link</a>, and a normal image.
+        </p>
+        <img src="/images/cover.jpg" alt="Cover">
+        <img src="data:image/png;base64,AAAA" alt="Inline data">
+      </article>
+    </main>
+    <footer>Footer boilerplate</footer>
+  </body>
+</html>`;
+
+test("cleanContent keeps the article body and removes obvious boilerplate", () => {
+  const cleaned = cleanContent(SAMPLE_HTML, "https://example.com/posts/story");
+
+  assert.match(cleaned, /Actual Story Title/);
+  assert.match(cleaned, /https:\/\/example\.com\/read-more/);
+  assert.match(cleaned, /https:\/\/example\.com\/images\/cover\.jpg/);
+
+  assert.doesNotMatch(cleaned, /Accept cookies/);
+  assert.doesNotMatch(cleaned, /Sidebar links/);
+  assert.doesNotMatch(cleaned, /Footer boilerplate/);
+  assert.doesNotMatch(cleaned, /window\.__noise/);
+  assert.doesNotMatch(cleaned, /comment that should be removed/);
+  assert.doesNotMatch(cleaned, /data:image\/png;base64/);
+});

skills/baoyu-url-to-markdown/scripts/content-cleaner.ts

@@ -0,0 +1,432 @@
+import { parseHTML } from "linkedom";
+
+export interface CleaningOptions {
+  removeAds?: boolean;
+  removeBase64Images?: boolean;
+  onlyMainContent?: boolean;
+  includeTags?: string[];
+  excludeTags?: string[];
+}
+
+const ALWAYS_REMOVE_SELECTORS = [
+  "script",
+  "style",
+  "noscript",
+  "link[rel='stylesheet']",
+  "[hidden]",
+  "[aria-hidden='true']",
+  "[style*='display: none']",
+  "[style*='display:none']",
+  "[style*='visibility: hidden']",
+  "[style*='visibility:hidden']",
+  "svg[aria-hidden='true']",
+  "svg.icon",
+  "svg[class*='icon']",
+  "template",
+  "meta",
+  "iframe",
+  "canvas",
+  "object",
+  "embed",
+  "form",
+  "input",
+  "select",
+  "textarea",
+  "button",
+];
+
+const OVERLAY_SELECTORS = [
+  "[class*='modal']",
+  "[class*='popup']",
+  "[class*='overlay']",
+  "[class*='dialog']",
+  "[role='dialog']",
+  "[role='alertdialog']",
+  "[class*='cookie']",
+  "[class*='consent']",
+  "[class*='gdpr']",
+  "[class*='privacy-banner']",
+  "[class*='notification-bar']",
+  "[id*='cookie']",
+  "[id*='consent']",
+  "[id*='gdpr']",
+  "[style*='position: fixed']",
+  "[style*='position:fixed']",
+  "[style*='position: sticky']",
+  "[style*='position:sticky']",
+];
+
+const NAVIGATION_SELECTORS = [
+  "header",
+  "footer",
+  "nav",
+  "aside",
+  ".header",
+  ".top",
+  ".navbar",
+  "#header",
+  ".footer",
+  ".bottom",
+  "#footer",
+  ".sidebar",
+  ".side",
+  ".aside",
+  "#sidebar",
+  ".modal",
+  ".popup",
+  "#modal",
+  ".overlay",
+  ".ad",
+  ".ads",
+  ".advert",
+  "#ad",
+  ".lang-selector",
+  ".language",
+  "#language-selector",
+  ".social",
+  ".social-media",
+  ".social-links",
+  "#social",
+  ".menu",
+  ".navigation",
+  "#nav",
+  ".breadcrumbs",
+  "#breadcrumbs",
+  ".share",
+  "#share",
+  ".widget",
+  "#widget",
+  ".cookie",
+  "#cookie",
+];
+
+const FORCE_INCLUDE_SELECTORS = [
+  "#main",
+  "#content",
+  "#main-content",
+  "#article",
+  "#post",
+  "#page-content",
+  "main",
+  "article",
+  "[role='main']",
+  ".main-content",
+  ".content",
+  ".post-content",
+  ".article-content",
+  ".entry-content",
+  ".page-content",
+  ".article-body",
+  ".post-body",
+  ".story-content",
+  ".blog-content",
+];
+
+const AD_SELECTORS = [
+  "ins.adsbygoogle",
+  ".google-ad",
+  ".adsense",
+  "[data-ad]",
+  "[data-ads]",
+  "[data-ad-slot]",
+  "[data-ad-client]",
+  ".ad-container",
+  ".ad-wrapper",
+  ".advertisement",
+  ".sponsored-content",
+  "img[width='1'][height='1']",
+  "img[src*='pixel']",
+  "img[src*='tracking']",
+  "img[src*='analytics']",
+];
+
+function getLinkDensity(element: Element): number {
+  const text = element.textContent || "";
+  const textLength = text.trim().length;
+  if (textLength === 0) return 1;
+
+  let linkLength = 0;
+  element.querySelectorAll("a").forEach((link: Element) => {
+    linkLength += (link.textContent || "").trim().length;
+  });
+
+  return linkLength / textLength;
+}
+
+function getContentScore(element: Element): number {
+  let score = 0;
+  const text = element.textContent || "";
+  const textLength = text.trim().length;
+
+  score += Math.min(textLength / 100, 50);
+  score += element.querySelectorAll("p").length * 3;
+  score += element.querySelectorAll("h1, h2, h3, h4, h5, h6").length * 2;
+  score += element.querySelectorAll("img").length;
+
+  score -= element.querySelectorAll("a").length * 0.5;
+  score -= element.querySelectorAll("li").length * 0.2;
+
+  const linkDensity = getLinkDensity(element);
+  if (linkDensity > 0.5) score -= 30;
+  else if (linkDensity > 0.3) score -= 15;
+
+  const className = typeof element.className === "string" ? element.className : "";
+  const classAndId = `${className} ${element.id || ""}`;
+  if (/article|content|post|body|main|entry/i.test(classAndId)) score += 25;
+  if (/comment|sidebar|footer|nav|menu|header|widget|ad/i.test(classAndId)) score -= 25;
+
+  return score;
+}
+
+function looksLikeNavigation(element: Element): boolean {
+  const linkDensity = getLinkDensity(element);
+  if (linkDensity > 0.5) return true;
+
+  const listItems = element.querySelectorAll("li");
+  const links = element.querySelectorAll("a");
+  return listItems.length > 5 && links.length > listItems.length * 0.8;
+}
+
+function removeElements(document: Document, selectors: string[]): void {
+  for (const selector of selectors) {
+    try {
+      document.querySelectorAll(selector).forEach((element: Element) => element.remove());
+    } catch {
+      // Ignore unsupported selectors from linkedom/jsdom differences.
+    }
+  }
+}
+
+function removeWithProtection(
+  document: Document,
+  selectorsToRemove: string[],
+  protectedSelectors: string[]
+): void {
+  for (const selector of selectorsToRemove) {
+    try {
+      document.querySelectorAll(selector).forEach((element: Element) => {
+        const isProtected = protectedSelectors.some((protectedSelector) => {
+          try {
+            return element.matches(protectedSelector);
+          } catch {
+            return false;
+          }
+        });
+        if (isProtected) return;
+
+        const containsProtected = protectedSelectors.some((protectedSelector) => {
+          try {
+            return element.querySelector(protectedSelector) !== null;
+          } catch {
+            return false;
+          }
+        });
+        if (containsProtected) return;
+
+        element.remove();
+      });
+    } catch {
+      // Ignore unsupported selectors from linkedom/jsdom differences.
+    }
+  }
+}
+
+function findMainContent(document: Document): Element | null {
+  const isValidContent = (element: Element | null): element is Element => {
+    if (!element) return false;
+    const text = element.textContent || "";
+    if (text.trim().length < 100) return false;
+    return !looksLikeNavigation(element);
+  };
+
+  const main = document.querySelector("main");
+  if (isValidContent(main) && getLinkDensity(main) < 0.4) return main;
+
+  const roleMain = document.querySelector('[role="main"]');
+  if (isValidContent(roleMain) && getLinkDensity(roleMain) < 0.4) return roleMain;
+
+  const articles = document.querySelectorAll("article");
+  if (articles.length === 1 && isValidContent(articles[0] ?? null)) {
+    return articles[0] ?? null;
+  }
+
+  const contentSelectors = [
+    "#content",
+    "#main-content",
+    "#main",
+    ".content",
+    ".main-content",
+    ".post-content",
+    ".article-content",
+    ".entry-content",
+    ".page-content",
+    ".article-body",
+    ".post-body",
+    ".story-content",
+    ".blog-content",
+  ];
+
+  for (const selector of contentSelectors) {
+    try {
+      const element = document.querySelector(selector);
+      if (isValidContent(element) && getLinkDensity(element) < 0.4) {
+        return element;
+      }
+    } catch {
+      // Ignore invalid selectors.
+    }
+  }
+
+  const candidates: Array<{ element: Element; score: number }> = [];
+  const containers = document.querySelectorAll("div, section, article");
+  containers.forEach((element: Element) => {
+    const text = element.textContent || "";
+    if (text.trim().length < 200) return;
+
+    const score = getContentScore(element);
+    if (score > 0) {
+      candidates.push({ element, score });
+    }
+  });
+
+  candidates.sort((left, right) => right.score - left.score);
+  if ((candidates[0]?.score ?? 0) > 20) {
+    return candidates[0]?.element ?? null;
+  }
+
+  return null;
+}
+
+function removeBase64ImagesFromDocument(document: Document): void {
+  document.querySelectorAll("img[src^='data:']").forEach((element: Element) => {
+    element.remove();
+  });
+
+  document.querySelectorAll("[style*='data:image']").forEach((element: Element) => {
+    const style = element.getAttribute("style");
+    if (!style) return;
+
+    const cleanedStyle = style.replace(
+      /background(-image)?:\s*url\([^)]*data:image[^)]*\)[^;]*;?/gi,
+      ""
+    );
+
+    if (cleanedStyle.trim()) {
+      element.setAttribute("style", cleanedStyle);
+    } else {
+      element.removeAttribute("style");
+    }
+  });
+
+  document.querySelectorAll("source[src^='data:'], source[srcset*='data:']").forEach((element: Element) => {
+    element.remove();
+  });
+}
+
+function makeAbsoluteUrl(value: string, baseUrl: string): string | null {
+  try {
+    return new URL(value, baseUrl).toString();
+  } catch {
+    return null;
+  }
+}
+
+function convertRelativeUrls(document: Document, baseUrl: string): void {
+  document.querySelectorAll("[src]").forEach((element: Element) => {
+    const src = element.getAttribute("src");
+    if (!src || src.startsWith("http") || src.startsWith("//") || src.startsWith("data:")) return;
+
+    const absolute = makeAbsoluteUrl(src, baseUrl);
+    if (absolute) element.setAttribute("src", absolute);
+  });
+
+  document.querySelectorAll("[href]").forEach((element: Element) => {
+    const href = element.getAttribute("href");
+    if (
+      !href ||
+      href.startsWith("http") ||
+      href.startsWith("//") ||
+      href.startsWith("#") ||
+      href.startsWith("mailto:") ||
+      href.startsWith("tel:") ||
+      href.startsWith("javascript:")
+    ) {
+      return;
+    }
+
+    const absolute = makeAbsoluteUrl(href, baseUrl);
+    if (absolute) element.setAttribute("href", absolute);
+  });
+}
+
+export function cleanHtml(html: string, baseUrl: string, options: CleaningOptions = {}): string {
+  const {
+    removeAds = true,
+    removeBase64Images = true,
+    onlyMainContent = true,
+    includeTags,
+    excludeTags,
+  } = options;
+
+  const { document } = parseHTML(html);
+
+  removeElements(document, ALWAYS_REMOVE_SELECTORS);
+  removeElements(document, OVERLAY_SELECTORS);
+
+  if (removeAds) {
+    removeElements(document, AD_SELECTORS);
+  }
+
+  if (excludeTags?.length) {
+    removeElements(document, excludeTags);
+  }
+
+  if (onlyMainContent) {
+    removeWithProtection(document, NAVIGATION_SELECTORS, FORCE_INCLUDE_SELECTORS);
+
+    const mainContent = findMainContent(document);
+    if (mainContent && document.body) {
+      const clone = mainContent.cloneNode(true) as Element;
+      document.body.innerHTML = "";
+      document.body.appendChild(clone);
+    }
+  }
+
+  if (includeTags?.length && document.body) {
+    const matchedElements: Element[] = [];
+
+    for (const selector of includeTags) {
+      try {
+        document.querySelectorAll(selector).forEach((element: Element) => {
+          matchedElements.push(element.cloneNode(true) as Element);
+        });
+      } catch {
+        // Ignore invalid selectors.
+      }
+    }
+
+    if (matchedElements.length > 0) {
+      document.body.innerHTML = "";
+      matchedElements.forEach((element) => document.body?.appendChild(element));
+    }
+  }
+
+  if (removeBase64Images) {
+    removeBase64ImagesFromDocument(document);
+  }
+
+  const walker = document.createTreeWalker(document, 128);
+  const comments: Node[] = [];
+  while (walker.nextNode()) {
+    comments.push(walker.currentNode);
+  }
+  comments.forEach((comment) => comment.parentNode?.removeChild(comment));
+
+  convertRelativeUrls(document, baseUrl);
+
+  return document.documentElement?.outerHTML || html;
+}
+
+export function cleanContent(html: string, baseUrl: string, options: CleaningOptions = {}): string {
+  return cleanHtml(html, baseUrl, options);
+}

skills/baoyu-url-to-markdown/scripts/html-to-markdown.test.ts

@@ -0,0 +1,28 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import { extractContent } from "./html-to-markdown.js";
+
+const EMBEDDED_IMAGE_HTML = `<!doctype html>
+<html>
+  <body>
+    <main>
+      <article>
+        <h1>Embedded Image Story</h1>
+        <p>
+          This paragraph is intentionally long enough to satisfy the extractor thresholds so the
+          resulting markdown keeps the main article body and the embedded image reference.
+        </p>
+        <img src="data:image/png;base64,AAAA" alt="inline">
+      </article>
+    </main>
+  </body>
+</html>`;
+
+test("extractContent preserves base64 images when requested for media download", async () => {
+  const result = await extractContent(EMBEDDED_IMAGE_HTML, "https://example.com/embedded", {
+    preserveBase64Images: true,
+  });
+
+  assert.match(result.markdown, /!\[inline\]\(data:image\/png;base64,AAAA\)/);
+});

skills/baoyu-url-to-markdown/scripts/html-to-markdown.ts

@@ -12,10 +12,16 @@ import {
   scoreMarkdownQuality,
   shouldCompareWithLegacy,
 } from "./legacy-converter.js";
+import { tryUrlRuleParsers } from "./parsers/index.js";
+import { cleanContent } from "./content-cleaner.js";
 
 export type { ConversionResult, PageMetadata };
 export { createMarkdownDocument, formatMetadataYaml };
 
+export interface ExtractContentOptions {
+  preserveBase64Images?: boolean;
+}
+
 export const absolutizeUrlsScript = String.raw`
 (function() {
   const baseUrl = document.baseURI || location.href;
@@ -84,7 +90,10 @@ export const absolutizeUrlsScript = String.raw`
   absAttr(htmlClone, "video[poster]", "poster");
   absSrcset(htmlClone, "img[srcset], source[srcset]");
 
-  return { html: "<!doctype html>\n" + htmlClone.outerHTML };
+  return {
+    html: "<!doctype html>\n" + htmlClone.outerHTML,
+    finalUrl: location.href,
+  };
 })()
 `;
 
@@ -101,18 +110,36 @@ function shouldPreferDefuddle(result: ConversionResult): boolean {
   return /^##?\s+transcript\b/im.test(result.markdown);
 }
 
-export async function extractContent(html: string, url: string): Promise<ConversionResult> {
+export async function extractContent(
+  html: string,
+  url: string,
+  options: ExtractContentOptions = {}
+): Promise<ConversionResult> {
   const capturedAt = new Date().toISOString();
   const baseMetadata = extractMetadataFromHtml(html, url, capturedAt);
 
-  const defuddleResult = await tryDefuddleConversion(html, url, baseMetadata);
+  const specializedResult = tryUrlRuleParsers(html, url, baseMetadata);
+  if (specializedResult) {
+    return specializedResult;
+  }
+
+  let cleanedHtml = html;
+  try {
+    cleanedHtml = cleanContent(html, url, {
+      removeBase64Images: !options.preserveBase64Images,
+    });
+  } catch {
+    cleanedHtml = html;
+  }
+
+  const defuddleResult = await tryDefuddleConversion(cleanedHtml, url, baseMetadata);
   if (defuddleResult.ok) {
     if (shouldPreferDefuddle(defuddleResult.result)) {
-      return defuddleResult.result;
+      return { ...defuddleResult.result, rawHtml: html };
     }
 
     if (shouldCompareWithLegacy(defuddleResult.result.markdown)) {
-      const legacyResult = convertWithLegacyExtractor(html, baseMetadata);
+      const legacyResult = convertWithLegacyExtractor(html, baseMetadata, cleanedHtml);
       const legacyScore = scoreMarkdownQuality(legacyResult.markdown);
       const defuddleScore = scoreMarkdownQuality(defuddleResult.result.markdown);
 
@@ -124,10 +151,10 @@ export async function extractContent(html: string, url: string): Promise<Convers
       }
     }
 
-    return defuddleResult.result;
+    return { ...defuddleResult.result, rawHtml: html };
   }
 
-  const fallbackResult = convertWithLegacyExtractor(html, baseMetadata);
+  const fallbackResult = convertWithLegacyExtractor(html, baseMetadata, cleanedHtml);
   return {
     ...fallbackResult,
     fallbackReason: defuddleResult.reason,

skills/baoyu-url-to-markdown/scripts/legacy-converter.test.ts

@@ -0,0 +1,48 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import { cleanContent } from "./content-cleaner.js";
+import { convertWithLegacyExtractor } from "./legacy-converter.js";
+import { extractMetadataFromHtml } from "./markdown-conversion-shared.js";
+
+const CAPTURED_AT = "2026-03-24T03:00:00.000Z";
+
+const NEXT_DATA_HTML = `<!doctype html>
+<html>
+  <head>
+    <title>Hydrated Story</title>
+  </head>
+  <body>
+    <div class="cookie-banner">Accept cookies</div>
+    <main>
+      <p>Short teaser text that should not win over the structured article payload.</p>
+    </main>
+    <script id="__NEXT_DATA__" type="application/json">
+      {
+        "props": {
+          "pageProps": {
+            "article": {
+              "title": "Hydrated Story",
+              "description": "A structured article payload from Next.js",
+              "body": "<p>The full article lives in __NEXT_DATA__ and should still be extracted even when the cleaned HTML removes scripts before the selector and readability passes run.</p><p>A second paragraph keeps the content comfortably above the minimum extraction threshold and proves the legacy extractor still has access to the original structured payload.</p>"
+            }
+          }
+        }
+      }
+    </script>
+  </body>
+</html>`;
+
+test("legacy extractor still uses original __NEXT_DATA__ after HTML cleaning", () => {
+  const url = "https://example.com/posts/hydrated-story";
+  const baseMetadata = extractMetadataFromHtml(NEXT_DATA_HTML, url, CAPTURED_AT);
+  const cleanedHtml = cleanContent(NEXT_DATA_HTML, url);
+
+  const result = convertWithLegacyExtractor(NEXT_DATA_HTML, baseMetadata, cleanedHtml);
+
+  assert.equal(result.conversionMethod, "legacy:next-data");
+  assert.match(result.markdown, /The full article lives in .*NEXT.*DATA/);
+  assert.match(result.markdown, /A second paragraph keeps the content comfortably above the minimum extraction threshold/);
+  assert.doesNotMatch(result.markdown, /Short teaser text that should not win/);
+  assert.equal(result.rawHtml, NEXT_DATA_HTML);
+});

skills/baoyu-url-to-markdown/scripts/legacy-converter.ts

@@ -336,29 +336,32 @@ function tryNextDataExtraction(document: Document): ExtractionCandidate | null {
 
 function buildReadabilityCandidate(
   article: ReturnType<Readability["parse"]>,
-  document: Document,
+  referenceDocument: Document,
   method: string
 ): ExtractionCandidate | null {
   const textContent = article?.textContent?.trim() ?? "";
   if (textContent.length < MIN_CONTENT_LENGTH) return null;
 
   return {
-    title: pickString(article?.title, extractTitle(document)),
+    title: pickString(article?.title, extractTitle(referenceDocument)),
     byline: pickString((article as { byline?: string } | null)?.byline),
     excerpt: pickString(article?.excerpt, generateExcerpt(null, textContent)),
-    published: pickString((article as { publishedTime?: string } | null)?.publishedTime, extractPublishedTime(document)),
+    published: pickString(
+      (article as { publishedTime?: string } | null)?.publishedTime,
+      extractPublishedTime(referenceDocument)
+    ),
     html: article?.content ? sanitizeHtml(article.content) : null,
     textContent,
     method,
   };
 }
 
