chore: release v1.83.0

- 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

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.81.0"
+    "version": "1.83.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,26 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 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

CHANGELOG.zh.md

@@ -2,6 +2,26 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 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

CLAUDE.md

@@ -1,6 +1,6 @@
 # CLAUDE.md
 
-Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.81.0**.
+Claude Code marketplace plugin providing AI-powered content generation skills. Version: **1.83.0**.
 
 ## Architecture
 

README.md

@@ -663,7 +663,7 @@ AI-powered generation backends.
 
 #### baoyu-image-gen
 
-AI SDK-based image generation using OpenAI, Azure 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)
@@ -684,9 +684,21 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 # OpenRouter
 /baoyu-image-gen --prompt "A cat" --image cat.png --provider openrouter
 
+# OpenRouter with reference images
+/baoyu-image-gen --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
 
+# DashScope with custom size
+/baoyu-image-gen --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-image-gen --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
+
+# MiniMax with subject reference
+/baoyu-image-gen --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
 
@@ -696,8 +708,11 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 # Seedream (豆包)
 /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
 
-# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, or Seedream 5.0/4.5/4.0)
+# With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 5.0/4.5/4.0)
 /baoyu-image-gen --prompt "Make it blue" --image out.png --ref source.png
+
+# Batch mode
+/baoyu-image-gen --batchfile batch.json --jobs 4 --json
 ```
 
 **Options**:
@@ -706,44 +721,73 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `--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
 
@@ -1018,11 +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
@@ -1034,6 +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

@@ -663,7 +663,7 @@ AI 驱动的生成后端。
 
 #### baoyu-image-gen
 
-基于 AI SDK 的图像生成，支持 OpenAI、Azure 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）
@@ -684,9 +684,21 @@ AI 驱动的生成后端。
 # OpenRouter
 /baoyu-image-gen --prompt "一只猫" --image cat.png --provider openrouter
 
+# OpenRouter + 参考图
+/baoyu-image-gen --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
 
+# DashScope 自定义尺寸
+/baoyu-image-gen --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-image-gen --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
+
+# MiniMax + 角色参考图
+/baoyu-image-gen --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
 
@@ -696,8 +708,11 @@ AI 驱动的生成后端。
 # 豆包（Seedream）
 /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
 
-# 带参考图（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate 或 Seedream 5.0/4.5/4.0）
+# 带参考图（Google、OpenAI、Azure OpenAI、OpenRouter、Replicate、MiniMax 或 Seedream 5.0/4.5/4.0）
 /baoyu-image-gen --prompt "把它变成蓝色" --image out.png --ref source.png
+
+# 批量模式
+/baoyu-image-gen --batchfile batch.json --jobs 4 --json
 ```
 
 **选项**：
@@ -706,44 +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
 
@@ -1018,11 +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
@@ -1034,6 +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

skills/baoyu-image-gen/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: baoyu-image-gen
-description: AI image generation with OpenAI, Azure 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
+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-image-gen
@@ -13,7 +13,7 @@ metadata:
 
 # Image Generation (AI SDK)
 
-Official API-based image generation. Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Jimeng (即梦), Seedream (豆包) and Replicate providers.
+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
 
@@ -74,7 +74,7 @@ ${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, or Seedream 4.0/4.5/5.0)
+# 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)
@@ -101,6 +101,15 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9
 # 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
 
@@ -150,13 +159,13 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `--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\|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`) |
+| `--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, and Seedream 5.0/4.5/4.0. Not supported by Jimeng, Seedream 3.0, or removed SeedEdit 3.0 |
+| `--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 |
 
@@ -169,6 +178,7 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `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 |
@@ -179,6 +189,7 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `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) |
@@ -190,6 +201,7 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `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`) |
@@ -263,6 +275,34 @@ Official references:
 - [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-image-gen` 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.:
@@ -297,8 +337,8 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 
 ## 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`)
+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
 
@@ -319,6 +359,7 @@ Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
 - 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
 

skills/baoyu-image-gen/references/config/first-time-setup.md

@@ -53,6 +53,8 @@ options:
     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"
 ```
@@ -103,6 +105,20 @@ options:
     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
@@ -149,6 +165,7 @@ default_model:
   azure: [selected azure deployment or null]
   openrouter: [selected openrouter model or null]
   dashscope: null
+  minimax: [selected minimax model or null]
   replicate: null
 ---
 ```
@@ -252,6 +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:
@@ -267,6 +302,7 @@ default_model:
   azure: [value or null]
   openrouter: [value or null]
   dashscope: [value or null]
+  minimax: [value or null]
   replicate: [value or null]
 ```
 

skills/baoyu-image-gen/references/config/preferences-schema.md

@@ -11,7 +11,7 @@ description: EXTEND.md YAML schema for baoyu-image-gen user preferences
 ---
 version: 1
 
-default_provider: null      # google|openai|azure|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)
 
@@ -25,6 +25,7 @@ default_model:
   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:
@@ -48,6 +49,9 @@ batch:
     dashscope:
       concurrency: 3
       start_interval_ms: 1100
+    minimax:
+      concurrency: 3
+      start_interval_ms: 1100
 ---
 ```
 