-function tryReadability(document: Document): ExtractionCandidate | null {
+function tryReadability(document: Document, referenceDocument: Document = document): ExtractionCandidate | null {
   try {
     const strictClone = document.cloneNode(true) as Document;
     const strictResult = buildReadabilityCandidate(
       new Readability(strictClone).parse(),
-      document,
+      referenceDocument,
       "readability"
     );
     if (strictResult) return strictResult;
@@ -366,7 +369,7 @@ function tryReadability(document: Document): ExtractionCandidate | null {
     const relaxedClone = document.cloneNode(true) as Document;
     return buildReadabilityCandidate(
       new Readability(relaxedClone, { charThreshold: 120 }).parse(),
-      document,
+      referenceDocument,
       "readability-relaxed"
     );
   } catch {
@@ -471,14 +474,15 @@ function pickBestCandidate(candidates: ExtractionCandidate[]): ExtractionCandida
   return ranked[0];
 }
 
-function extractFromHtml(html: string): ExtractionCandidate | null {
-  const document = parseDocument(html);
+function extractFromHtml(html: string, cleanedHtml: string = html): ExtractionCandidate | null {
+  const originalDocument = parseDocument(html);
+  const cleanedDocument = parseDocument(cleanedHtml);
 
-  const readabilityCandidate = tryReadability(document);
-  const nextDataCandidate = tryNextDataExtraction(document);
-  const jsonLdCandidate = tryJsonLdExtraction(document);
-  const selectorCandidate = trySelectorExtraction(document);
-  const bodyCandidate = tryBodyExtraction(document);
+  const readabilityCandidate = tryReadability(cleanedDocument, originalDocument);
+  const nextDataCandidate = tryNextDataExtraction(originalDocument);
+  const jsonLdCandidate = tryJsonLdExtraction(originalDocument);
+  const selectorCandidate = trySelectorExtraction(cleanedDocument);
+  const bodyCandidate = tryBodyExtraction(cleanedDocument);
 
   const candidates = [
     readabilityCandidate,
@@ -493,8 +497,8 @@ function extractFromHtml(html: string): ExtractionCandidate | null {
 
   return {
     ...winner,
-    title: winner.title ?? extractTitle(document),
-    published: winner.published ?? extractPublishedTime(document),
+    title: winner.title ?? extractTitle(originalDocument),
+    published: winner.published ?? extractPublishedTime(originalDocument),
     excerpt: winner.excerpt ?? generateExcerpt(null, winner.textContent),
   };
 }
@@ -521,14 +525,18 @@ turndown.addRule("collapseFigure", {
 
 turndown.addRule("dropInvisibleAnchors", {
   filter(node) {
-    return node.nodeName === "A" && !(node as Element).textContent?.trim();
+    return (
+      node.nodeName === "A" &&
+      !(node as Element).textContent?.trim() &&
+      !(node as Element).querySelector("img, video, picture, source")
+    );
   },
   replacement() {
     return "";
   },
 });
 
-function convertHtmlToMarkdown(html: string): string {
+export function convertHtmlFragmentToMarkdown(html: string): string {
   if (!html || !html.trim()) return "";
 
   try {
@@ -606,12 +614,16 @@ export function shouldCompareWithLegacy(markdown: string): boolean {
   );
 }
 
-export function convertWithLegacyExtractor(html: string, baseMetadata: PageMetadata): ConversionResult {
-  const extracted = extractFromHtml(html);
+export function convertWithLegacyExtractor(
+  html: string,
+  baseMetadata: PageMetadata,
+  cleanedHtml: string = html
+): ConversionResult {
+  const extracted = extractFromHtml(html, cleanedHtml);
 
-  let markdown = extracted?.html ? convertHtmlToMarkdown(extracted.html) : "";
+  let markdown = extracted?.html ? convertHtmlFragmentToMarkdown(extracted.html) : "";
   if (!markdown.trim()) {
-    markdown = extracted?.textContent?.trim() || fallbackPlainText(html);
+    markdown = extracted?.textContent?.trim() || fallbackPlainText(cleanedHtml);
   }
 
   return {

skills/baoyu-url-to-markdown/scripts/main.ts

@@ -29,10 +29,33 @@ interface Args {
   wait: boolean;
   timeout: number;
   downloadMedia: boolean;
+  browserMode: BrowserMode;
 }
 
+type BrowserMode = "auto" | "headless" | "headed";
+
+interface CaptureAttemptOptions {
+  headless: boolean;
+  wait: boolean;
+  existingPort?: number;
+  waitPrompt?: string;
+}
+
+interface CaptureSnapshot {
+  html: string;
+  finalUrl: string;
+}
+
+const BROWSER_MODES = new Set<BrowserMode>(["auto", "headless", "headed"]);
+
 function parseArgs(argv: string[]): Args {
-  const args: Args = { url: "", wait: false, timeout: DEFAULT_TIMEOUT_MS, downloadMedia: false };
+  const args: Args = {
+    url: "",
+    wait: false,
+    timeout: DEFAULT_TIMEOUT_MS,
+    downloadMedia: false,
+    browserMode: "auto",
+  };
   for (let i = 2; i < argv.length; i++) {
     const arg = argv[i];
     if (arg === "--wait" || arg === "-w") {
@@ -45,6 +68,12 @@ function parseArgs(argv: string[]): Args {
       args.outputDir = argv[++i];
     } else if (arg === "--download-media") {
       args.downloadMedia = true;
+    } else if (arg === "--browser") {
+      args.browserMode = (argv[++i] as BrowserMode | undefined) ?? "auto";
+    } else if (arg === "--headless") {
+      args.browserMode = "headless";
+    } else if (arg === "--headed" || arg === "--noheadless" || arg === "--no-headless") {
+      args.browserMode = "headed";
     } else if (!arg.startsWith("-") && !args.url) {
       args.url = arg;
     }
@@ -52,15 +81,71 @@ function parseArgs(argv: string[]): Args {
   return args;
 }
 
-function generateSlug(title: string, url: string): string {
-  const text = title || new URL(url).pathname.replace(/\//g, "-");
-  return text
+const SLUG_STOP_WORDS = new Set([
+  "the", "a", "an", "is", "are", "was", "were", "be", "been", "being",
+  "have", "has", "had", "do", "does", "did", "will", "would", "shall",
+  "should", "may", "might", "must", "can", "could", "to", "of", "in",
+  "for", "on", "with", "at", "by", "from", "as", "into", "through",
+  "during", "before", "after", "above", "below", "between", "out",
+  "off", "over", "under", "again", "further", "then", "once", "here",
+  "there", "when", "where", "why", "how", "all", "both", "each",
+  "few", "more", "most", "other", "some", "such", "no", "nor", "not",
+  "only", "own", "same", "so", "than", "too", "very", "just", "but",
+  "and", "or", "if", "this", "that", "these", "those", "it", "its",
+  "http", "https", "www", "com", "org", "net", "post", "article",
+]);
+
+function extractSlugFromContent(content: string): string | null {
+  const body = content.replace(/^---\n[\s\S]*?\n---\n?/, "").slice(0, 1000);
+  const words = body
+    .replace(/[^\w\s-]/g, " ")
+    .split(/\s+/)
+    .filter((w) => /^[a-zA-Z]/.test(w) && w.length >= 2 && !SLUG_STOP_WORDS.has(w.toLowerCase()))
+    .map((w) => w.toLowerCase());
+
+  const unique: string[] = [];
+  const seen = new Set<string>();
+  for (const w of words) {
+    if (!seen.has(w)) {
+      seen.add(w);
+      unique.push(w);
+      if (unique.length >= 6) break;
+    }
+  }
+  return unique.length >= 2 ? unique.join("-").slice(0, 50) : null;
+}
+
+function generateSlug(title: string, url: string, content?: string): string {
+  const asciiWords = title
+    .replace(/[^\w\s]/g, " ")
+    .split(/\s+/)
+    .filter((w) => /[a-zA-Z]/.test(w) && w.length >= 2 && !SLUG_STOP_WORDS.has(w.toLowerCase()))
+    .map((w) => w.toLowerCase());
+
+  if (asciiWords.length >= 2) {
+    return asciiWords.slice(0, 6).join("-").slice(0, 50);
+  }
+
+  if (content) {
+    const contentSlug = extractSlugFromContent(content);
+    if (contentSlug) return contentSlug;
+  }
+
+  const GENERIC_PATH_SEGMENTS = new Set(["status", "article", "post", "posts", "p", "blog", "news", "articles"]);
+  const parsed = new URL(url);
+  const pathSlug = parsed.pathname
+    .split("/")
+    .filter((s) => s.length > 0 && !/^\d{10,}$/.test(s) && !GENERIC_PATH_SEGMENTS.has(s.toLowerCase()))
+    .join("-")
     .toLowerCase()
-    .replace(/[^\w\s-]/g, "")
-    .replace(/\s+/g, "-")
+    .replace(/[^\w-]/g, "-")
     .replace(/-+/g, "-")
     .replace(/^-|-$/g, "")
-    .slice(0, 50) || "page";
+    .slice(0, 40);
+
+  const prefix = asciiWords.slice(0, 2).join("-");
+  const combined = prefix ? `${prefix}-${pathSlug}` : pathSlug;
+  return combined.slice(0, 50) || "page";
 }
 
 function formatTimestamp(): string {
@@ -124,35 +209,42 @@ async function fetchDefuddleApiMarkdown(targetUrl: string): Promise<{ markdown:
   };
 }
 
-async function generateOutputPath(url: string, title: string, outputDir?: string): Promise<string> {
+async function generateOutputPath(url: string, title: string, outputDir?: string, content?: string): Promise<string> {
   const domain = new URL(url).hostname.replace(/^www\./, "");
-  const slug = generateSlug(title, url);
+  const slug = generateSlug(title, url, content);
   const dataDir = outputDir ? path.resolve(outputDir) : resolveUrlToMarkdownDataDir();
-  const basePath = path.join(dataDir, domain, `${slug}.md`);
+  const basePath = path.join(dataDir, domain, slug, `${slug}.md`);
 
   if (!(await fileExists(basePath))) {
     return basePath;
   }
 
   const timestampSlug = `${slug}-${formatTimestamp()}`;
-  return path.join(dataDir, domain, `${timestampSlug}.md`);
+  return path.join(dataDir, domain, timestampSlug, `${timestampSlug}.md`);
 }
 
-async function waitForUserSignal(): Promise<void> {
-  console.log("Page opened. Press Enter when ready to capture...");
+function defaultWaitPrompt(): string {
+  return "A browser window has been opened. If the page requires login or verification, complete it first, then press Enter to capture.";
+}
+
+async function waitForUserSignal(prompt: string): Promise<void> {
+  console.log(prompt);
   const rl = createInterface({ input: process.stdin, output: process.stdout });
   await new Promise<void>((resolve) => {
     rl.once("line", () => { rl.close(); resolve(); });
   });
 }
 
-async function captureUrl(args: Args): Promise<ConversionResult> {
-  const existingPort = await findExistingChromePort();
-  const reusing = existingPort !== null;
-  const port = existingPort ?? await getFreePort();
-  const chrome = reusing ? null : await launchChrome(args.url, port, false);
+async function captureUrlOnce(args: Args, options: CaptureAttemptOptions): Promise<ConversionResult> {
+  const reusing = options.existingPort !== undefined;
+  const port = options.existingPort ?? await getFreePort();
+  const chrome = reusing ? null : await launchChrome(args.url, port, options.headless);
 
-  if (reusing) console.log(`Reusing existing Chrome on port ${port}`);
+  if (reusing) {
+    console.log(`Reusing existing Chrome on port ${port}`);
+  } else {
+    console.log(`Launching Chrome (${options.headless ? "headless" : "headed"})...`);
+  }
 
   let cdp: CdpConnection | null = null;
   let targetId: string | null = null;
@@ -179,8 +271,8 @@ async function captureUrl(args: Args): Promise<ConversionResult> {
       await cdp.send("Page.enable", {}, { sessionId });
     }
 
-    if (args.wait) {
-      await waitForUserSignal();
+    if (options.wait) {
+      await waitForUserSignal(options.waitPrompt ?? defaultWaitPrompt());
     } else {
       console.log("Waiting for page to load...");
       await Promise.race([
@@ -195,11 +287,12 @@ async function captureUrl(args: Args): Promise<ConversionResult> {
     }
 
     console.log("Capturing page content...");
-    const { html } = await evaluateScript<{ html: string }>(
+    const snapshot = await evaluateScript<CaptureSnapshot>(
       cdp, sessionId, absolutizeUrlsScript, args.timeout
     );
-
-    return await extractContent(html, args.url);
+    return await extractContent(snapshot.html, snapshot.finalUrl || args.url, {
+      preserveBase64Images: args.downloadMedia,
+    });
   } finally {
     if (reusing) {
       if (cdp && targetId) {
@@ -216,10 +309,67 @@ async function captureUrl(args: Args): Promise<ConversionResult> {
   }
 }
 
+async function runHeadedFlow(
+  args: Args,
+  options: { existingPort?: number; wait: boolean; waitPrompt?: string }
+): Promise<ConversionResult> {
+  return await captureUrlOnce(args, {
+    headless: false,
+    wait: options.wait,
+    existingPort: options.existingPort,
+    waitPrompt: options.waitPrompt,
+  });
+}
+
+async function captureUrl(args: Args): Promise<ConversionResult> {
+  const existingPort = await findExistingChromePort();
+  if (existingPort !== null) {
+    console.log("Found an existing Chrome session for this profile. Reusing it instead of launching a new browser.");
+    return await runHeadedFlow(args, {
+      existingPort,
+      wait: args.wait,
+      waitPrompt: args.wait ? defaultWaitPrompt() : undefined,
+    });
+  }
+
+  if (args.browserMode === "headless") {
+    return await captureUrlOnce(args, { headless: true, wait: false });
+  }
+
+  if (args.browserMode === "headed") {
+    return await runHeadedFlow(args, {
+      wait: args.wait,
+      waitPrompt: args.wait ? defaultWaitPrompt() : undefined,
+    });
+  }
+
+  if (args.wait) {
+    return await runHeadedFlow(args, {
+      wait: true,
+      waitPrompt: defaultWaitPrompt(),
+    });
+  }
+
+  try {
+    return await captureUrlOnce(args, { headless: true, wait: false });
+  } catch (error) {
+    const headlessMessage = error instanceof Error ? error.message : String(error);
+    console.warn(`Headless capture failed: ${headlessMessage}`);
+    console.log("Retrying with a visible browser window...");
+
+    try {
+      return await runHeadedFlow(args, { wait: false });
+    } catch (headedError) {
+      const headedMessage = headedError instanceof Error ? headedError.message : String(headedError);
+      throw new Error(`Headless capture failed (${headlessMessage}); headed retry failed (${headedMessage})`);
+    }
+  }
+}
+
 async function main(): Promise<void> {
   const args = parseArgs(process.argv);
   if (!args.url) {
-    console.error("Usage: bun main.ts <url> [-o output.md] [--output-dir dir] [--wait] [--timeout ms] [--download-media]");
+    console.error("Usage: bun main.ts <url> [-o output.md] [--output-dir dir] [--wait] [--browser auto|headless|headed] [--timeout ms] [--download-media]");
     process.exit(1);
   }
 
@@ -230,6 +380,16 @@ async function main(): Promise<void> {
     process.exit(1);
   }
 