@@ -65,6 +69,7 @@ batch:
 | `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 |
@@ -95,6 +100,7 @@ default_model:
   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
@@ -108,5 +114,8 @@ batch:
     openrouter:
       concurrency: 3
       start_interval_ms: 1100
+    minimax:
+      concurrency: 3
+      start_interval_ms: 1100
 ---
 ```

skills/baoyu-image-gen/scripts/main.test.ts

@@ -124,6 +124,7 @@ 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:
@@ -132,6 +133,9 @@ batch:
       start_interval_ms: 900
     openai:
       concurrency: 4
+    minimax:
+      concurrency: 2
+      start_interval_ms: 1400
     azure:
       concurrency: 1
       start_interval_ms: 1500
@@ -147,6 +151,7 @@ batch:
   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,
@@ -155,6 +160,10 @@ 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,
@@ -200,6 +209,7 @@ 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,
@@ -216,6 +226,7 @@ test("detectProvider selects an available ref-capable provider for reference-ima
     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,
@@ -235,6 +246,7 @@ test("detectProvider selects Azure when only Azure credentials are configured",
     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,
@@ -254,6 +266,7 @@ test("detectProvider infers Seedream from model id and allows Seedream reference
     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,
@@ -281,6 +294,26 @@ 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",
@@ -296,6 +329,10 @@ 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,
+        },
       },
     },
   };
@@ -305,6 +342,10 @@ 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) => {

skills/baoyu-image-gen/scripts/main.ts

@@ -58,6 +58,7 @@ 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 },
@@ -75,13 +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|azure  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, Azure, 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
@@ -112,6 +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
@@ -120,6 +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)
@@ -130,6 +133,7 @@ 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
@@ -235,6 +239,7 @@ export function parseArgs(argv: string[]): CliArgs {
         v !== "openai" &&
         v !== "openrouter" &&
         v !== "dashscope" &&
+        v !== "minimax" &&
         v !== "replicate" &&
         v !== "jimeng" &&
         v !== "seedream" &&
@@ -390,6 +395,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           openai: null,
           openrouter: null,
           dashscope: null,
+          minimax: null,
           replicate: null,
           jimeng: null,
           seedream: null,
@@ -417,6 +423,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
+          key === "minimax" ||
           key === "replicate" ||
           key === "jimeng" ||
           key === "seedream" ||
@@ -434,6 +441,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
+          key === "minimax" ||
           key === "replicate" ||
           key === "jimeng" ||
           key === "seedream" ||
@@ -528,12 +536,13 @@ 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", "azure"] 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] = {
@@ -582,7 +591,9 @@ 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;
 }
 
@@ -595,10 +606,11 @@ export function detectProvider(args: CliArgs): Provider {
     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 azure (Azure OpenAI), --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."
     );
   }
 
@@ -609,6 +621,7 @@ export function detectProvider(args: CliArgs): Provider {
   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;
@@ -621,6 +634,13 @@ 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";
@@ -628,8 +648,9 @@ export function detectProvider(args: CliArgs): Provider {
     if (hasOpenrouter) return "openrouter";
     if (hasReplicate) return "replicate";
     if (hasSeedream) return "seedream";
+    if (hasMinimax) return "minimax";
     throw new Error(
-      "Reference images require Google, OpenAI, Azure, OpenRouter, Replicate, or supported Seedream models. Set GOOGLE_API_KEY/GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, 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."
     );
   }
 
@@ -639,6 +660,7 @@ export function detectProvider(args: CliArgs): Provider {
     hasAzure && "azure",
     hasOpenrouter && "openrouter",
     hasDashscope && "dashscope",
+    hasMinimax && "minimax",
     hasReplicate && "replicate",
     hasJimeng && "jimeng",
     hasSeedream && "seedream",
@@ -648,7 +670,7 @@ 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, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, 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."
   );
 }
@@ -687,6 +709,7 @@ 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;
@@ -717,6 +740,7 @@ 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;

skills/baoyu-image-gen/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-image-gen/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-image-gen/scripts/types.ts

@@ -1,4 +1,13 @@
-export type Provider = "google" | "openai" | "openrouter" | "dashscope" | "replicate" | "jimeng" | "seedream" | "azure";
+export type Provider =
+  | "google"
+  | "openai"
+  | "openrouter"
+  | "dashscope"
+  | "minimax"
+  | "replicate"
+  | "jimeng"
+  | "seedream"
+  | "azure";
 export type Quality = "normal" | "2k";
 
 export type CliArgs = {
@@ -52,6 +61,7 @@ export type ExtendConfig = {
     openai: string | null;
     openrouter: string | null;
     dashscope: string | null;
+    minimax: string | null;
     replicate: string | null;
     jimeng: string | null;
     seedream: string | null;

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

@@ -118,6 +118,7 @@ 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
@@ -137,6 +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
 
@@ -158,6 +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 |
 
@@ -165,7 +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**:
@@ -173,6 +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:
@@ -211,8 +258,9 @@ Conversion order:
 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 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
-6. The legacy fallback path uses the older Readability/selector/Next.js-data based HTML-to-Markdown implementation recovered from git history
+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:
 

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

@@ -13,10 +13,15 @@ import {
   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;
@@ -85,7 +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,
+  };
 })()
 `;
 
@@ -102,7 +110,11 @@ 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);
 
@@ -111,14 +123,23 @@ export async function extractContent(html: string, url: string): Promise<Convers
     return specializedResult;
   }
 
-  const defuddleResult = await tryDefuddleConversion(html, url, baseMetadata);
+  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);
 
@@ -130,10 +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),
   };
 }
@@ -610,12 +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 ? 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;
     }
@@ -194,21 +223,28 @@ async function generateOutputPath(url: string, title: string, outputDir?: string
   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;
@@ -235,8 +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([
@@ -251,11 +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) {
@@ -272,10 +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);
   }
 
@@ -286,6 +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()) {
@@ -296,6 +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;
@@ -306,7 +411,7 @@ async function main(): Promise<void> {
   try {
     const result = await captureUrl(args);
     document = createMarkdownDocument(result);
-    outputPath = args.output || await generateOutputPath(args.url, result.metadata.title, args.outputDir, document);
+    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 });

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",