+  if (!BROWSER_MODES.has(args.browserMode)) {
+    console.error(`Invalid --browser mode: ${args.browserMode}. Expected auto, headless, or headed.`);
+    process.exit(1);
+  }
+
+  if (args.wait && args.browserMode === "headless") {
+    console.error("Error: --wait requires a visible browser. Use --browser auto or --browser headed.");
+    process.exit(1);
+  }
+
   if (args.output) {
     const stat = await import("node:fs").then(fs => fs.statSync(args.output!, { throwIfNoEntry: false }));
     if (stat?.isDirectory()) {
@@ -240,6 +400,7 @@ async function main(): Promise<void> {
 
   console.log(`Fetching: ${args.url}`);
   console.log(`Mode: ${args.wait ? "wait" : "auto"}`);
+  console.log(`Browser: ${args.browserMode}`);
 
   let outputPath: string;
   let htmlSnapshotPath: string | null = null;
@@ -249,13 +410,12 @@ async function main(): Promise<void> {
 
   try {
     const result = await captureUrl(args);
-    outputPath = args.output || await generateOutputPath(args.url, result.metadata.title, args.outputDir);
+    document = createMarkdownDocument(result);
+    outputPath = args.output || await generateOutputPath(result.metadata.url || args.url, result.metadata.title, args.outputDir, document);
     const outputDir = path.dirname(outputPath);
     htmlSnapshotPath = deriveHtmlSnapshotPath(outputPath);
     await mkdir(outputDir, { recursive: true });
     await writeFile(htmlSnapshotPath, result.rawHtml, "utf-8");
-
-    document = createMarkdownDocument(result);
     conversionMethod = result.conversionMethod;
     fallbackReason = result.fallbackReason;
   } catch (error) {
@@ -265,10 +425,9 @@ async function main(): Promise<void> {
 
     try {
       const remoteResult = await fetchDefuddleApiMarkdown(args.url);
-      outputPath = args.output || await generateOutputPath(args.url, remoteResult.title, args.outputDir);
-      await mkdir(path.dirname(outputPath), { recursive: true });
-
       document = remoteResult.markdown;
+      outputPath = args.output || await generateOutputPath(args.url, remoteResult.title, args.outputDir, document);
+      await mkdir(path.dirname(outputPath), { recursive: true });
       conversionMethod = "defuddle-api";
       fallbackReason = `Local browser capture failed: ${primaryError}`;
     } catch (remoteError) {

skills/baoyu-url-to-markdown/scripts/markdown-conversion-shared.ts

@@ -300,6 +300,24 @@ export function createMarkdownDocument(result: ConversionResult): string {
   const escapedTitle = result.metadata.title.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
   const titleRegex = new RegExp(`^#\\s+${escapedTitle}\\s*(\\n|$)`, "i");
   const hasTitle = titleRegex.test(result.markdown.trimStart());
-  const title = result.metadata.title && !hasTitle ? `\n\n# ${result.metadata.title}\n\n` : "\n\n";
+  const firstMeaningfulLine = result.markdown
+    .replace(/\r\n/g, "\n")
+    .split("\n")
+    .map((line) => line.trim())
+    .find((line) => line && !/^!?\[[^\]]*\]\([^)]+\)$/.test(line))
+    ?.replace(/^>\s*/, "")
+    ?.replace(/^#+\s+/, "")
+    ?.trim();
+  const comparableTitle = result.metadata.title.toLowerCase().replace(/(?:\.{3}|…)\s*$/, "");
+  const comparableFirstLine = firstMeaningfulLine?.toLowerCase() ?? "";
+  const titleRepeatsContent =
+    comparableTitle !== "" &&
+    comparableFirstLine !== "" &&
+    (comparableFirstLine === comparableTitle ||
+      comparableFirstLine.startsWith(comparableTitle) ||
+      comparableTitle.startsWith(comparableFirstLine));
+  const title = result.metadata.title && !hasTitle && !titleRepeatsContent
+    ? `\n\n# ${result.metadata.title}\n\n`
+    : "\n\n";
   return yaml + title + result.markdown;
 }

skills/baoyu-url-to-markdown/scripts/media-localizer.test.ts

@@ -0,0 +1,40 @@
+import assert from "node:assert/strict";
+import { mkdtemp, readFile, readdir } from "node:fs/promises";
+import os from "node:os";
+import path from "node:path";
+import test from "node:test";
+
+import { localizeMarkdownMedia } from "./media-localizer.js";
+
+const PNG_1X1_BASE64 =
+  "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/x8AAwMCAO7Z0ioAAAAASUVORK5CYII=";
+
+test("localizeMarkdownMedia saves embedded base64 images into imgs directory", async () => {
+  const tempDir = await mkdtemp(path.join(os.tmpdir(), "url-to-markdown-media-"));
+  const dataUri = `data:image/png;base64,${PNG_1X1_BASE64}`;
+  const markdown = [
+    "---",
+    `coverImage: "${dataUri}"`,
+    "---",
+    "",
+    "# Embedded Image",
+    "",
+    `![inline](${dataUri})`,
+    "",
+  ].join("\n");
+
+  const result = await localizeMarkdownMedia(markdown, {
+    markdownPath: path.join(tempDir, "post.md"),
+  });
+
+  assert.equal(result.downloadedImages, 1);
+  assert.equal(result.downloadedVideos, 0);
+  assert.match(result.markdown, /coverImage: "imgs\/img-001\.png"/);
+  assert.match(result.markdown, /!\[inline\]\(imgs\/img-001\.png\)/);
+
+  const files = await readdir(path.join(tempDir, "imgs"));
+  assert.deepEqual(files, ["img-001.png"]);
+
+  const bytes = await readFile(path.join(tempDir, "imgs", "img-001.png"));
+  assert.equal(bytes.length, Buffer.from(PNG_1X1_BASE64, "base64").length);
+});

skills/baoyu-url-to-markdown/scripts/media-localizer.ts

@@ -3,10 +3,12 @@ import { mkdir, writeFile } from "node:fs/promises";
 
 type MediaKind = "image" | "video";
 type MediaHint = "image" | "unknown";
+type MediaSource = "remote" | "data";
 
 type MarkdownLinkCandidate = {
   url: string;
   hint: MediaHint;
+  source: MediaSource;
 };
 
 export type LocalizeMarkdownMediaOptions = {
@@ -22,8 +24,9 @@ export type LocalizeMarkdownMediaResult = {
   videoDir: string | null;
 };
 
-const MARKDOWN_LINK_RE = /(!?\[[^\]\n]*\])\((<)?(https?:\/\/[^)\s>]+)(>)?\)/g;
-const FRONTMATTER_COVER_RE = /^(coverImage:\s*")(https?:\/\/[^"]+)(")/m;
+const MARKDOWN_LINK_RE =
+  /(!?\[[^\]\n]*\])\((<)?((?:https?:\/\/[^)\s>]+)|(?:data:[^)>\s]+))(>)?\)/g;
+const FRONTMATTER_COVER_RE = /^(coverImage:\s*")((?:https?:\/\/[^"]+)|(?:data:[^"]+))(")/m;
 
 const IMAGE_EXTENSIONS = new Set([
   "jpg",
@@ -86,6 +89,10 @@ function resolveExtensionFromUrl(rawUrl: string): string | undefined {
   return undefined;
 }
 
+function resolveExtensionFromContentType(contentType: string): string | undefined {
+  return normalizeExtension(MIME_EXTENSION_MAP[contentType]);
+}
+
 function resolveKindFromContentType(contentType: string): MediaKind | undefined {
   if (!contentType) return undefined;
   if (contentType.startsWith("image/")) return "image";
@@ -124,7 +131,7 @@ function resolveOutputExtension(
   extension: string | undefined,
   kind: MediaKind
 ): string {
-  const extFromMime = normalizeExtension(MIME_EXTENSION_MAP[contentType]);
+  const extFromMime = resolveExtensionFromContentType(contentType);
   if (extFromMime) return extFromMime;
 
   const normalizedExt = normalizeExtension(extension);
@@ -150,6 +157,10 @@ function sanitizeFileSegment(input: string): string {
 }
 
 function resolveFileStem(rawUrl: string, extension: string): string {
+  if (isDataUri(rawUrl)) {
+    return "";
+  }
+
   try {
     const parsed = new URL(rawUrl);
     const base = path.posix.basename(parsed.pathname);
@@ -172,6 +183,26 @@ function buildFileName(kind: MediaKind, index: number, sourceUrl: string, extens
   return `${prefix}-${serial}${suffix}.${extension}`;
 }
 
+function isDataUri(value: string): boolean {
+  return value.startsWith("data:");
+}
+
+function parseBase64DataUri(rawUrl: string): { contentType: string; bytes: Buffer } | null {
+  const match = rawUrl.match(/^data:([^;,]+);base64,([A-Za-z0-9+/=\s]+)$/i);
+  if (!match?.[1] || !match[2]) return null;
+
+  const contentType = normalizeContentType(match[1]);
+  if (!contentType) return null;
+
+  try {
+    const bytes = Buffer.from(match[2].replace(/\s+/g, ""), "base64");
+    if (bytes.length === 0) return null;
+    return { contentType, bytes };
+  } catch {
+    return null;
+  }
+}
+
 function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[] {
   const candidates: MarkdownLinkCandidate[] = [];
   const seen = new Set<string>();
@@ -181,7 +212,11 @@ function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[
     const coverMatch = fmMatch[1]?.match(FRONTMATTER_COVER_RE);
     if (coverMatch?.[2] && !seen.has(coverMatch[2])) {
       seen.add(coverMatch[2]);
-      candidates.push({ url: coverMatch[2], hint: "image" });
+      candidates.push({
+        url: coverMatch[2],
+        hint: "image",
+        source: isDataUri(coverMatch[2]) ? "data" : "remote",
+      });
     }
   }
 
@@ -195,6 +230,7 @@ function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[
     candidates.push({
       url: rawUrl,
       hint: label.startsWith("![") ? "image" : "unknown",
+      source: isDataUri(rawUrl) ? "data" : "remote",
     });
   }
 
@@ -244,24 +280,45 @@ export async function localizeMarkdownMedia(
 
   for (const candidate of candidates) {
     try {
-      const response = await fetch(candidate.url, {
-        method: "GET",
-        redirect: "follow",
-        headers: {
-          "user-agent": DOWNLOAD_USER_AGENT,
-        },
-      });
+      let sourceUrl = candidate.url;
+      let contentType = "";
+      let extension: string | undefined;
+      let kind: MediaKind | undefined;
+      let bytes: Buffer | null = null;
 
-      if (!response.ok) {
-        log(`[url-to-markdown] Skip media (${response.status}): ${candidate.url}`);
-        continue;
+      if (candidate.source === "data") {
+        const parsed = parseBase64DataUri(candidate.url);
+        if (!parsed) {
+          log("[url-to-markdown] Skip embedded media: unsupported or invalid data URI");
+          continue;
+        }
+
+        contentType = parsed.contentType;
+        extension = resolveExtensionFromContentType(contentType);
+        kind = resolveMediaKind(sourceUrl, contentType, extension, candidate.hint);
+        bytes = parsed.bytes;
+      } else {
+        const response = await fetch(candidate.url, {
+          method: "GET",
+          redirect: "follow",
+          headers: {
+            "user-agent": DOWNLOAD_USER_AGENT,
+          },
+        });
+
+        if (!response.ok) {
+          log(`[url-to-markdown] Skip media (${response.status}): ${candidate.url}`);
+          continue;
+        }
+
+        sourceUrl = response.url || candidate.url;
+        contentType = normalizeContentType(response.headers.get("content-type"));
+        extension = resolveExtensionFromUrl(sourceUrl) ?? resolveExtensionFromUrl(candidate.url);
+        kind = resolveMediaKind(sourceUrl, contentType, extension, candidate.hint);
+        bytes = Buffer.from(await response.arrayBuffer());
       }
 
-      const sourceUrl = response.url || candidate.url;
-      const contentType = normalizeContentType(response.headers.get("content-type"));
-      const extension = resolveExtensionFromUrl(sourceUrl) ?? resolveExtensionFromUrl(candidate.url);
-      const kind = resolveMediaKind(sourceUrl, contentType, extension, candidate.hint);
-      if (!kind) {
+      if (!kind || !bytes) {
         continue;
       }
 
@@ -274,7 +331,6 @@ export async function localizeMarkdownMedia(
       const fileName = buildFileName(kind, nextIndex, sourceUrl, outputExtension);
       const absolutePath = path.join(targetDir, fileName);
       const relativePath = path.posix.join(dirName, fileName);
-      const bytes = Buffer.from(await response.arrayBuffer());
       await writeFile(absolutePath, bytes);
       replacements.set(candidate.url, relativePath);
 
@@ -305,6 +361,7 @@ export function countRemoteMedia(markdown: string): { images: number; videos: nu
   let images = 0;
   let videos = 0;
   for (const c of candidates) {
+    if (c.source !== "remote") continue;
     const ext = resolveExtensionFromUrl(c.url);
     const kind = resolveKindFromExtension(ext);
     if (kind === "video") {

skills/baoyu-url-to-markdown/scripts/package.json

@@ -5,7 +5,7 @@
   "dependencies": {
     "@mozilla/readability": "^0.6.0",
     "baoyu-chrome-cdp": "file:./vendor/baoyu-chrome-cdp",
-    "defuddle": "^0.12.0",
+    "defuddle": "^0.14.0",
     "jsdom": "^24.1.3",
     "linkedom": "^0.18.12",
     "turndown": "^7.2.2",

skills/baoyu-url-to-markdown/scripts/parsers/index.test.ts

@@ -0,0 +1,206 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import {
+  createMarkdownDocument,
+  extractMetadataFromHtml,
+} from "../markdown-conversion-shared.js";
+import { tryUrlRuleParsers } from "./index.js";
+
+const CAPTURED_AT = "2026-03-22T06:00:00.000Z";
+
+const ARTICLE_HTML = `<!doctype html>
+<html lang="zh-CN">
+  <body>
+    <div data-testid="twitterArticleReadView">
+      <a href="/dotey/article/2035141635713941927/media/1">
+        <div data-testid="tweetPhoto">
+          <img src="https://pbs.twimg.com/media/article-cover.jpg" alt="Image">
+        </div>
+      </a>
+      <div data-testid="twitter-article-title">Karpathy："写代码"已经不是对的动词了</div>
+      <div data-testid="User-Name">
+        <a href="/dotey">宝玉 Verified account</a>
+        <a href="/dotey">@dotey</a>
+        <time datetime="2026-03-20T23:49:11.000Z">Mar 20</time>
+      </div>
+      <div data-testid="twitterArticleRichTextView">
+        <p>Andrej Karpathy 说他从 2024 年 12 月起就基本没手写过一行代码。</p>
+        <a href="/dotey/article/2035141635713941927/media/2">
+          <div>
+            <div>
+              <div data-testid="tweetPhoto">
+                <img src="https://pbs.twimg.com/media/article-inline.jpg" alt="Image">
+              </div>
+            </div>
+          </div>
+        </a>
+        <h2>要点速览</h2>
+        <ul>
+          <li>核心焦虑从 GPU 利用率转向 Token 吞吐量</li>
+        </ul>
+        <blockquote>
+          <p>写代码已经不是对的动词了。</p>
+        </blockquote>
+      </div>
+    </div>
+  </body>
+</html>`;
+
+const STATUS_HTML = `<!doctype html>
+<html lang="en">
+  <body>
+    <article data-testid="tweet">
+      <div data-testid="User-Name">
+        <a href="/dotey">宝玉 Verified account</a>
+        <a href="/dotey">@dotey</a>
+        <time datetime="2026-03-22T05:33:00.000Z">Mar 22</time>
+      </div>
+      <div data-testid="tweetText">
+        <span>转译：把下面这段加到你的 Codex 自定义指令里，体验会好太多：</span>
+      </div>
+      <div data-testid="tweetPhoto">
+        <img src="https://pbs.twimg.com/media/tweet-main.jpg" alt="Image">
+      </div>
+      <div data-testid="User-Name">
+        <a href="/mattshumer_">Matt Shumer Verified account</a>
+        <a href="/mattshumer_">@mattshumer_</a>
+        <time datetime="2026-03-17T00:00:00.000Z">Mar 17</time>
+      </div>
+      <div data-testid="tweetText">
+        <span>Add this to your Codex custom instructions for a way better experience.</span>
+      </div>
+    </article>
+  </body>
+</html>`;
+
+const ARCHIVE_HTML = `<!doctype html>
+<html>
+  <head>
+    <title>archive.ph</title>
+  </head>
+  <body>
+    <form>
+      <input
+        type="text"
+        name="q"
+        value="https://www.newscientist.com/article/2520204-major-leap-towards-reanimation-after-death-as-mammals-brain-preserved/"
+      >
+    </form>
+    <div id="HEADER">
+      Archive shell text that should be ignored when CONTENT exists.
+    </div>
+    <div id="CONTENT">
+      <h1>Major leap towards reanimation after death as mammal brain preserved</h1>
+      <p>
+        Researchers say the preserved structure and activity markers suggest a significant step
+        forward in keeping delicate brain tissue viable after clinical death.
+      </p>
+      <p>
+        The archive wrapper should not take precedence over the actual article body when the
+        CONTENT container is available for parsing.
+      </p>
+      <img src="https://cdn.example.com/brain.jpg" alt="Brain tissue">
+    </div>
+  </body>
+</html>`;
+
+const ARCHIVE_FALLBACK_HTML = `<!doctype html>
+<html>
+  <head>
+    <title>archive.ph</title>
+  </head>
+  <body>
+    <input type="text" name="q" value="https://example.com/fallback-story">
+    <main>
+      <h1>Fallback body parsing still works</h1>
+      <p>
+        When CONTENT is absent, the parser should fall back to the body content instead of
+        returning null or keeping the archive wrapper as the final URL.
+      </p>
+      <p>
+        This ensures archived pages with slightly different layouts still produce usable markdown.
+      </p>
+    </main>
+  </body>
+</html>`;
+
+function parse(html: string, url: string) {
+  const baseMetadata = extractMetadataFromHtml(html, url, CAPTURED_AT);
+  return tryUrlRuleParsers(html, url, baseMetadata);
+}
+
+test("parses archive.ph pages from CONTENT and restores the original URL", () => {
+  const result = parse(ARCHIVE_HTML, "https://archive.ph/SMcX5");
+
+  assert.ok(result);
+  assert.equal(result.conversionMethod, "parser:archive-ph");
+  assert.equal(
+    result.metadata.url,
+    "https://www.newscientist.com/article/2520204-major-leap-towards-reanimation-after-death-as-mammals-brain-preserved/"
+  );
+  assert.equal(
+    result.metadata.title,
+    "Major leap towards reanimation after death as mammal brain preserved"
+  );
+  assert.equal(result.metadata.coverImage, "https://cdn.example.com/brain.jpg");
+  assert.ok(result.markdown.includes("Researchers say the preserved structure"));
+  assert.ok(result.markdown.includes("![Brain tissue](https://cdn.example.com/brain.jpg)"));
+  assert.ok(!result.markdown.includes("Archive shell text that should be ignored"));
+});
+
+test("falls back to body when archive.ph CONTENT is missing", () => {
+  const result = parse(ARCHIVE_FALLBACK_HTML, "https://archive.ph/fallback");
+
+  assert.ok(result);
+  assert.equal(result.conversionMethod, "parser:archive-ph");
+  assert.equal(result.metadata.url, "https://example.com/fallback-story");
+  assert.equal(result.metadata.title, "Fallback body parsing still works");
+  assert.ok(result.markdown.includes("When CONTENT is absent"));
+});
+
+test("parses X article pages from HTML", () => {
+  const result = parse(
+    ARTICLE_HTML,
+    "https://x.com/dotey/article/2035141635713941927"
+  );
+
+  assert.ok(result);
+  assert.equal(result.conversionMethod, "parser:x-article");
+  assert.equal(result.metadata.title, "Karpathy：\"写代码\"已经不是对的动词了");
+  assert.equal(result.metadata.author, "宝玉 (@dotey)");
+  assert.equal(result.metadata.coverImage, "https://pbs.twimg.com/media/article-cover.jpg");
+  assert.equal(result.metadata.published, "2026-03-20T23:49:11.000Z");
+  assert.equal(result.metadata.language, "zh");
+  assert.ok(result.markdown.includes("## 要点速览"));
+  assert.ok(
+    result.markdown.includes(
+      "[![](https://pbs.twimg.com/media/article-inline.jpg)](/dotey/article/2035141635713941927/media/2)"
+    )
+  );
+  assert.ok(result.markdown.includes("写代码已经不是对的动词了。"));
+
+  const document = createMarkdownDocument(result);
+  assert.ok(document.includes("# Karpathy：\"写代码\"已经不是对的动词了"));
+});
+
+test("parses X status pages from HTML without duplicating the title heading", () => {
+  const result = parse(
+    STATUS_HTML,
+    "https://x.com/dotey/status/2035590649081196710"
+  );
+
+  assert.ok(result);
+  assert.equal(result.conversionMethod, "parser:x-status");
+  assert.equal(result.metadata.author, "宝玉 (@dotey)");
+  assert.equal(result.metadata.coverImage, "https://pbs.twimg.com/media/tweet-main.jpg");
+  assert.equal(result.metadata.language, "zh");
+  assert.ok(result.markdown.includes("转译：把下面这段加到你的 Codex 自定义指令里"));
+  assert.ok(result.markdown.includes("> Quote from Matt Shumer (@mattshumer_)"));
+  assert.ok(result.markdown.includes("!["));
+
+  const document = createMarkdownDocument(result);
+  assert.ok(
+    !document.includes("\n\n# 转译：把下面这段加到你的 Codex 自定义指令里，体验会好太多：\n\n")
+  );
+});

skills/baoyu-url-to-markdown/scripts/parsers/index.ts

@@ -0,0 +1,47 @@
+import {
+  isMarkdownUsable,
+  normalizeMarkdown,
+  parseDocument,
+  type ConversionResult,
+  type PageMetadata,
+} from "../markdown-conversion-shared.js";
+import { URL_RULE_PARSERS } from "./rules/index.js";
+import type { UrlRuleParserContext } from "./types.js";
+
+export type { UrlRuleParser, UrlRuleParserContext } from "./types.js";
+
+export function tryUrlRuleParsers(
+  html: string,
+  url: string,
+  baseMetadata: PageMetadata
+): ConversionResult | null {
+  const document = parseDocument(html);
+  const context: UrlRuleParserContext = {
+    html,
+    url,
+    document,
+    baseMetadata,
+  };
+
+  for (const parser of URL_RULE_PARSERS) {
+    if (!parser.supports(context)) continue;
+
+    try {
+      const result = parser.parse(context);
+      if (!result) continue;
+
+      const markdown = normalizeMarkdown(result.markdown);
+      if (!isMarkdownUsable(markdown, html)) continue;
+
+      return {
+        ...result,
+        markdown,
+      };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error);
+      console.warn(`[url-to-markdown] parser ${parser.id} failed: ${message}`);
+    }
+  }
+
+  return null;
+}

skills/baoyu-url-to-markdown/scripts/parsers/rules/archive-ph.ts

@@ -0,0 +1,97 @@
+import { convertHtmlFragmentToMarkdown } from "../../legacy-converter.js";
+import {
+  normalizeMarkdown,
+  pickString,
+  type ConversionResult,
+} from "../../markdown-conversion-shared.js";
+import type { UrlRuleParser, UrlRuleParserContext } from "../types.js";
+
+const ARCHIVE_HOSTS = new Set([
+  "archive.ph",
+  "archive.is",
+  "archive.today",
+  "archive.md",
+  "archive.vn",
+  "archive.li",
+  "archive.fo",
+]);
+
+function isArchiveHost(url: string): boolean {
+  try {
+    return ARCHIVE_HOSTS.has(new URL(url).hostname.toLowerCase());
+  } catch {
+    return false;
+  }
+}
+
+function readOriginalUrl(document: Document): string | undefined {
+  const value = document.querySelector("input[name='q']")?.getAttribute("value")?.trim();
+  if (!value) return undefined;
+
+  try {
+    return new URL(value).href;
+  } catch {
+    return undefined;
+  }
+}
+
+function summarize(text: string, maxLength: number): string | undefined {
+  const normalized = text.replace(/\s+/g, " ").trim();
+  if (!normalized) return undefined;
+  if (normalized.length <= maxLength) return normalized;
+  return `${normalized.slice(0, Math.max(0, maxLength - 1)).trimEnd()}…`;
+}
+
+function pickContentRoot(document: Document): Element | null {
+  return (
+    document.querySelector("#CONTENT") ??
+    document.querySelector("#content") ??
+    document.body
+  );
+}
+
+function pickContentTitle(root: Element, fallbackTitle: string): string {
+  const contentTitle = pickString(
+    root.querySelector("h1")?.textContent,
+    root.querySelector("[itemprop='headline']")?.textContent,
+    root.querySelector("article h2")?.textContent
+  );
+  if (contentTitle) return contentTitle;
+  if (fallbackTitle && !/^archive\./i.test(fallbackTitle.trim())) return fallbackTitle;
+  return "";
+}
+
+function parseArchivePage(context: UrlRuleParserContext): ConversionResult | null {
+  const root = pickContentRoot(context.document);
+  if (!root) return null;
+
+  const markdown = normalizeMarkdown(convertHtmlFragmentToMarkdown(root.innerHTML));
+  if (!markdown) return null;
+
+  const originalUrl = readOriginalUrl(context.document) ?? context.baseMetadata.url;
+  const bodyText = root.textContent?.replace(/\s+/g, " ").trim() ?? "";
+  const published = root.querySelector("time[datetime]")?.getAttribute("datetime") ?? undefined;
+  const coverImage = root.querySelector("img[src]")?.getAttribute("src") ?? undefined;
+
+  return {
+    metadata: {
+      ...context.baseMetadata,
+      url: originalUrl,
+      title: pickContentTitle(root, context.baseMetadata.title),
+      description: summarize(bodyText, 220) ?? context.baseMetadata.description,
+      published: pickString(published, context.baseMetadata.published) ?? undefined,
+      coverImage: pickString(coverImage, context.baseMetadata.coverImage) ?? undefined,
+    },
+    markdown,
+    rawHtml: context.html,
+    conversionMethod: "parser:archive-ph",
+  };
+}
+
+export const archivePhRuleParser: UrlRuleParser = {
+  id: "archive-ph",
+  supports(context) {
+    return isArchiveHost(context.url);
+  },
+  parse: parseArchivePage,
+};

skills/baoyu-url-to-markdown/scripts/parsers/rules/index.ts

@@ -0,0 +1,10 @@
+import { archivePhRuleParser } from "./archive-ph.js";
+import { xArticleRuleParser } from "./x-article.js";
+import { xStatusRuleParser } from "./x-status.js";
+import type { UrlRuleParser } from "../types.js";
+
+export const URL_RULE_PARSERS: UrlRuleParser[] = [
+  archivePhRuleParser,
+  xArticleRuleParser,
+  xStatusRuleParser,
+];

skills/baoyu-url-to-markdown/scripts/parsers/rules/x-article.ts

@@ -0,0 +1,137 @@
+import {
+  normalizeMarkdown,
+  pickString,
+  type ConversionResult,
+} from "../../markdown-conversion-shared.js";
+import type { UrlRuleParser, UrlRuleParserContext } from "../types.js";
+import {
+  cleanText,
+  collectMediaMarkdown,
+  convertXRichTextElementToMarkdown,
+  extractPublishedForCurrentUrl,
+  inferLanguage,
+  isXArticlePath,
+  isXHost,
+  normalizeXMarkdown,
+  parseUrl,
+  pickFirstValidLinkText,
+  sanitizeCoverImage,
+  summarizeText,
+} from "./x-shared.js";
+
+function collectArticleMarkdown(root: Element): { markdown: string; mediaUrls: string[] } {
+  const parts: string[] = [];
+  const seenMedia = new Set<string>();
+  const mediaUrls: string[] = [];
+
+  function pushPart(value: string): void {
+    const normalized = normalizeMarkdown(value);
+    if (!normalized) return;
+    parts.push(normalized);
+  }
+
+  function walk(node: Element): void {
+    const testId = node.getAttribute("data-testid");
+
+    if (testId === "twitterArticleRichTextView" || testId === "longformRichTextComponent") {
+      const bodyMedia = collectMediaMarkdown(node, seenMedia);
+      mediaUrls.push(...bodyMedia.urls.filter((url) => !mediaUrls.includes(url)));
+      pushPart(convertXRichTextElementToMarkdown(node));
+      return;
+    }
+
+    if (testId === "tweetPhoto") {
+      const media = collectMediaMarkdown(node, seenMedia);
+      mediaUrls.push(...media.urls.filter((url) => !mediaUrls.includes(url)));
+      for (const line of media.lines) pushPart(line);
+      return;
+    }
+
+    if (
+      testId === "twitter-article-title" ||
+      testId === "User-Name" ||
+      testId === "Tweet-User-Avatar" ||
+      testId === "reply" ||
+      testId === "retweet" ||
+      testId === "like" ||
+      testId === "bookmark" ||
+      testId === "caret" ||
+      testId === "app-text-transition-container"
+    ) {
+      return;
+    }
+
+    if (node.tagName === "TIME" || node.tagName === "BUTTON") {
+      return;
+    }
+
+    for (const child of Array.from(node.children)) {
+      walk(child);
+    }
+  }
+
+  for (const child of Array.from(root.children)) {
+    walk(child);
+  }
+
+  return {
+    markdown: normalizeXMarkdown(parts.join("\n\n")),
+    mediaUrls,
+  };
+}
+
+function parseXArticle(context: UrlRuleParserContext): ConversionResult | null {
+  const articleRoot = context.document.querySelector("[data-testid='twitterArticleReadView']") as Element | null;
+  if (!articleRoot) return null;
+
+  const title = cleanText(
+    context.document.querySelector("[data-testid='twitter-article-title']")?.textContent
+  );
+  const identity = pickFirstValidLinkText(
+    context.document.querySelector("[data-testid='User-Name']")
+  );
+  const published = extractPublishedForCurrentUrl(articleRoot, context.url);
+  const { markdown, mediaUrls } = collectArticleMarkdown(articleRoot);
+  if (!markdown) return null;
+
+  const bodyText = cleanText(
+    context.document.querySelector("[data-testid='twitterArticleRichTextView']")?.textContent ??
+    context.document.querySelector("[data-testid='longformRichTextComponent']")?.textContent
+  );
+
+  return {
+    metadata: {
+      ...context.baseMetadata,
+      title: pickString(title, context.baseMetadata.title) ?? "",
+      description: summarizeText(bodyText, 220) ?? context.baseMetadata.description,
+      author: pickString(identity.author, context.baseMetadata.author) ?? undefined,
+      published: pickString(published, context.baseMetadata.published) ?? undefined,
+      coverImage: sanitizeCoverImage(mediaUrls[0], context.baseMetadata.coverImage),
+      language: inferLanguage(bodyText, context.baseMetadata.language),
+    },
+    markdown,
+    rawHtml: context.html,
+    conversionMethod: "parser:x-article",
+  };
+}
+
+export const xArticleRuleParser: UrlRuleParser = {
+  id: "x-article",
+  supports(context) {
+    const parsed = parseUrl(context.url);
+    if (!parsed || !isXHost(parsed.hostname)) {
+      return false;
+    }
+
+    return (
+      isXArticlePath(parsed.pathname) ||
+      Boolean(
+        context.document.querySelector("[data-testid='twitterArticleReadView']") ||
+        context.document.querySelector("[data-testid='twitterArticleRichTextView']")
+      )
+    );
+  },
+  parse(context) {
+    return parseXArticle(context);
+  },
+};

skills/baoyu-url-to-markdown/scripts/parsers/rules/x-shared.ts

@@ -0,0 +1,249 @@
+import { convertHtmlFragmentToMarkdown } from "../../legacy-converter.js";
+import { normalizeMarkdown } from "../../markdown-conversion-shared.js";
+
+export const DEFAULT_X_OG_IMAGE = "https://abs.twimg.com/rweb/ssr/default/v2/og/image.png";
+
+export type MediaResult = {
+  lines: string[];
+  urls: string[];
+};
+
+export function isXHost(hostname: string): boolean {
+  const normalized = hostname.toLowerCase();
+  return (
+    normalized === "x.com" ||
+    normalized === "twitter.com" ||
+    normalized.endsWith(".x.com") ||
+    normalized.endsWith(".twitter.com")
+  );
+}
+
+export function parseUrl(input: string): URL | null {
+  try {
+    return new URL(input);
+  } catch {
+    return null;
+  }
+}
+
+export function isXStatusPath(pathname: string): boolean {
+  return /^\/[^/]+\/status(?:es)?\/\d+$/i.test(pathname) || /^\/i\/web\/status\/\d+$/i.test(pathname);
+}
+
+export function isXArticlePath(pathname: string): boolean {
+  return /^\/[^/]+\/article\/\d+$/i.test(pathname) || /^\/(?:i\/)?article\/\d+$/i.test(pathname);
+}
+
+export function cleanText(value: string | null | undefined): string {
+  return (value ?? "").replace(/\s+/g, " ").trim();
+}
+
+export function cleanUserLabel(value: string | null | undefined): string {
+  return cleanText(value).replace(/\bVerified account\b/gi, "").replace(/\s{2,}/g, " ").trim();
+}
+
+export function escapeMarkdownAlt(text: string): string {
+  return text.replace(/[\[\]]/g, "\\$&");
+}
+
+export function normalizeAlt(text: string | null | undefined): string {
+  const cleaned = cleanText(text);
+  if (!cleaned || /^(image|photo)$/i.test(cleaned)) return "";
+  return escapeMarkdownAlt(cleaned);
+}
+
+export function summarizeText(text: string, maxLength: number): string | undefined {
+  const normalized = cleanText(text);
+  if (!normalized) return undefined;
+  return normalized.length > maxLength
+    ? `${normalized.slice(0, maxLength - 3)}...`
+    : normalized;
+}
+
+export function buildTweetTitle(text: string, fallback: string): string {
+  return summarizeText(text, 80) ?? fallback;
+}
+
+export function normalizeXMarkdown(markdown: string): string {
+  return normalizeMarkdown(markdown.replace(/^(#{1,6})\s*\n+([^\n])/gm, "$1 $2"));
+}
+
+export function inferLanguage(text: string, fallback?: string): string | undefined {
+  const normalized = cleanText(text);
+  if (!normalized) return fallback;
+
+  const han = (normalized.match(/\p{Script=Han}/gu) || []).length;
+  const hiragana = (normalized.match(/\p{Script=Hiragana}/gu) || []).length;
+  const katakana = (normalized.match(/\p{Script=Katakana}/gu) || []).length;
+  const hangul = (normalized.match(/\p{Script=Hangul}/gu) || []).length;
+
+  if (hangul >= 8) return "ko";
+  if (hiragana + katakana >= 8) return "ja";
+  if (han >= 16) return "zh";
+  return fallback;
+}
+
+export function buildQuoteMarkdown(markdown: string, author?: string): string {
+  const normalized = normalizeMarkdown(markdown);
+  if (!normalized) return "";
+
+  const lines = normalized.split("\n");
+  const prefixed = lines.map((line) => (line ? `> ${line}` : ">")).join("\n");
+  const header = author ? `> Quote from ${author}` : "> Quote";
+  return `${header}\n${prefixed}`;
+}
+
+export function pickFirstValidLinkText(userNameEl: Element | null | undefined): {
+  name?: string;
+  username?: string;
+  author?: string;
+} {
+  if (!userNameEl) return {};
+
+  const linkTexts = Array.from(userNameEl.querySelectorAll("a[href]"))
+    .map((link) => cleanUserLabel(link.textContent))
+    .filter(Boolean);
+
+  let username = linkTexts.find((text) => text.startsWith("@"));
+  let name = linkTexts.find((text) => !text.startsWith("@") && !/^(promote|more)$/i.test(text));
+
+  if (!username || !name) {
+    const text = cleanUserLabel(userNameEl.textContent);
+    const fallbackMatch = text.match(/^(.*?)\s*(@[A-Za-z0-9_]+)(?:\s*·.*)?$/);
+    if (fallbackMatch) {
+      name = name ?? cleanText(fallbackMatch[1]);
+      username = username ?? cleanText(fallbackMatch[2]);
+    }
+  }
+
+  const author = name && username ? `${name} (${username})` : username ?? name;
+  return { name, username, author };
+}
+
+export function extractPublishedForCurrentUrl(root: ParentNode, url: string): string | undefined {
+  const parsed = parseUrl(url);
+  if (!parsed) return undefined;
+  const currentPath = parsed.pathname.toLowerCase();
+
+  for (const timeElement of root.querySelectorAll("a[href] time[datetime]")) {
+    const href = timeElement.closest("a")?.getAttribute("href");
+    const hrefUrl = href ? parseUrl(href.startsWith("http") ? href : `${parsed.origin}${href}`) : null;
+    if (hrefUrl?.pathname.toLowerCase() === currentPath) {
+      return timeElement.getAttribute("datetime") ?? undefined;
+    }
+  }
+
+  return root.querySelector("time[datetime]")?.getAttribute("datetime") ?? undefined;
+}
+
+export function collectMediaMarkdown(root: ParentNode, seen: Set<string>): MediaResult {
+  const lines: string[] = [];
+  const urls: string[] = [];
+  const rootElement = root as Element & {
+    getAttribute?: (name: string) => string | null;
+  };
+  const photoNodes = [
+    ...(typeof rootElement.getAttribute === "function" &&
+    rootElement.getAttribute("data-testid") === "tweetPhoto"
+      ? [rootElement]
+      : []),
+    ...Array.from(root.querySelectorAll("[data-testid='tweetPhoto']")),
+  ];
+
+  for (const node of photoNodes) {
+    const img = node.querySelector("img");
+    const imageUrl = img?.getAttribute("src");
+    if (imageUrl && !seen.has(imageUrl)) {
+      seen.add(imageUrl);
+      urls.push(imageUrl);
+      lines.push(`![${normalizeAlt(img?.getAttribute("alt"))}](${imageUrl})`);
+    }
+
+    const video = node.querySelector("video");
+    const posterUrl = video?.getAttribute("poster");
+    if (posterUrl && !seen.has(posterUrl)) {
+      seen.add(posterUrl);
+      urls.push(posterUrl);
+      lines.push(`![video](${posterUrl})`);
+    }
+
+    const videoUrl = video?.getAttribute("src") ?? video?.querySelector("source")?.getAttribute("src");
+    if (videoUrl && !seen.has(videoUrl)) {
+      seen.add(videoUrl);
+      urls.push(videoUrl);
+      lines.push(`[video](${videoUrl})`);
+    }
+  }
+
+  return { lines, urls };
+}
+
+export function materializeTweetPhotoNodes(root: Element): void {
+  for (const photo of Array.from(root.querySelectorAll("[data-testid='tweetPhoto']"))) {
+    const document = photo.ownerDocument;
+    const container = document.createElement("span");
+
+    const img = photo.querySelector("img");
+    const imageUrl = img?.getAttribute("src");
+    if (imageUrl) {
+      const image = document.createElement("img");
+      image.setAttribute("src", imageUrl);
+      const alt = normalizeAlt(img?.getAttribute("alt"));
+      if (alt) {
+        image.setAttribute("alt", alt);
+      }
+      container.appendChild(image);
+    }
+
+    const video = photo.querySelector("video");
+    const posterUrl = video?.getAttribute("poster");
+    if (posterUrl) {
+      const poster = document.createElement("img");
+      poster.setAttribute("src", posterUrl);
+      poster.setAttribute("alt", "video");
+      container.appendChild(poster);
+    }
+
+    const videoUrl = video?.getAttribute("src") ?? video?.querySelector("source")?.getAttribute("src");
+    if (videoUrl) {
+      if (container.childNodes.length > 0) {
+        container.appendChild(document.createTextNode(" "));
+      }
+      const link = document.createElement("a");
+      link.setAttribute("href", videoUrl);
+      link.textContent = "video";
+      container.appendChild(link);
+    }
+
+    if (container.childNodes.length === 0) {
+      photo.remove();
+      continue;
+    }
+
+    photo.replaceWith(container);
+  }
+}
+
+function collapseLinkedMediaContainers(root: Element): void {
+  for (const anchor of Array.from(root.querySelectorAll("a[href]"))) {
+    const images = Array.from(anchor.querySelectorAll("img"));
+    if (images.length !== 1) continue;
+    if (cleanText(anchor.textContent)) continue;
+
+    const image = images[0].cloneNode(true);
+    anchor.replaceChildren(image);
+  }
+}
+
+export function convertXRichTextElementToMarkdown(node: Element): string {
+  const clone = node.cloneNode(true) as Element;
+  materializeTweetPhotoNodes(clone);
+  collapseLinkedMediaContainers(clone);
+  return normalizeXMarkdown(convertHtmlFragmentToMarkdown(clone.innerHTML));
+}
+
+export function sanitizeCoverImage(primary?: string, fallback?: string): string | undefined {
+  if (primary) return primary;
+  if (!fallback || fallback === DEFAULT_X_OG_IMAGE) return undefined;
+  return fallback;
+}

skills/baoyu-url-to-markdown/scripts/parsers/rules/x-status.ts

@@ -0,0 +1,82 @@
+import type { ConversionResult } from "../../markdown-conversion-shared.js";
+import type { UrlRuleParser, UrlRuleParserContext } from "../types.js";
+import {
+  buildQuoteMarkdown,
+  buildTweetTitle,
+  cleanText,
+  collectMediaMarkdown,
+  convertXRichTextElementToMarkdown,
+  extractPublishedForCurrentUrl,
+  inferLanguage,
+  isXHost,
+  isXStatusPath,
+  normalizeXMarkdown,
+  parseUrl,
+  pickFirstValidLinkText,
+  sanitizeCoverImage,
+  summarizeText,
+} from "./x-shared.js";
+
+function parseXStatus(context: UrlRuleParserContext): ConversionResult | null {
+  const article = context.document.querySelector("article[data-testid='tweet'], article") as Element | null;
+  if (!article) return null;
+
+  const tweetTextElements = Array.from(article.querySelectorAll("[data-testid='tweetText']")) as Element[];
+  if (tweetTextElements.length === 0) return null;
+
+  const userNameElements = Array.from(article.querySelectorAll("[data-testid='User-Name']")) as Element[];
+  const mainTextElement = tweetTextElements[0];
+  const mainIdentity = pickFirstValidLinkText(userNameElements[0]);
+  const published = extractPublishedForCurrentUrl(article, context.url);
+  const mainMarkdown = normalizeXMarkdown(convertXRichTextElementToMarkdown(mainTextElement));
+  if (!mainMarkdown) return null;
+
+  const parts = [mainMarkdown];
+  const quotedTextElements = tweetTextElements.slice(1);
+  const quotedUserNameElements = userNameElements.slice(1);
+
+  quotedTextElements.forEach((element, index) => {
+    const quoteMarkdown = normalizeXMarkdown(convertXRichTextElementToMarkdown(element));
+    if (!quoteMarkdown) return;
+    const quoteIdentity = pickFirstValidLinkText(quotedUserNameElements[index]);
+    parts.push(buildQuoteMarkdown(quoteMarkdown, quoteIdentity.author));
+  });
+
+  const media = collectMediaMarkdown(article, new Set<string>());
+  if (media.lines.length > 0) {
+    parts.push(media.lines.join("\n\n"));
+  }
+
+  const mainText = cleanText(mainTextElement.textContent);
+  const markdown = normalizeXMarkdown(parts.join("\n\n"));
+
+  return {
+    metadata: {
+      ...context.baseMetadata,
+      title: buildTweetTitle(mainText, context.baseMetadata.title),
+      description: summarizeText(mainText, 220) ?? context.baseMetadata.description,
+      author: mainIdentity.author ?? context.baseMetadata.author,
+      published: published ?? context.baseMetadata.published,
+      coverImage: sanitizeCoverImage(media.urls[0], context.baseMetadata.coverImage),
+      language: inferLanguage(mainText, context.baseMetadata.language),
+    },
+    markdown,
+    rawHtml: context.html,
+    conversionMethod: "parser:x-status",
+  };
+}
+
+export const xStatusRuleParser: UrlRuleParser = {
+  id: "x-status",
+  supports(context) {
+    const parsed = parseUrl(context.url);
+    if (!parsed || !isXHost(parsed.hostname)) {
+      return false;
+    }
+
+    return isXStatusPath(parsed.pathname) && Boolean(context.document.querySelector("[data-testid='tweetText']"));
+  },
+  parse(context): ConversionResult | null {
+    return parseXStatus(context);
+  },
+};

skills/baoyu-url-to-markdown/scripts/parsers/types.ts

@@ -0,0 +1,14 @@
+import type { ConversionResult, PageMetadata } from "../markdown-conversion-shared.js";
+
+export interface UrlRuleParserContext {
+  html: string;
+  url: string;
+  document: Document;
+  baseMetadata: PageMetadata;
+}
+
+export interface UrlRuleParser {
+  id: string;
+  supports(context: UrlRuleParserContext): boolean;
+  parse(context: UrlRuleParserContext): ConversionResult | null;
+}

skills/baoyu-xhs-images/references/workflows/prompt-assembly.md

@@ -151,8 +151,7 @@ From outline entry:
 ```markdown
 ## Watermark
 
-Include a subtle watermark "{content}" positioned at {position}
-with approximately {opacity*100}% visibility. The watermark should
+Include a subtle watermark "{content}" positioned at {position}. The watermark should
 be legible but not distracting from the main content.
 ```
 
@@ -295,19 +294,19 @@ Create a Xiaohongshu (Little Red Book) style infographic following these guideli
 ## Content
 
 **Position**: Content (Page 3 of 6)
-**Core Message**: ChatGPT使用技巧
+**Core Message**: ChatGPT 使用技巧
 
 **Text Content**:
 - Title: 「ChatGPT」
-- Subtitle: 最强AI助手
+- Subtitle: 最强 AI 助手
 - Points:
   - 写文案：给出框架，秒出初稿
   - 改文章：润色、翻译、总结
-  - 编程：写代码、找bug
+  - 编程：写代码、找 bug
   - 学习：解释概念、出题练习
 
 **Visual Concept**:
-ChatGPT logo居中，四周放射状展示功能点
+ChatGPT logo 居中，四周放射状展示功能点
 深色科技背景，霓虹绿点缀
 
 ---

skills/baoyu-youtube-transcript/SKILL.md

@@ -0,0 +1,186 @@
+---
+name: baoyu-youtube-transcript
+description: Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants the transcript/subtitle text or cover image extracted.
+version: 1.1.0
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-youtube-transcript
+    requires:
+      anyBins:
+        - bun
+        - npx
+---
+
+# YouTube Transcript
+
+Downloads transcripts (subtitles/captions) from YouTube videos. Works with both manually created and auto-generated transcripts. No API key or browser required — uses YouTube's InnerTube API directly and automatically falls back to `yt-dlp` when YouTube blocks the direct API path.
+
+Fetches video metadata and cover image on first run, caches raw data for fast re-formatting.
+
+## Script Directory
+
+Scripts in `scripts/` subdirectory. `{baseDir}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `{baseDir}` and `${BUN_X}` with actual values.
+
+| Script | Purpose |
+|--------|---------|
+| `scripts/main.ts` | Transcript download CLI |
+
+## Usage
+
+```bash
+# Default: markdown with timestamps (English)
+${BUN_X} {baseDir}/scripts/main.ts <youtube-url-or-id>
+
+# Specify languages (priority order)
+${BUN_X} {baseDir}/scripts/main.ts <url> --languages zh,en,ja
+
+# Without timestamps
+${BUN_X} {baseDir}/scripts/main.ts <url> --no-timestamps
+
+# With chapter segmentation
+${BUN_X} {baseDir}/scripts/main.ts <url> --chapters
+
+# With speaker identification (requires AI post-processing)
+${BUN_X} {baseDir}/scripts/main.ts <url> --speakers
+
+# SRT subtitle file
+${BUN_X} {baseDir}/scripts/main.ts <url> --format srt
+
+# Translate transcript
+${BUN_X} {baseDir}/scripts/main.ts <url> --translate zh-Hans
+
+# List available transcripts
+${BUN_X} {baseDir}/scripts/main.ts <url> --list
+
+# Force re-fetch (ignore cache)
+${BUN_X} {baseDir}/scripts/main.ts <url> --refresh
+```
+
+## Options
+
+| Option | Description | Default |
+|--------|-------------|---------|
+| `<url-or-id>` | YouTube URL or video ID (multiple allowed) | Required |
+| `--languages <codes>` | Language codes, comma-separated, in priority order | `en` |
+| `--format <fmt>` | Output format: `text`, `srt` | `text` |
+| `--translate <code>` | Translate to specified language code | |
+| `--list` | List available transcripts instead of fetching | |
+| `--timestamps` | Include `[HH:MM:SS → HH:MM:SS]` timestamps per paragraph | on |
+| `--no-timestamps` | Disable timestamps | |
+| `--chapters` | Chapter segmentation from video description | |
+| `--speakers` | Raw transcript with metadata for speaker identification | |
+| `--exclude-generated` | Skip auto-generated transcripts | |
+| `--exclude-manually-created` | Skip manually created transcripts | |
+| `--refresh` | Force re-fetch, ignore cached data | |
+| `-o, --output <path>` | Save to specific file path | auto-generated |
+| `--output-dir <dir>` | Base output directory | `youtube-transcript` |
+
+## Optional Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `YOUTUBE_TRANSCRIPT_COOKIES_FROM_BROWSER` | Passed to `yt-dlp --cookies-from-browser` during fallback, e.g. `chrome`, `safari`, `firefox`, or `chrome:Profile 1` |
+
+## Input Formats
+
+Accepts any of these as video input:
+- Full URL: `https://www.youtube.com/watch?v=dQw4w9WgXcQ`
+- Short URL: `https://youtu.be/dQw4w9WgXcQ`
+- Embed URL: `https://www.youtube.com/embed/dQw4w9WgXcQ`
+- Shorts URL: `https://www.youtube.com/shorts/dQw4w9WgXcQ`
+- Video ID: `dQw4w9WgXcQ`
+
+## Output Formats
+
+| Format | Extension | Description |
+|--------|-----------|-------------|
+| `text` | `.md` | Markdown with frontmatter (incl. `description`), title heading, summary, optional TOC/cover/timestamps/chapters/speakers |
+| `srt` | `.srt` | SubRip subtitle format for video players |
+
+## Output Directory
+
+```
+youtube-transcript/
+├── .index.json                          # Video ID → directory path mapping (for cache lookup)
+└── {channel-slug}/{title-full-slug}/
+    ├── meta.json                        # Video metadata (title, channel, description, duration, chapters, etc.)
+    ├── transcript-raw.json              # Raw transcript snippets from YouTube API (cached)
+    ├── transcript-sentences.json        # Sentence-segmented transcript (split by punctuation, merged across snippets)
+    ├── imgs/
+    │   └── cover.jpg                    # Video thumbnail
+    ├── transcript.md                    # Markdown transcript (generated from sentences)
+    └── transcript.srt                   # SRT subtitle (generated from raw snippets, if --format srt)
+```
+
+- `{channel-slug}`: Channel name in kebab-case
+- `{title-full-slug}`: Full video title in kebab-case
+
+The `--list` mode outputs to stdout only (no file saved).
+
+## Caching
+
+On first fetch, the script saves:
+- `meta.json` — video metadata, chapters, cover image path, language info
+- `transcript-raw.json` — raw transcript snippets from YouTube API (`{ text, start, duration }[]`)
+- `transcript-sentences.json` — sentence-segmented transcript (`{ text, start: "HH:mm:ss", end: "HH:mm:ss" }[]`), split by sentence-ending punctuation (`.?!…。？！` etc.), timestamps proportionally allocated by character length, CJK-aware text merging
+- `imgs/cover.jpg` — video thumbnail
+
+Subsequent runs for the same video use cached data (no network calls). Use `--refresh` to force re-fetch. If a different language is requested, the cache is automatically refreshed.
+
+When YouTube returns anti-bot / blocked responses on the direct InnerTube path, the script retries with alternate client identities and then falls back to `yt-dlp` if available. If fallback is needed but `yt-dlp` is unavailable, the agent should decide how to make `yt-dlp` available and continue rather than pushing the installation decision to the user.
+
+SRT output (`--format srt`) is generated from `transcript-raw.json`. Text/markdown output uses `transcript-sentences.json` for natural sentence boundaries.
+
+## Workflow
+
+When user provides a YouTube URL and wants the transcript:
+
+1. Run with `--list` first if the user hasn't specified a language, to show available options
+2. **Always single-quote the URL** when running the script — zsh treats `?` as a glob wildcard, so an unquoted YouTube URL causes "no matches found": use `'https://www.youtube.com/watch?v=ID'`
+3. Default: run with `--chapters --speakers` for the richest output (chapters + speaker identification)
+3. The script auto-saves cached data + output file and prints the file path
+4. For `--speakers` mode: after the script saves the raw file, follow the speaker identification workflow below to post-process with speaker labels
+
+When user only wants a cover image or metadata, running the script with any option will also cache `meta.json` and `imgs/cover.jpg`.
+
+When re-formatting the same video (e.g., first text then SRT), the cached data is reused — no re-fetch needed.
+
+## Chapter & Speaker Workflow
+
+### Chapters (`--chapters`)
+
+The script parses chapter timestamps from the video description (e.g., `0:00 Introduction`), segments the transcript by chapter boundaries, groups snippets into readable paragraphs, and saves as `.md` with a Table of Contents. No further processing needed.
+
+If no chapter timestamps exist in the description, the transcript is output as grouped paragraphs without chapter headings.
+
+### Speaker Identification (`--speakers`)
+
+Speaker identification requires AI processing. The script outputs a raw `.md` file containing:
+- YAML frontmatter with video metadata (title, channel, date, cover, description, language)
+- Video description (for speaker name extraction)
+- Chapter list from description (if available)
+- Raw transcript in SRT format (pre-computed start/end timestamps, token-efficient)
+
+After the script saves the raw file, spawn a sub-agent (use a cheaper model like Sonnet for cost efficiency) to process speaker identification:
+
+1. Read the saved `.md` file
+2. Read the prompt template at `{baseDir}/prompts/speaker-transcript.md`
+3. Process the raw transcript following the prompt:
+   - Identify speakers using video metadata (title → guest, channel → host, description → names)
+   - Detect speaker turns from conversation flow, question-answer patterns, and contextual cues
+   - Segment into chapters (use description chapters if available, else create from topic shifts)
+   - Format with `**Speaker Name:**` labels, paragraph grouping (2-4 sentences), and `[HH:MM:SS → HH:MM:SS]` timestamps
+4. Overwrite the `.md` file with the processed transcript (keep the YAML frontmatter)
+
+When `--speakers` is used, `--chapters` is implied — the processed output always includes chapter segmentation.
+
+## Error Cases
+
+| Error | Meaning |
+|-------|---------|
+| Transcripts disabled | Video has no captions at all |
+| No transcript found | Requested language not available |
+| Video unavailable | Video deleted, private, or region-locked |
+| IP blocked | Too many requests, try again later |
+| Age restricted | Video requires login for age verification |
+| bot detected | The script retries alternate clients and then `yt-dlp`; if fallback tooling is missing, the agent should resolve that itself, otherwise if it still fails try `YOUTUBE_TRANSCRIPT_COOKIES_FROM_BROWSER=safari` (or your browser) |

skills/baoyu-youtube-transcript/prompts/speaker-transcript.md

@@ -0,0 +1,118 @@
+# Speaker & Chapter Transcript Processing
+
+You are an expert transcript specialist. Process the raw transcript file (with YAML frontmatter metadata and SRT-formatted transcript) into a structured, verbatim transcript with speaker identification and chapter segmentation.
+
+## Output Structure
+
+Produce a single cohesive markdown file containing:
+1. YAML frontmatter (keep the original frontmatter from the raw file, which includes `description`)
+2. `# Title` heading (from frontmatter title)
+3. Description/summary paragraph (from frontmatter `description`)
+4. Table of Contents
+5. Cover image (if `cover` exists in frontmatter): `![cover](imgs/cover.jpg)` — right after the ToC
+6. Full chapter-segmented transcript with speaker labels
+
+Use the same language as the transcription for the title and ToC.
+
+## Rules
+
+### Transcription Fidelity
+- Preserve every spoken word exactly, including filler words (`um`, `uh`, `like`) and stutters
+- **NEVER translate.** If the audio mixes languages (e.g., "这个 feature 很酷"), replicate that mix exactly
+
+### Speaker Identification
+- **Priority 1: Use metadata.** Analyze the video's title, channel name, and description to identify speakers
+- **Priority 2: Use transcript content.** Look for introductions, how speakers address each other, contextual cues
+- **Fallback:** Use consistent generic labels (`**Speaker 1:**`, `**Host:**`, etc.)
+- **Consistency:** If a speaker's name is revealed later, update ALL previous labels for that speaker
+
+### Chapter Generation
+- If the raw file contains a `# Chapters` section, use those as the primary basis for segmenting
+- Otherwise, create chapters based on significant topic shifts in the conversation
+
+### Input Format
+- The `# Transcript` section contains SRT-formatted subtitles with pre-computed start/end timestamps
+- Each SRT block has: sequence number, `HH:MM:SS,mmm --> HH:MM:SS,mmm` timestamp line, and text
+- Use the SRT timestamps directly — no need to calculate paragraph start/end times, just merge adjacent blocks
+
+### Formatting
+
+**Timestamps:** Use `[HH:MM:SS → HH:MM:SS]` format (start → end) at the end of each paragraph. No milliseconds.
+
+**Table of Contents:**
+```
+## Table of Contents
+* [HH:MM:SS] Chapter Title
+```
+
+**Chapters:**
+```
+## Chapter Title [HH:MM:SS]
+```
+Two blank lines between chapters.
+
+**Dialogue Paragraphs:**
+- First paragraph of a speaker's turn starts with `**Speaker Name:** `
+- Split long monologues into 2-4 sentence paragraphs separated by blank lines
+- Subsequent paragraphs from the SAME speaker do NOT repeat the speaker label
+- Every paragraph ends with exactly ONE timestamp range `[HH:MM:SS → HH:MM:SS]`
+
+Correct example:
+```
+**Jane Doe:** The study focuses on long-term effects of dietary changes. We tracked two groups over five years. [00:00:15 → 00:00:21]
+
+The first group followed the new regimen, while the second group maintained a traditional diet. [00:00:21 → 00:00:28]
+
+**Host:** Fascinating. And what did you find? [00:00:28 → 00:00:31]
+```
+
+Wrong (multiple timestamps in one paragraph):
+```
+**Host:** Welcome back. [00:00:01] Today we have a guest. [00:00:02]
+```
+
+**Non-Speech Audio:** On its own line: `[Laughter] [HH:MM:SS]`
+
+## Example Output
+
+```markdown
+---
+title: "Example Interview"
+channel: "The Show"
+date: 2024-04-15
+url: "https://www.youtube.com/watch?v=xxx"
+cover: imgs/cover.jpg
+description: "Jane Doe discusses her groundbreaking five-year study on the long-term effects of dietary changes."
+language: en
+---
+
+# Example Interview
+
+Jane Doe discusses her groundbreaking five-year study on the long-term effects of dietary changes.
+
+## Table of Contents
+* [00:00:00] Introduction and Welcome
+* [00:00:12] Overview of the New Research
+
+![cover](imgs/cover.jpg)
+
+
+## Introduction and Welcome [00:00:00]
+
+**Host:** Welcome back to the show. Today, we have a, uh, very special guest, Jane Doe. [00:00:00 → 00:00:03]
+
+**Jane Doe:** Thank you for having me. I'm excited to be here and discuss the findings. [00:00:03 → 00:00:07]
+
+
+## Overview of the New Research [00:00:12]
+
+**Host:** So, Jane, before we get into the nitty-gritty, could you, you know, give us a brief overview for our audience? [00:00:12 → 00:00:16]
+
+**Jane Doe:** Of course. The study focuses on the long-term effects of specific dietary changes. It's a bit complicated but essentially we tracked two large groups over a five-year period. [00:00:16 → 00:00:23]
+
+The first group followed the new regimen, while the second group, our control, maintained a traditional diet. This allowed us to isolate variables effectively. [00:00:23 → 00:00:30]
+
+[Laughter] [00:00:30]
+
+**Host:** Fascinating. And what did you find? [00:00:31 → 00:00:33]
+```

skills/baoyu-youtube-transcript/scripts/main.test.ts

@@ -0,0 +1,125 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+
+import { findTranscript, parseTranscriptJson3, parseWebVtt } from "./transcript.ts";
+import { buildTranscriptListFromYtDlp, resolveVideoSource, selectYtDlpTrack } from "./youtube.ts";
+
+test("selectYtDlpTrack prefers json3 over xml and vtt", () => {
+  const track = selectYtDlpTrack([
+    { ext: "vtt", url: "https://example.com/subs.vtt" },
+    { ext: "srv3", url: "https://example.com/subs.srv3" },
+    { ext: "json3", url: "https://example.com/subs.json3" },
+  ]);
+
+  assert.equal(track?.ext, "json3");
+});
+
+test("buildTranscriptListFromYtDlp keeps manual and generated tracks separate", () => {
+  const transcripts = buildTranscriptListFromYtDlp({
+    subtitles: {
+      en: [
+        { ext: "json3", url: "https://example.com/en.json3", name: "English" },
+      ],
+    },
+    automatic_captions: {
+      "zh-Hans": [
+        { ext: "json3", url: "https://example.com/zh.json3", name: "Chinese (Simplified)" },
+      ],
+    },
+  });
+
+  assert.equal(transcripts.length, 2);
+  assert.equal(transcripts[0].isGenerated, false);
+  assert.equal(transcripts[1].isGenerated, true);
+  assert.equal(transcripts[0].translationLanguages[0]?.languageCode, "zh-Hans");
+
+  const translated = findTranscript(transcripts, ["zh-Hans"], false, false);
+  assert.equal(translated.languageCode, "zh-Hans");
+  assert.equal(translated.isGenerated, true);
+});
+
+test("parseTranscriptJson3 reads youtube timedtext json3 payloads", () => {
+  const snippets = parseTranscriptJson3(JSON.stringify({
+    events: [
+      {
+        tStartMs: 80,
+        dDurationMs: 3120,
+        segs: [{ utf8: "hello\nworld" }],
+      },
+      {
+        tStartMs: 4000,
+        dDurationMs: 1800,
+        segs: [{ utf8: "again" }],
+      },
+    ],
+  }));
+
+  assert.deepEqual(snippets, [
+    { text: "hello world", start: 0.08, duration: 3.12 },
+    { text: "again", start: 4, duration: 1.8 },
+  ]);
+});
+
+test("parseWebVtt strips tags and cue settings", () => {
+  const snippets = parseWebVtt(`WEBVTT
+
+00:00:00.080 --> 00:00:03.200 align:start position:0%
+<c.colorE5E5E5>Hello</c> world
+
+00:00:04.000 --> 00:00:05.800
+Again
+`);
+
+  assert.equal(snippets.length, 2);
+  assert.equal(snippets[0].text, "Hello world");
+  assert.equal(snippets[0].start, 0.08);
+  assert.equal(snippets[0].duration, 3.12);
+  assert.equal(snippets[1].text, "Again");
+  assert.equal(snippets[1].start, 4);
+  assert.equal(Number(snippets[1].duration.toFixed(1)), 1.8);
+});
+
+test("resolveVideoSource prefers primary InnerTube result before fallback", async () => {
+  let fallbackCalled = false;
+  const source = await resolveVideoSource(
+    "video12345ab",
+    async () => ({ kind: "innertube", data: { videoDetails: { title: "Primary" } }, transcripts: [] }),
+    () => {
+      fallbackCalled = true;
+      return {
+        subtitles: {
+          en: [{ ext: "json3", url: "https://example.com/en.json3", name: "English" }],
+        },
+      };
+    },
+    () => {}
+  );
+
+  assert.equal(source.kind, "innertube");
+  assert.equal(fallbackCalled, false);
+});
+
+test("resolveVideoSource falls back to yt-dlp only after fallback-eligible errors", async () => {
+  let fallbackCalled = false;
+  const source = await resolveVideoSource(
+    "video12345ab",
+    async () => {
+      const error = new Error("Request blocked for video12345ab: bot detected");
+      (error as Error & { code?: string }).code = "BOT_DETECTED";
+      throw error;
+    },
+    () => {
+      fallbackCalled = true;
+      return {
+        automatic_captions: {
+          en: [{ ext: "json3", url: "https://example.com/en.json3", name: "English (auto-generated)" }],
+        },
+      };
+    },
+    () => {}
+  );
+
+  assert.equal(source.kind, "yt-dlp");
+  assert.equal(fallbackCalled, true);
+  assert.equal(source.transcripts[0].languageCode, "en");
+});

skills/baoyu-youtube-transcript/scripts/main.ts

@@ -0,0 +1,251 @@
+#!/usr/bin/env bun
+import { writeFileSync } from "fs";
+import { join, resolve } from "path";
+
+import { extractVideoId, slugify } from "./shared.ts";
+import {
+  ensureDir,
+  hasCachedData,
+  loadMeta,
+  loadSentences,
+  loadSnippets,
+  lookupVideoDir,
+  registerVideoDir,
+  resolveBaseDir,
+} from "./storage.ts";
+import { findTranscript, formatListOutput, formatMarkdown, formatSrt, segmentIntoSentences } from "./transcript.ts";
+import type { Options, Sentence, Snippet, VideoMeta, VideoResult } from "./types.ts";
+import {
+  buildVideoMeta,
+  buildVideoMetaFromYtDlp,
+  downloadCoverImage,
+  fetchTranscriptSnippets,
+  fetchVideoSource,
+  getThumbnailUrls,
+  getYtDlpThumbnailUrls,
+  parseChapters,
+} from "./youtube.ts";
+
+async function fetchAndCache(
+  videoId: string,
+  baseDir: string,
+  opts: Options
+): Promise<{ meta: VideoMeta; snippets: Snippet[]; sentences: Sentence[]; videoDir: string }> {
+  const source = await fetchVideoSource(videoId);
+  const requestedLanguages = source.kind === "yt-dlp" && opts.translate ? [opts.translate] : opts.languages;
+  const transcript = findTranscript(source.transcripts, requestedLanguages, opts.excludeGenerated, opts.excludeManual);
+  const result = await fetchTranscriptSnippets(transcript, source.kind === "yt-dlp" ? undefined : opts.translate || undefined);
+  const description = source.kind === "yt-dlp"
+    ? source.info.description || ""
+    : source.data?.videoDetails?.shortDescription || "";
+  const duration = source.kind === "yt-dlp"
+    ? Number(source.info.duration || 0)
+    : parseInt(source.data?.videoDetails?.lengthSeconds || "0");
+  const chapters = parseChapters(description, duration);
+  const language = {
+    code: result.languageCode,
+    name: result.language,
+    isGenerated: transcript.isGenerated,
+  };
+  const meta = source.kind === "yt-dlp"
+    ? buildVideoMetaFromYtDlp(source.info, videoId, language, chapters)
+    : buildVideoMeta(source.data, videoId, language, chapters);
+
+  const videoDir = registerVideoDir(videoId, slugify(meta.channel), slugify(meta.title), baseDir);
+  ensureDir(join(videoDir, "meta.json"));
+
+  writeFileSync(join(videoDir, "transcript-raw.json"), JSON.stringify(result.snippets, null, 2));
+
+  const sentences = segmentIntoSentences(result.snippets);
+  writeFileSync(join(videoDir, "transcript-sentences.json"), JSON.stringify(sentences, null, 2));
+
+  const imagePath = join(videoDir, "imgs", "cover.jpg");
+  ensureDir(imagePath);
+  const downloaded = await downloadCoverImage(
+    source.kind === "yt-dlp" ? getYtDlpThumbnailUrls(videoId, source.info) : getThumbnailUrls(videoId, source.data),
+    imagePath
+  );
+  meta.coverImage = downloaded ? "imgs/cover.jpg" : "";
+
+  writeFileSync(join(videoDir, "meta.json"), JSON.stringify(meta, null, 2));
+
+  return { meta, snippets: result.snippets, sentences, videoDir };
+}
+
+async function processVideo(videoId: string, opts: Options): Promise<VideoResult> {
+  const baseDir = resolveBaseDir(opts.outputDir);
+
+  if (opts.list) {
+    const source = await fetchVideoSource(videoId);
+    const title = source.kind === "yt-dlp" ? source.info.title || "" : source.data?.videoDetails?.title || "";
+    return { videoId, title, content: formatListOutput(videoId, title, source.transcripts) };
+  }
+
+  let videoDir = lookupVideoDir(videoId, baseDir);
+  let meta: VideoMeta;
+  let snippets: Snippet[];
+  let sentences: Sentence[];
+  let needsFetch = opts.refresh || !videoDir || !hasCachedData(videoDir);
+
+  if (!needsFetch && videoDir) {
+    meta = loadMeta(videoDir);
+    snippets = loadSnippets(videoDir);
+    sentences = loadSentences(videoDir);
+    const wantedLanguages = opts.translate ? [opts.translate] : opts.languages;
+    if (!wantedLanguages.includes(meta.language.code)) needsFetch = true;
+    if (!needsFetch && meta.chapters.length > 0 && meta.chapters.some((chapter: any) => chapter.end === undefined)) {
+      for (let i = 0; i < meta.chapters.length; i++) {
+        meta.chapters[i].end = i < meta.chapters.length - 1
+          ? meta.chapters[i + 1].start
+          : Math.max(meta.duration, meta.chapters[i].start);
+      }
+      try {
+        writeFileSync(join(videoDir, "meta.json"), JSON.stringify(meta, null, 2));
+      } catch {}
+    }
+  }
+
+  if (needsFetch) {
+    const result = await fetchAndCache(videoId, baseDir, opts);
+    meta = result.meta;
+    snippets = result.snippets;
+    sentences = result.sentences;
+    videoDir = result.videoDir;
+  } else {
+    meta = meta!;
+    snippets = snippets!;
+    sentences = sentences!;
+  }
+
+  const content = opts.format === "srt"
+    ? formatSrt(snippets)
+    : formatMarkdown(
+      sentences,
+      meta,
+      {
+        timestamps: opts.timestamps,
+        chapters: opts.chapters,
+        speakers: opts.speakers,
+      },
+      snippets
+    );
+  const ext = opts.format === "srt" ? "srt" : "md";
+  const filePath = opts.output ? resolve(opts.output) : join(videoDir!, `transcript.${ext}`);
+  ensureDir(filePath);
+  writeFileSync(filePath, content);
+
+  return { videoId, title: meta.title, filePath };
+}
+
+function printHelp() {
+  console.log(`Usage: bun main.ts <video-url-or-id> [options]
+
+Options:
+  --languages <codes>          Language codes, comma-separated (default: en)
+  --format <fmt>               Output format: text, srt (default: text)
+  --translate <code>           Translate to language code
+  --list                       List available transcripts
+  --timestamps                 Include timestamps (default: on)
+  --no-timestamps              Disable timestamps
+  --chapters                   Chapter segmentation from description
+  --speakers                   Raw transcript with metadata for speaker identification
+  --exclude-generated          Skip auto-generated transcripts
+  --exclude-manually-created   Skip manually created transcripts
+  --refresh                    Force re-fetch (ignore cache)
+  -o, --output <path>          Save to specific file path
+  --output-dir <dir>           Base output directory (default: youtube-transcript)
+  -h, --help                   Show help`);
+}
+
+function parseArgs(argv: string[]): Options | null {
+  const opts: Options = {
+    videoIds: [],
+    languages: ["en"],
+    format: "text",
+    translate: "",
+    list: false,
+    excludeGenerated: false,
+    excludeManual: false,
+    output: "",
+    outputDir: "",
+    timestamps: true,
+    chapters: false,
+    speakers: false,
+    refresh: false,
+  };
+
+  for (let i = 0; i < argv.length; i++) {
+    const arg = argv[i];
+    if (arg === "-h" || arg === "--help") {
+      printHelp();
+      process.exit(0);
+    } else if (arg === "--languages") {
+      const value = argv[++i];
+      if (value) opts.languages = value.split(",").map((entry) => entry.trim());
+    } else if (arg === "--format") {
+      const value = argv[++i]?.toLowerCase();
+      if (value === "text" || value === "srt") opts.format = value;
+      else {
+        console.error(`Invalid format: ${value}. Use: text, srt`);
+        return null;
+      }
+    } else if (arg === "--translate") {
+      opts.translate = argv[++i] || "";
+    } else if (arg === "--list" || arg === "--list-transcripts") {
+      opts.list = true;
+    } else if (arg === "--timestamps" || arg === "-t") {
+      opts.timestamps = true;
+    } else if (arg === "--no-timestamps") {
+      opts.timestamps = false;
+    } else if (arg === "--chapters") {
+      opts.chapters = true;
+    } else if (arg === "--speakers") {
+      opts.speakers = true;
+    } else if (arg === "--exclude-generated") {
+      opts.excludeGenerated = true;
+    } else if (arg === "--exclude-manually-created") {
+      opts.excludeManual = true;
+    } else if (arg === "--refresh") {
+      opts.refresh = true;
+    } else if (arg === "-o" || arg === "--output") {
+      opts.output = argv[++i] || "";
+    } else if (arg === "--output-dir") {
+      opts.outputDir = argv[++i] || "";
+    } else if (!arg.startsWith("-")) {
+      opts.videoIds.push(extractVideoId(arg));
+    }
+  }
+
+  if (opts.videoIds.length === 0) {
+    console.error("Error: At least one video URL or ID required");
+    printHelp();
+    return null;
+  }
+
+  return opts;
+}
+
+async function main() {
+  const opts = parseArgs(process.argv.slice(2));
+  if (!opts) process.exit(1);
+
+  if (opts.excludeGenerated && opts.excludeManual) {
+    console.error("Error: Cannot exclude both generated and manually created transcripts");
+    process.exit(1);
+  }
+
+  for (const videoId of opts.videoIds) {
+    try {
+      const result = await processVideo(videoId, opts);
+      if (result.error) console.error(`Error (${result.videoId}): ${result.error}`);
+      else if (result.filePath) console.log(result.filePath);
+      else if (result.content) console.log(result.content);
+    } catch (error) {
+      console.error(`Error (${videoId}): ${(error as Error).message}`);
+    }
+  }
+}
+
+if (import.meta.main) {
+  main();
+}

skills/baoyu-youtube-transcript/scripts/shared.ts

@@ -0,0 +1,83 @@
+import type { TranscriptError } from "./types.ts";
+
+export function extractVideoId(input: string): string {
+  input = input.replace(/\\/g, "").trim();
+  const patterns = [
+    /(?:youtube\.com\/watch\?.*v=|youtu\.be\/|youtube\.com\/embed\/|youtube\.com\/v\/|youtube\.com\/shorts\/)([a-zA-Z0-9_-]{11})/,
+    /^([a-zA-Z0-9_-]{11})$/,
+  ];
+  for (const pattern of patterns) {
+    const match = input.match(pattern);
+    if (match) return match[1];
+  }
+  return input;
+}
+
+export function slugify(value: string): string {
+  return value
+    .toLowerCase()
+    .replace(/[^\w\s-]/g, "")
+    .replace(/\s+/g, "-")
+    .replace(/-+/g, "-")
+    .replace(/^-|-$/g, "") || "untitled";
+}
+
+export function htmlUnescape(value: string): string {
+  return value
+    .replace(/&/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&#x27;/g, "'")
+    .replace(/&#x2F;/g, "/")
+    .replace(/&apos;/g, "'")
+    .replace(/&#(\d+);/g, (_, n) => String.fromCharCode(parseInt(n)))
+    .replace(/&#x([0-9a-fA-F]+);/g, (_, n) => String.fromCharCode(parseInt(n, 16)));
+}
+
+export function stripTags(value: string): string {
+  return value.replace(/<[^>]*>/g, "");
+}
+
+export function makeError(message: string, code?: string): Error {
+  const error = new Error(message) as TranscriptError;
+  if (code) error.code = code;
+  return error;
+}
+
+export function normalizeError(error: unknown): TranscriptError {
+  if (error instanceof Error) {
+    const known = error as TranscriptError;
+    if (known.code) return known;
+    const message = known.message || String(error);
+    const lower = message.toLowerCase();
+    if (lower.includes("bot detected")) known.code = "BOT_DETECTED";
+    else if (lower.includes("age restricted")) known.code = "AGE_RESTRICTED";
+    else if (lower.includes("video unavailable")) known.code = "VIDEO_UNAVAILABLE";
+    else if (lower.includes("transcripts disabled")) known.code = "TRANSCRIPTS_DISABLED";
+    else if (lower.includes("no transcript found")) known.code = "NO_TRANSCRIPT";
+    else if (lower.includes("invalid video id")) known.code = "INVALID_VIDEO_ID";
+    else if (lower.includes("ip blocked") || lower.includes("recaptcha") || lower.includes("http 429")) known.code = "IP_BLOCKED";
+    else if (lower.includes("cannot extract api key")) known.code = "PAGE_FETCH_FAILED";
+    else if (lower.includes("innertube api") || lower.includes("http 403")) known.code = "INNERTUBE_REJECTED";
+    else if (lower.includes("yt-dlp fallback failed")) known.code = "YT_DLP_FAILED";
+    return known;
+  }
+  return makeError(String(error), "UNKNOWN") as TranscriptError;
+}
+
+export function shouldTryAlternateClient(error: unknown): boolean {
+  const code = normalizeError(error).code;
+  return code === "BOT_DETECTED" || code === "IP_BLOCKED" || code === "INNERTUBE_REJECTED" || code === "AGE_RESTRICTED" || code === "VIDEO_UNAVAILABLE";
+}
+
+export function shouldTryYtDlpFallback(error: unknown): boolean {
+  const code = normalizeError(error).code;
+  return code === "BOT_DETECTED" || code === "IP_BLOCKED" || code === "INNERTUBE_REJECTED" || code === "PAGE_FETCH_FAILED" || code === "AGE_RESTRICTED" || code === "VIDEO_UNAVAILABLE";
+}
+
+export function normalizePublishDate(uploadDate?: string): string {
+  if (!uploadDate || !/^\d{8}$/.test(uploadDate)) return uploadDate || "";
+  return `${uploadDate.slice(0, 4)}-${uploadDate.slice(4, 6)}-${uploadDate.slice(6, 8)}`;
+}

skills/baoyu-youtube-transcript/scripts/storage.ts

@@ -0,0 +1,60 @@
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from "fs";
+import { dirname, join, resolve } from "path";
+
+import type { Sentence, Snippet, VideoMeta } from "./types.ts";
+
+export function ensureDir(path: string) {
+  const dir = dirname(path);
+  if (!existsSync(dir)) mkdirSync(dir, { recursive: true });
+}
+
+export function resolveBaseDir(outputDir: string): string {
+  return resolve(outputDir || "youtube-transcript");
+}
+
+function loadIndex(baseDir: string): Record<string, string> {
+  try {
+    return JSON.parse(readFileSync(join(baseDir, ".index.json"), "utf-8"));
+  } catch {
+    return {};
+  }
+}
+
+function saveIndex(baseDir: string, index: Record<string, string>) {
+  const path = join(baseDir, ".index.json");
+  ensureDir(path);
+  writeFileSync(path, JSON.stringify(index, null, 2));
+}
+
+export function lookupVideoDir(videoId: string, baseDir: string): string | null {
+  const rel = loadIndex(baseDir)[videoId];
+  if (rel) {
+    const dir = resolve(baseDir, rel);
+    if (existsSync(dir)) return dir;
+  }
+  return null;
+}
+
+export function registerVideoDir(videoId: string, channelSlug: string, titleSlug: string, baseDir: string): string {
+  const rel = join(channelSlug, titleSlug);
+  const index = loadIndex(baseDir);
+  index[videoId] = rel;
+  saveIndex(baseDir, index);
+  return resolve(baseDir, rel);
+}
+
+export function hasCachedData(videoDir: string): boolean {
+  return existsSync(join(videoDir, "meta.json")) && existsSync(join(videoDir, "transcript-raw.json"));
+}
+
+export function loadMeta(videoDir: string): VideoMeta {
+  return JSON.parse(readFileSync(join(videoDir, "meta.json"), "utf-8"));
+}
+
+export function loadSnippets(videoDir: string): Snippet[] {
+  return JSON.parse(readFileSync(join(videoDir, "transcript-raw.json"), "utf-8"));
+}
+
+export function loadSentences(videoDir: string): Sentence[] {
+  return JSON.parse(readFileSync(join(videoDir, "transcript-sentences.json"), "utf-8"));
+}

skills/baoyu-youtube-transcript/scripts/transcript.ts

@@ -0,0 +1,349 @@
+import { htmlUnescape, makeError, stripTags } from "./shared.ts";
+import type { Sentence, Snippet, TranscriptInfo, VideoMeta } from "./types.ts";
+
+interface Paragraph {
+  text: string;
+  start: number;
+  end: number;
+}
+
+const SENTENCE_END_RE = /[.?!…。？！⁈⁇‼‽．]/;
+
+export function parseTranscriptXml(xml: string): Snippet[] {
+  const snippets: Snippet[] = [];
+  const pattern = /<text\s+start="([^"]*)"(?:\s+dur="([^"]*)")?[^>]*>([\s\S]*?)<\/text>/g;
+  let match: RegExpExecArray | null;
+  while ((match = pattern.exec(xml)) !== null) {
+    const raw = match[3];
+    if (!raw) continue;
+    snippets.push({
+      text: htmlUnescape(stripTags(raw)),
+      start: parseFloat(match[1]),
+      duration: parseFloat(match[2] || "0"),
+    });
+  }
+  return snippets;
+}
+
+export function parseTranscriptJson3(text: string): Snippet[] {
+  const data = JSON.parse(text);
+  const events = Array.isArray(data?.events) ? data.events : [];
+  const snippets: Snippet[] = [];
+  for (const event of events) {
+    const segs = Array.isArray(event?.segs) ? event.segs : [];
+    const textParts = segs
+      .map((seg: any) => htmlUnescape(String(seg?.utf8 || "").replace(/\n+/g, " ").trim()))
+      .filter(Boolean);
+    const merged = mergeTexts(textParts).trim();
+    if (!merged) continue;
+    snippets.push({
+      text: merged,
+      start: Number(event?.tStartMs || 0) / 1000,
+      duration: Number(event?.dDurationMs || 0) / 1000,
+    });
+  }
+  return snippets;
+}
+
+function parseSrt(srt: string): Snippet[] {
+  const blocks = srt.trim().split(/\n\n+/);
+  const snippets: Snippet[] = [];
+  for (const block of blocks) {
+    const lines = block.split("\n");
+    if (lines.length < 3) continue;
+    const match = lines[1].match(/(\d{2}):(\d{2}):(\d{2}),(\d{3})\s*-->\s*(\d{2}):(\d{2}):(\d{2}),(\d{3})/);
+    if (!match) continue;
+    const start = parseInt(match[1]) * 3600 + parseInt(match[2]) * 60 + parseInt(match[3]) + parseInt(match[4]) / 1000;
+    const end = parseInt(match[5]) * 3600 + parseInt(match[6]) * 60 + parseInt(match[7]) + parseInt(match[8]) / 1000;
+    snippets.push({ text: lines.slice(2).join(" "), start, duration: end - start });
+  }
+  return snippets;
+}
+
+export function parseWebVtt(vtt: string): Snippet[] {
+  const blocks = vtt
+    .replace(/^WEBVTT\s*/m, "")
+    .trim()
+    .split(/\n\n+/);
+  const snippets: Snippet[] = [];
+  for (const block of blocks) {
+    const lines = block.split("\n").map((line) => line.trim()).filter(Boolean);
+    const tsLine = lines.find((line) => line.includes("-->"));
+    if (!tsLine) continue;
+    const match = tsLine.match(
+      /(?:(\d{2}):)?(\d{2}):(\d{2})\.(\d{3})\s*-->\s*(?:(\d{2}):)?(\d{2}):(\d{2})\.(\d{3})/
+    );
+    if (!match) continue;
+    const start =
+      (match[1] ? parseInt(match[1]) : 0) * 3600 +
+      parseInt(match[2]) * 60 +
+      parseInt(match[3]) +
+      parseInt(match[4]) / 1000;
+    const end =
+      (match[5] ? parseInt(match[5]) : 0) * 3600 +
+      parseInt(match[6]) * 60 +
+      parseInt(match[7]) +
+      parseInt(match[8]) / 1000;
+    const text = htmlUnescape(stripTags(lines.slice(lines.indexOf(tsLine) + 1).join(" ").replace(/\s+/g, " ").trim()));
+    if (!text) continue;
+    snippets.push({ text, start, duration: end - start });
+  }
+  return snippets;
+}
+
+export function parseTranscriptPayload(payload: string, url: string): Snippet[] {
+  const normalized = payload.trimStart();
+  if (url.includes("fmt=json3") || normalized.startsWith("{")) return parseTranscriptJson3(payload);
+  if (normalized.startsWith("WEBVTT")) return parseWebVtt(payload);
+  if (/^\d+\s*\n\d{2}:\d{2}:\d{2},\d{3}\s*-->/.test(normalized)) return parseSrt(payload);
+  return parseTranscriptXml(payload);
+}
+
+function isCJK(ch: string): boolean {
+  const code = ch.charCodeAt(0);
+  return (code >= 0x4E00 && code <= 0x9FFF) ||
+    (code >= 0x3040 && code <= 0x309F) ||
+    (code >= 0x30A0 && code <= 0x30FF) ||
+    (code >= 0xAC00 && code <= 0xD7AF) ||
+    (code >= 0x3400 && code <= 0x4DBF) ||
+    (code >= 0xF900 && code <= 0xFAFF);
+}
+
+function splitSnippetAtPunctuation(snippet: Snippet): { text: string; start: number; end: number }[] {
+  const { text, start, duration } = snippet;
+  const end = start + duration;
+  if (!text.length) return [];
+
+  const splitPoints: number[] = [];
+  for (let i = 0; i < text.length; i++) {
+    if (SENTENCE_END_RE.test(text[i])) {
+      while (i + 1 < text.length && SENTENCE_END_RE.test(text[i + 1])) i++;
+      if (i < text.length - 1) splitPoints.push(i);
+    }
+  }
+
+  if (!splitPoints.length) return [{ text, start, end }];
+
+  const parts: { text: string; start: number; end: number }[] = [];
+  let prev = 0;
+  for (const pos of splitPoints) {
+    const partText = text.slice(prev, pos + 1).trim();
+    if (partText) {
+      parts.push({
+        text: partText,
+        start: start + (prev / text.length) * duration,
+        end: start + ((pos + 1) / text.length) * duration,
+      });
+    }
+    prev = pos + 1;
+  }
+
+  const remaining = text.slice(prev).trim();
+  if (remaining) parts.push({ text: remaining, start: start + (prev / text.length) * duration, end });
+
+  return parts;
+}
+
+function mergeTexts(texts: string[]): string {
+  if (!texts.length) return "";
+  let result = texts[0];
+  for (let i = 1; i < texts.length; i++) {
+    const next = texts[i];
+    if (!next) continue;
+    const lastChar = result[result.length - 1];
+    const firstChar = next[0];
+    if (isCJK(lastChar) || isCJK(firstChar)) {
+      result += next;
+    } else {
+      result = result.trimEnd() + " " + next.trimStart();
+    }
+  }
+  return result.replace(/ {2,}/g, " ");
+}
+
+export function ts(time: number): string {
+  const h = Math.floor(time / 3600);
+  const m = Math.floor((time % 3600) / 60);
+  const s = Math.floor(time % 60);
+  return `${String(h).padStart(2, "0")}:${String(m).padStart(2, "0")}:${String(s).padStart(2, "0")}`;
+}
+
+function tsMs(time: number, sep: string): string {
+  const h = Math.floor(time / 3600);
+  const m = Math.floor((time % 3600) / 60);
+  const s = Math.floor(time % 60);
+  const ms = Math.round((time - Math.floor(time)) * 1000);
+  return `${String(h).padStart(2, "0")}:${String(m).padStart(2, "0")}:${String(s).padStart(2, "0")}${sep}${String(ms).padStart(3, "0")}`;
+}
+
+function parseTs(time: string): number {
+  const [h, m, s] = time.split(":").map(Number);
+  return h * 3600 + m * 60 + s;
+}
+
+export function segmentIntoSentences(snippets: Snippet[]): Sentence[] {
+  const parts: { text: string; start: number; end: number }[] = [];
+  for (const snippet of snippets) parts.push(...splitSnippetAtPunctuation(snippet));
+
+  const sentences: Sentence[] = [];
+  let buffer: { text: string; start: number; end: number }[] = [];
+
+  for (const part of parts) {
+    buffer.push(part);
+    if (SENTENCE_END_RE.test(part.text[part.text.length - 1])) {
+      sentences.push({
+        text: mergeTexts(buffer.map((entry) => entry.text)),
+        start: ts(buffer[0].start),
+        end: ts(buffer[buffer.length - 1].end),
+      });
+      buffer = [];
+    }
+  }
+
+  if (buffer.length) {
+    sentences.push({
+      text: mergeTexts(buffer.map((entry) => entry.text)),
+      start: ts(buffer[0].start),
+      end: ts(buffer[buffer.length - 1].end),
+    });
+  }
+
+  return sentences;
+}
+
+function groupSentenceParas(sentences: Sentence[]): Paragraph[] {
+  if (!sentences.length) return [];
+  const paragraphs: Paragraph[] = [];
+  let buffer: Sentence[] = [];
+  for (let i = 0; i < sentences.length; i++) {
+    buffer.push(sentences[i]);
+    const last = i === sentences.length - 1;
+    const gap = !last && parseTs(sentences[i + 1].start) - parseTs(sentences[i].end) > 2;
+    if (last || gap || buffer.length >= 5) {
+      paragraphs.push({
+        text: mergeTexts(buffer.map((sentence) => sentence.text)),
+        start: parseTs(buffer[0].start),
+        end: parseTs(buffer[buffer.length - 1].end),
+      });
+      buffer = [];
+    }
+  }
+  return paragraphs;
+}
+
+export function formatSrt(snippets: Snippet[]): string {
+  return snippets
+    .map((snippet, index) => {
+      const end = index < snippets.length - 1 && snippets[index + 1].start < snippet.start + snippet.duration
+        ? snippets[index + 1].start
+        : snippet.start + snippet.duration;
+      return `${index + 1}\n${tsMs(snippet.start, ",")} --> ${tsMs(end, ",")}\n${snippet.text}`;
+    })
+    .join("\n\n") + "\n";
+}
+
+function yamlEscape(value: string): string {
+  if (/[:"'{}\[\]#&*!|>%@`\n]/.test(value) || value.trim() !== value) {
+    return `"${value.replace(/\\/g, "\\\\").replace(/"/g, '\\"')}"`;
+  }
+  return value;
+}
+
+function extractSummary(description: string): string {
+  if (!description) return "";
+  const firstPara = description.split(/\n\s*\n/)[0].trim();
+  const lines = firstPara.split("\n").filter((line) => !/^\s*(https?:\/\/|#|@|\d+:\d+)/.test(line) && line.trim());
+  return lines.join(" ").slice(0, 300).trim();
+}
+
+export function formatMarkdown(
+  sentences: Sentence[],
+  meta: VideoMeta,
+  opts: { timestamps: boolean; chapters: boolean; speakers: boolean },
+  snippets?: Snippet[]
+): string {
+  const summary = extractSummary(meta.description);
+  let md = "---\n";
+  md += `title: ${yamlEscape(meta.title)}\n`;
+  md += `channel: ${yamlEscape(meta.channel)}\n`;
+  if (meta.publishDate) md += `date: ${meta.publishDate}\n`;
+  md += `url: ${yamlEscape(meta.url)}\n`;
+  if (meta.coverImage) md += `cover: ${meta.coverImage}\n`;
+  if (summary) md += `description: ${yamlEscape(summary)}\n`;
+  if (meta.language) md += `language: ${meta.language.code}\n`;
+  md += "---\n\n";
+
+  if (opts.speakers) {
+    md += `# ${meta.title}\n\n`;
+    if (summary) md += `${summary}\n\n`;
+    if (meta.description) md += `# Description\n\n${meta.description.trim()}\n\n`;
+    if (meta.chapters.length) {
+      md += "# Chapters\n\n";
+      for (const chapter of meta.chapters) md += `* [${ts(chapter.start)}] ${chapter.title}\n`;
+      md += "\n";
+    }
+    md += "# Transcript\n\n";
+    md += snippets ? formatSrt(snippets) : "";
+    return md;
+  }
+
+  md += `# ${meta.title}\n\n`;
+  if (summary) md += `${summary}\n\n`;
+
+  const chapters = opts.chapters ? meta.chapters : [];
+  if (chapters.length) {
+    md += "## Table of Contents\n\n";
+    for (const chapter of chapters) md += opts.timestamps ? `* [${ts(chapter.start)}] ${chapter.title}\n` : `* ${chapter.title}\n`;
+    md += "\n";
+    if (meta.coverImage) md += `\n![cover](${meta.coverImage})\n`;
+    md += "\n";
+    for (let i = 0; i < chapters.length; i++) {
+      const nextStart = i < chapters.length - 1 ? chapters[i + 1].start : Infinity;
+      const chapterSentences = sentences.filter((sentence) => parseTs(sentence.start) >= chapters[i].start && parseTs(sentence.start) < nextStart);
+      const paragraphs = groupSentenceParas(chapterSentences);
+      md += opts.timestamps ? `## [${ts(chapters[i].start)}] ${chapters[i].title}\n\n` : `## ${chapters[i].title}\n\n`;
+      for (const paragraph of paragraphs) {
+        md += opts.timestamps ? `${paragraph.text} [${ts(paragraph.start)} → ${ts(paragraph.end)}]\n\n` : `${paragraph.text}\n\n`;
+      }
+      md += "\n";
+    }
+  } else {
+    const paragraphs = groupSentenceParas(sentences);
+    for (const paragraph of paragraphs) {
+      md += opts.timestamps ? `${paragraph.text} [${ts(paragraph.start)} → ${ts(paragraph.end)}]\n\n` : `${paragraph.text}\n\n`;
+    }
+  }
+
+  return md.trimEnd() + "\n";
+}
+
+export function formatListOutput(videoId: string, title: string, transcripts: TranscriptInfo[]): string {
+  const manual = transcripts.filter((transcript) => !transcript.isGenerated);
+  const generated = transcripts.filter((transcript) => transcript.isGenerated);
+  const translationLanguages = transcripts.find((transcript) => transcript.translationLanguages.length > 0)?.translationLanguages || [];
+  const formatList = (list: TranscriptInfo[]) =>
+    list.length
+      ? list.map((transcript) => ` - ${transcript.languageCode} ("${transcript.language}")${transcript.isTranslatable ? " [TRANSLATABLE]" : ""}`).join("\n")
+      : "None";
+  const formatTranslations = translationLanguages.length
+    ? translationLanguages.map((language) => ` - ${language.languageCode} ("${language.language}")`).join("\n")
+    : "None";
+  return `Transcripts for ${videoId}${title ? ` (${title})` : ""}:\n\n(MANUALLY CREATED)\n${formatList(manual)}\n\n(GENERATED)\n${formatList(generated)}\n\n(TRANSLATION LANGUAGES)\n${formatTranslations}`;
+}
+
+export function findTranscript(
+  transcripts: TranscriptInfo[],
+  languages: string[],
+  excludeGenerated: boolean,
+  excludeManual: boolean
+): TranscriptInfo {
+  let filtered = transcripts;
+  if (excludeGenerated) filtered = filtered.filter((transcript) => !transcript.isGenerated);
+  if (excludeManual) filtered = filtered.filter((transcript) => transcript.isGenerated);
+  for (const language of languages) {
+    const found = filtered.find((transcript) => transcript.languageCode === language);
+    if (found) return found;
+  }
+  const available = filtered.map((transcript) => `${transcript.languageCode} ("${transcript.language}")`).join(", ");
+  throw makeError(`No transcript found for languages [${languages.join(", ")}]. Available: ${available || "none"}`, "NO_TRANSCRIPT");
+}

skills/baoyu-youtube-transcript/scripts/types.ts

@@ -0,0 +1,123 @@
+export type Format = "text" | "srt";
+
+export interface Options {
+  videoIds: string[];
+  languages: string[];
+  format: Format;
+  translate: string;
+  list: boolean;
+  excludeGenerated: boolean;
+  excludeManual: boolean;
+  output: string;
+  outputDir: string;
+  timestamps: boolean;
+  chapters: boolean;
+  speakers: boolean;
+  refresh: boolean;
+}
+
+export interface Snippet {
+  text: string;
+  start: number;
+  duration: number;
+}
+
+export interface Sentence {
+  text: string;
+  start: string;
+  end: string;
+}
+
+export interface TranscriptLanguage {
+  language: string;
+  languageCode: string;
+}
+
+export interface TranscriptInfo {
+  language: string;
+  languageCode: string;
+  isGenerated: boolean;
+  isTranslatable: boolean;
+  baseUrl: string;
+  translationLanguages: TranscriptLanguage[];
+}
+
+export interface Chapter {
+  title: string;
+  start: number;
+  end: number;
+}
+
+export interface LanguageMeta {
+  code: string;
+  name: string;
+  isGenerated: boolean;
+}
+
+export interface VideoMeta {
+  videoId: string;
+  title: string;
+  channel: string;
+  channelId: string;
+  description: string;
+  duration: number;
+  publishDate: string;
+  url: string;
+  coverImage: string;
+  thumbnailUrl: string;
+  language: LanguageMeta;
+  chapters: Chapter[];
+}
+
+export interface VideoResult {
+  videoId: string;
+  title?: string;
+  filePath?: string;
+  content?: string;
+  error?: string;
+}
+
+export interface InnerTubeSession {
+  apiKey: string;
+  webClientVersion: string;
+  visitorData: string;
+}
+
+export interface InnerTubeClient {
+  id: string;
+  clientName: string;
+  clientVersion?: string;
+  clientHeaderName?: string;
+  userAgent: string;
+  extraContext?: Record<string, any>;
+}
+
+export interface TranscriptError extends Error {
+  code?: string;
+}
+
+export interface YtDlpTrack {
+  ext?: string;
+  url?: string;
+  name?: string;
+}
+
+export interface YtDlpInfo {
+  title?: string;
+  channel?: string;
+  channel_id?: string;
+  uploader?: string;
+  uploader_id?: string;
+  description?: string;
+  duration?: number;
+  upload_date?: string;
+  webpage_url?: string;
+  thumbnail?: string;
+  thumbnails?: { url?: string; width?: number; height?: number }[];
+  subtitles?: Record<string, YtDlpTrack[]>;
+  automatic_captions?: Record<string, YtDlpTrack[]>;
+}
+
+export type VideoSource =
+  | { kind: "innertube"; data: any; transcripts: TranscriptInfo[] }
+  | { kind: "yt-dlp"; info: YtDlpInfo; transcripts: TranscriptInfo[] };

skills/baoyu-youtube-transcript/scripts/youtube.ts

@@ -0,0 +1,477 @@
+import { spawnSync } from "child_process";
+import { writeFileSync } from "fs";
+
+import { makeError, normalizeError, normalizePublishDate, shouldTryAlternateClient, shouldTryYtDlpFallback } from "./shared.ts";
+import { parseTranscriptPayload } from "./transcript.ts";
+import type {
+  Chapter,
+  InnerTubeClient,
+  InnerTubeSession,
+  LanguageMeta,
+  Snippet,
+  TranscriptInfo,
+  VideoMeta,
+  VideoSource,
+  YtDlpInfo,
+  YtDlpTrack,
+} from "./types.ts";
+
+const WATCH_URL = "https://www.youtube.com/watch?v=";
+const INNERTUBE_URL = "https://www.youtube.com/youtubei/v1/player";
+const WATCH_PAGE_USER_AGENT =
+  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36";
+const DEFAULT_WEB_CLIENT_VERSION = "2.20260320.08.00";
+const YT_DLP_MAX_BUFFER = 32 * 1024 * 1024;
+
+let cachedYtDlpCommand: { command: string; args: string[]; label: string } | null | undefined;
+
+const INNER_TUBE_CLIENTS: InnerTubeClient[] = [
+  {
+    id: "android",
+    clientName: "ANDROID",
+    clientHeaderName: "3",
+    clientVersion: "20.10.38",
+    userAgent:
+      "com.google.android.youtube/20.10.38 (Linux; U; Android 14; en_US; Pixel 8 Pro; Build/AP1A.240405.002)",
+    extraContext: {
+      clientFormFactor: "SMALL_FORM_FACTOR",
+      androidSdkVersion: 34,
+      osName: "Android",
+      osVersion: "14",
+      platform: "MOBILE",
+    },
+  },
+  {
+    id: "web",
+    clientName: "WEB",
+    clientHeaderName: "1",
+    userAgent: WATCH_PAGE_USER_AGENT,
+  },
+  {
+    id: "ios",
+    clientName: "IOS",
+    clientHeaderName: "5",
+    clientVersion: "20.10.4",
+    userAgent:
+      "com.google.ios.youtube/20.10.4 (iPhone16,2; U; CPU iOS 18_3 like Mac OS X; en_US)",
+    extraContext: {
+      deviceMake: "Apple",
+      deviceModel: "iPhone16,2",
+      osName: "iPhone",
+      osVersion: "18.3.0.22D5054f",
+      platform: "MOBILE",
+    },
+  },
+];
+
+async function fetchHtml(videoId: string): Promise<string> {
+  const watchUrl = `${WATCH_URL}${videoId}&hl=en&persist_hl=1&has_verified=1&bpctr=9999999999`;
+  const baseHeaders = {
+    Accept: "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+    "Accept-Language": "en-US,en;q=0.9",
+    "Cache-Control": "no-cache",
+    Pragma: "no-cache",
+    "User-Agent": WATCH_PAGE_USER_AGENT,
+  };
+  const response = await fetch(watchUrl, { headers: baseHeaders });
+  if (!response.ok) throw new Error(`HTTP ${response.status} fetching video page`);
+  let html = await response.text();
+  if (html.includes('action="https://consent.youtube.com/s"')) {
+    const consentValue = html.match(/name="v" value="(.*?)"/);
+    if (!consentValue) throw new Error("Failed to create consent cookie");
+    const consentResponse = await fetch(watchUrl, {
+      headers: {
+        ...baseHeaders,
+        Cookie: `CONSENT=YES+${consentValue[1]}`,
+      },
+    });
+    if (!consentResponse.ok) throw new Error(`HTTP ${consentResponse.status} fetching video page (consent)`);
+    html = await consentResponse.text();
+  }
+  return html;
+}
+
+function extractSession(html: string, videoId: string): InnerTubeSession {
+  const apiKey = html.match(/"INNERTUBE_API_KEY":\s*"([a-zA-Z0-9_-]+)"/)?.[1];
+  if (!apiKey) {
+    if (html.includes('class="g-recaptcha"')) throw new Error(`IP blocked for ${videoId} (reCAPTCHA)`);
+    throw new Error(`Cannot extract API key for ${videoId}`);
+  }
+  const webClientVersion =
+    html.match(/"INNERTUBE_CLIENT_VERSION":\s*"([^"]+)"/)?.[1] ||
+    html.match(/"clientVersion":"([^"]+)"/)?.[1] ||
+    DEFAULT_WEB_CLIENT_VERSION;
+  const visitorData =
+    html.match(/"VISITOR_DATA":"([^"]+)"/)?.[1] ||
+    html.match(/"visitorData":"([^"]+)"/)?.[1] ||
+    "";
+  return { apiKey, webClientVersion, visitorData };
+}
+
+function buildInnerTubeContext(client: InnerTubeClient, session: InnerTubeSession, videoId: string) {
+  return {
+    context: {
+      client: {
+        hl: "en",
+        gl: "US",
+        utcOffsetMinutes: 0,
+        visitorData: session.visitorData,
+        clientName: client.clientName,
+        clientVersion: client.clientVersion || session.webClientVersion,
+        ...client.extraContext,
+      },
+      request: { useSsl: true },
+    },
+    videoId,
+  };
+}
+
+async function fetchInnertubeData(videoId: string, session: InnerTubeSession, client: InnerTubeClient): Promise<any> {
+  const clientVersion = client.clientVersion || session.webClientVersion;
+  const headers: Record<string, string> = {
+    Accept: "application/json",
+    "Accept-Language": "en-US,en;q=0.9",
+    "Content-Type": "application/json",
+    Origin: "https://www.youtube.com",
+    Referer: `${WATCH_URL}${videoId}`,
+    "User-Agent": client.userAgent,
+    "X-YouTube-Client-Name": client.clientHeaderName || "1",
+    "X-YouTube-Client-Version": clientVersion,
+  };
+  if (session.visitorData) headers["X-Goog-Visitor-Id"] = session.visitorData;
+  const response = await fetch(`${INNERTUBE_URL}?key=${session.apiKey}&prettyPrint=false`, {
+    method: "POST",
+    headers,
+    body: JSON.stringify(buildInnerTubeContext(client, session, videoId)),
+  });
+  if (response.status === 429) throw new Error(`IP blocked for ${videoId} (429)`);
+  if (!response.ok) throw new Error(`HTTP ${response.status} from InnerTube API`);
+  return response.json();
+}
+
+function assertPlayability(data: any, videoId: string) {
+  const playabilityStatus = data?.playabilityStatus;
+  if (!playabilityStatus) return;
+  const status = playabilityStatus.status;
+  if (status === "OK" || !status) return;
+  const reason = playabilityStatus.reason || "";
+  const reasonLower = reason.toLowerCase();
+  if (status === "LOGIN_REQUIRED") {
+    if (reasonLower.includes("bot")) throw makeError(`Request blocked for ${videoId}: bot detected`, "BOT_DETECTED");
+    if (reasonLower.includes("inappropriate")) throw makeError(`Age restricted: ${videoId}`, "AGE_RESTRICTED");
+  }
+  if (status === "ERROR" && reasonLower.includes("unavailable")) {
+    if (videoId.startsWith("http")) throw makeError("Invalid video ID: pass the ID, not the URL", "INVALID_VIDEO_ID");
+    throw makeError(`Video unavailable: ${videoId}`, "VIDEO_UNAVAILABLE");
+  }
+  const subreasons = playabilityStatus.errorScreen?.playerErrorMessageRenderer?.subreason?.runs?.map((run: any) => run.text).join("") || "";
+  throw new Error(`Video unplayable (${videoId}): ${reason} ${subreasons}`.trim());
+}
+
+function extractCaptionsJson(data: any, videoId: string): any {
+  assertPlayability(data, videoId);
+  const captionsJson = data?.captions?.playerCaptionsTracklistRenderer;
+  if (!captionsJson || !captionsJson.captionTracks) throw makeError(`Transcripts disabled for ${videoId}`, "TRANSCRIPTS_DISABLED");
+  return captionsJson;
+}
+
+function buildTranscriptList(captionsJson: any): TranscriptInfo[] {
+  const translationLanguages = (captionsJson.translationLanguages || []).map((language: any) => ({
+    language: language.languageName?.runs?.[0]?.text || language.languageName?.simpleText || "",
+    languageCode: language.languageCode,
+  }));
+  return (captionsJson.captionTracks || []).map((track: any) => ({
+    language: track.name?.runs?.[0]?.text || track.name?.simpleText || "",
+    languageCode: track.languageCode,
+    isGenerated: track.kind === "asr",
+    isTranslatable: !!track.isTranslatable,
+    baseUrl: track.baseUrl || "",
+    translationLanguages: track.isTranslatable ? translationLanguages : [],
+  }));
+}
+
+export async function fetchTranscriptSnippets(
+  info: TranscriptInfo,
+  translateTo?: string
+): Promise<{ snippets: Snippet[]; language: string; languageCode: string }> {
+  let url = info.baseUrl;
+  let language = info.language;
+  let languageCode = info.languageCode;
+  if (translateTo) {
+    if (!info.isTranslatable) throw new Error(`Transcript ${info.languageCode} is not translatable`);
+    const translatedLanguage = info.translationLanguages.find((entry) => entry.languageCode === translateTo);
+    if (!translatedLanguage) throw new Error(`Translation language ${translateTo} not available`);
+    url += `&tlang=${translateTo}`;
+    language = translatedLanguage.language;
+    languageCode = translateTo;
+  }
+  const response = await fetch(url, {
+    headers: {
+      "Accept-Language": "en-US,en;q=0.9",
+      "User-Agent": WATCH_PAGE_USER_AGENT,
+    },
+  });
+  if (!response.ok) throw new Error(`HTTP ${response.status} fetching transcript`);
+  return {
+    snippets: parseTranscriptPayload(await response.text(), url),
+    language,
+    languageCode,
+  };
+}
+
+export function detectYtDlpCommand(): { command: string; args: string[]; label: string } | null {
+  if (cachedYtDlpCommand !== undefined) return cachedYtDlpCommand;
+  const candidates = [
+    { command: "yt-dlp", args: [], label: "yt-dlp" },
+    { command: "uvx", args: ["--from", "yt-dlp", "yt-dlp"], label: "uvx --from yt-dlp yt-dlp" },
+    { command: "python3", args: ["-m", "yt_dlp"], label: "python3 -m yt_dlp" },
+  ];
+  for (const candidate of candidates) {
+    const probe = spawnSync(candidate.command, [...candidate.args, "--version"], {
+      encoding: "utf8",
+      maxBuffer: 1024 * 1024,
+    });
+    if (probe.status !== 0) continue;
+
+    const helpProbe = spawnSync(candidate.command, [...candidate.args, "--help"], {
+      encoding: "utf8",
+      maxBuffer: 2 * 1024 * 1024,
+    });
+    const helpText = `${helpProbe.stdout || ""}\n${helpProbe.stderr || ""}`;
+    const supportsRequiredFlags =
+      helpProbe.status === 0 &&
+      helpText.includes("--js-runtimes") &&
+      helpText.includes("--remote-components");
+
+    if (supportsRequiredFlags) {
+      cachedYtDlpCommand = candidate;
+      return candidate;
+    }
+  }
+  cachedYtDlpCommand = null;
+  return cachedYtDlpCommand;
+}
+
+export function selectYtDlpTrack(entries: YtDlpTrack[]): YtDlpTrack | null {
+  const preferredExts = ["json3", "srv3", "srv2", "srv1", "ttml", "vtt"];
+  for (const ext of preferredExts) {
+    const match = entries.find((entry) => entry.url && entry.ext === ext);
+    if (match) return match;
+  }
+  return entries.find((entry) => !!entry.url) || null;
+}
+
+export function buildTranscriptListFromYtDlp(info: YtDlpInfo): TranscriptInfo[] {
+  const translationLanguages = Object.entries(info.automatic_captions || {}).map(([languageCode, entries]) => ({
+    language: entries.find((entry) => entry.name)?.name || languageCode,
+    languageCode,
+  }));
+  const manual = Object.entries(info.subtitles || {}).flatMap(([languageCode, entries]) => {
+    const selected = selectYtDlpTrack(entries);
+    if (!selected?.url) return [];
+    return [{
+      language: selected.name || languageCode,
+      languageCode,
+      isGenerated: false,
+      isTranslatable: translationLanguages.length > 0,
+      baseUrl: selected.url,
+      translationLanguages,
+    }];
+  });
+  const generated = Object.entries(info.automatic_captions || {}).flatMap(([languageCode, entries]) => {
+    const selected = selectYtDlpTrack(entries);
+    if (!selected?.url) return [];
+    return [{
+      language: selected.name || languageCode,
+      languageCode,
+      isGenerated: true,
+      isTranslatable: translationLanguages.length > 0,
+      baseUrl: selected.url,
+      translationLanguages,
+    }];
+  });
+  return [...manual, ...generated];
+}
+
+function fetchYtDlpInfo(videoId: string): YtDlpInfo {
+  const command = detectYtDlpCommand();
+  if (!command) {
+    throw makeError(
+      `Request blocked for ${videoId}: bot detected. yt-dlp fallback unavailable (install yt-dlp or uv).`,
+      "YT_DLP_UNAVAILABLE"
+    );
+  }
+
+  const args = [
+    ...command.args,
+    "-J",
+    "--skip-download",
+    "--js-runtimes",
+    "bun",
+    "--remote-components",
+    "ejs:github",
+  ];
+  const cookiesFromBrowser = process.env.YOUTUBE_TRANSCRIPT_COOKIES_FROM_BROWSER?.trim();
+  if (cookiesFromBrowser) args.push("--cookies-from-browser", cookiesFromBrowser);
+  args.push(`${WATCH_URL}${videoId}`);
+
+  const result = spawnSync(command.command, args, {
+    encoding: "utf8",
+    maxBuffer: YT_DLP_MAX_BUFFER,
+  });
+  if (result.status !== 0) {
+    const stderr = (result.stderr || "").trim();
+    const stdout = (result.stdout || "").trim();
+    const detail = stderr || stdout || `exit ${result.status ?? "unknown"}`;
+    throw makeError(`yt-dlp fallback failed for ${videoId} (${command.label}): ${detail}`, "YT_DLP_FAILED");
+  }
+  return JSON.parse(result.stdout);
+}
+
+async function fetchInnertubeSource(videoId: string): Promise<VideoSource> {
+  const html = await fetchHtml(videoId);
+  const session = extractSession(html, videoId);
+  const attempts: string[] = [];
+  let lastError: Error | null = null;
+
+  for (const client of INNER_TUBE_CLIENTS) {
+    try {
+      const data = await fetchInnertubeData(videoId, session, client);
+      const captionsJson = extractCaptionsJson(data, videoId);
+      return { kind: "innertube", data, transcripts: buildTranscriptList(captionsJson) };
+    } catch (error) {
+      const normalized = normalizeError(error);
+      attempts.push(`${client.id}: ${normalized.message}`);
+      lastError = normalized;
+      if (!shouldTryAlternateClient(normalized)) break;
+    }
+  }
+
+  if (!lastError) throw makeError(`Unable to fetch transcript metadata for ${videoId}`, "UNKNOWN");
+  if (attempts.length > 1) {
+    throw makeError(`${lastError.message}. Tried clients: ${attempts.join("; ")}`, normalizeError(lastError).code);
+  }
+  throw lastError;
+}
+
+export async function resolveVideoSource(
+  videoId: string,
+  fetchPrimary: (videoId: string) => Promise<VideoSource>,
+  fetchFallback: (videoId: string) => YtDlpInfo,
+  logWarning: (message: string) => void = (message) => console.error(message)
+): Promise<VideoSource> {
+  try {
+    return await fetchPrimary(videoId);
+  } catch (error) {
+    const normalized = normalizeError(error);
+    if (!shouldTryYtDlpFallback(normalized)) throw normalized;
+    logWarning(`Warning (${videoId}): ${normalized.message}. Retrying with yt-dlp fallback.`);
+    const info = fetchFallback(videoId);
+    const transcripts = buildTranscriptListFromYtDlp(info);
+    if (!transcripts.length) throw makeError(`Transcripts disabled for ${videoId}`, "TRANSCRIPTS_DISABLED");
+    return { kind: "yt-dlp", info, transcripts };
+  }
+}
+
+export async function fetchVideoSource(videoId: string): Promise<VideoSource> {
+  return resolveVideoSource(videoId, fetchInnertubeSource, fetchYtDlpInfo);
+}
+
+export function parseChapters(description: string, duration: number = 0): Chapter[] {
+  const raw: { title: string; start: number }[] = [];
+  for (const line of description.split("\n")) {
+    const match = line.trim().match(/^(?:(\d{1,2}):)?(\d{1,2}):(\d{2})\s+(.+)$/);
+    if (match) {
+      const hours = match[1] ? parseInt(match[1]) : 0;
+      raw.push({ title: match[4].trim(), start: hours * 3600 + parseInt(match[2]) * 60 + parseInt(match[3]) });
+    }
+  }
+  if (raw.length < 2) return [];
+  return raw.map((chapter, index) => ({
+    title: chapter.title,
+    start: chapter.start,
+    end: index < raw.length - 1 ? raw[index + 1].start : Math.max(duration, chapter.start),
+  }));
+}
+
+export function getThumbnailUrls(videoId: string, data: any): string[] {
+  const urls = [
+    `https://i.ytimg.com/vi/${videoId}/maxresdefault.jpg`,
+    `https://i.ytimg.com/vi/${videoId}/hqdefault.jpg`,
+  ];
+  const thumbnails = data?.videoDetails?.thumbnail?.thumbnails ||
+    data?.microformat?.playerMicroformatRenderer?.thumbnail?.thumbnails ||
+    [];
+  if (thumbnails.length) {
+    const sorted = [...thumbnails].sort((a: any, b: any) => (b.width || 0) - (a.width || 0));
+    for (const thumbnail of sorted) {
+      if (thumbnail.url && !urls.includes(thumbnail.url)) urls.push(thumbnail.url);
+    }
+  }
+  return urls;
+}
+
+export function getYtDlpThumbnailUrls(videoId: string, info: YtDlpInfo): string[] {
+  const urls = getThumbnailUrls(videoId, null);
+  const thumbnails = Array.isArray(info.thumbnails) ? info.thumbnails : [];
+  const sorted = [...thumbnails].sort((a, b) => (b?.width || 0) - (a?.width || 0));
+  for (const thumbnail of sorted) {
+    if (thumbnail?.url && !urls.includes(thumbnail.url)) urls.push(thumbnail.url);
+  }
+  if (info.thumbnail && !urls.includes(info.thumbnail)) urls.push(info.thumbnail);
+  return urls;
+}
+
+export function buildVideoMeta(data: any, videoId: string, language: LanguageMeta, chapters: Chapter[]): VideoMeta {
+  const videoDetails = data?.videoDetails || {};
+  const microformat = data?.microformat?.playerMicroformatRenderer || {};
+  return {
+    videoId,
+    title: videoDetails.title || microformat.title?.simpleText || "",
+    channel: videoDetails.author || microformat.ownerChannelName || "",
+    channelId: videoDetails.channelId || microformat.externalChannelId || "",
+    description: videoDetails.shortDescription || microformat.description?.simpleText || "",
+    duration: parseInt(videoDetails.lengthSeconds || "0"),
+    publishDate: microformat.publishDate || microformat.uploadDate || "",
+    url: `${WATCH_URL}${videoId}`,
+    coverImage: "",
+    thumbnailUrl: getThumbnailUrls(videoId, data)[0],
+    language,
+    chapters,
+  };
+}
+
+export function buildVideoMetaFromYtDlp(
+  info: YtDlpInfo,
+  videoId: string,
+  language: LanguageMeta,
+  chapters: Chapter[]
+): VideoMeta {
+  return {
+    videoId,
+    title: info.title || "",
+    channel: info.channel || info.uploader || "",
+    channelId: info.channel_id || info.uploader_id || "",
+    description: info.description || "",
+    duration: Number(info.duration || 0),
+    publishDate: normalizePublishDate(info.upload_date),
+    url: info.webpage_url || `${WATCH_URL}${videoId}`,
+    coverImage: "",
+    thumbnailUrl: getYtDlpThumbnailUrls(videoId, info)[0] || "",
+    language,
+    chapters,
+  };
+}
+
+export async function downloadCoverImage(urls: string[], outputPath: string): Promise<boolean> {
+  for (const url of urls) {
+    try {
+      const response = await fetch(url);
+      if (response.ok) {
+        writeFileSync(outputPath, Buffer.from(await response.arrayBuffer()));
+        return true;
+      }
+    } catch {}
+  }
+  return false;
+}