chore: release v1.59.1

refactor(scripts): replace clawhub CLI with local sync-clawhub.mjs
refactor(baoyu-post-to-weibo): add entry point guard to md-to-html.ts
2026-07-12 13:59:47 +08:00 · 2026-03-11 17:08:33 -05:00 · 2026-03-11 16:45:57 -05:00 · 2026-03-11 16:45:56 -05:00 · 2026-03-11 16:45:55 -05:00 · 2026-03-11 16:45:51 -05:00
51 changed files with 2198 additions and 388 deletions
@@ -6,7 +6,7 @@
  },
  "metadata": {
    "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.56.1"
+    "version": "1.59.1"
  },
  "plugins": [
    {
@@ -161,3 +161,6 @@ posts/
 *.ipr

 .claude/skills/baoyu-skill-evolution
+# ClawHub local state (current and legacy directory names from the official CLI)
+.clawhub/
+.clawdhub/
@@ -2,6 +2,56 @@

 English | [中文](./CHANGELOG.zh.md)

+## 1.59.1 - 2026-03-11
+
+### Fixes
+- `baoyu-translate`: improve short text annotation density rule and add explicit style preset passing to 02-prompt.md
+- `baoyu-post-to-x`: remove `--disable-blink-features=AutomationControlled` Chrome flag
+
+### Refactor
+- `baoyu-post-to-weibo`: add entry point guard to md-to-html.ts for module import compatibility
+- Replace clawhub CLI with local sync-clawhub.mjs script
+
+### Documentation
+- Update CLAUDE.md to reflect v1.59.0 codebase state (by @jackL1020)
+
+## 1.59.0 - 2026-03-09
+
+### Features
+- `baoyu-image-gen`: add batch parallel image generation and provider-level throttling (by @SeamoonAO)
+
+### Fixes
+- `baoyu-image-gen`: restore Google as default provider when multiple keys available
+
+### Documentation
+- Improve skill documentation clarity (by @SeamoonAO)
+
+## 1.58.0 - 2026-03-08
+
+### Features
+- Add XDG config path support for EXTEND.md (by @liby)
+
+### Fixes
+- `baoyu-post-to-wechat`: surface agent-browser startup errors
+- `baoyu-post-to-wechat`: harden agent-browser command and eval handling (by @luojiyin1987)
+- `baoyu-image-gen`: use execFileSync for google curl requests (by @luojiyin1987)
+- `baoyu-format-markdown`: use spawnSync for autocorrect command (by @luojiyin1987)
+
+### Documentation
+- Fix CLAUDE dependency statement (by @luojiyin1987)
+- Add markdown-to-html to README utility skills (by @luojiyin1987)
+
+## 1.57.0 - 2026-03-08
+
+### Features
+- Add ClawHub/OpenClaw publishing support with sync script and README documentation
+
+### Refactor
+- Add openclaw metadata to all skill frontmatter for ClawHub registry compatibility
+- Rename `SKILL_DIR` to `baseDir` across all skills for consistency
+- `baoyu-danger-gemini-web`, `baoyu-danger-x-to-markdown`: dynamic script path in usage display
+- `baoyu-comic`, `baoyu-xhs-images`: use skill interface instead of direct script invocation for image generation
+
 ## 1.56.1 - 2026-03-08

 ### Fixes
@@ -2,6 +2,56 @@

 [English](./CHANGELOG.md) | 中文

+## 1.59.1 - 2026-03-11
+
+### 修复
+- `baoyu-translate`：改进短文本注释密度规则，补充风格预设到 02-prompt.md 的显式传递
+- `baoyu-post-to-x`：移除 `--disable-blink-features=AutomationControlled` Chrome 启动参数
+
+### 重构
+- `baoyu-post-to-weibo`：为 md-to-html.ts 添加入口守卫，支持模块导入
+- 使用本地 sync-clawhub.mjs 脚本替代 clawhub CLI
+
+### 文档
+- 更新 CLAUDE.md 以反映 v1.59.0 代码库状态 (by @jackL1020)
+
+## 1.59.0 - 2026-03-09
+
+### 新功能
+- `baoyu-image-gen`：新增批量并行图片生成和提供商级别限流 (by @SeamoonAO)
+
+### 修复
+- `baoyu-image-gen`：修复多个 API key 可用时恢复 Google 为默认提供商
+
+### 文档
+- 改进技能文档清晰度 (by @SeamoonAO)
+
+## 1.58.0 - 2026-03-08
+
+### 新功能
+- 新增 EXTEND.md 的 XDG 配置路径支持 (by @liby)
+
+### 修复
+- `baoyu-post-to-wechat`：暴露 agent-browser 启动错误信息
+- `baoyu-post-to-wechat`：加固 agent-browser 命令和 eval 处理 (by @luojiyin1987)
+- `baoyu-image-gen`：使用 execFileSync 替代 shell 执行 Google curl 请求 (by @luojiyin1987)
+- `baoyu-format-markdown`：使用 spawnSync 替代 shell 执行 autocorrect 命令 (by @luojiyin1987)
+
+### 文档
+- 修正 CLAUDE 依赖说明 (by @luojiyin1987)
+- 将 markdown-to-html 添加到 README 工具技能列表 (by @luojiyin1987)
+
+## 1.57.0 - 2026-03-08
+
+### 新功能
+- 新增 ClawHub/OpenClaw 发布支持，包含同步脚本和 README 文档
+
+### 重构
+- 为所有 skill 前言添加 openclaw 元数据，兼容 ClawHub 注册表
+- 全部 skill 中将 `SKILL_DIR` 统一重命名为 `baseDir`
+- `baoyu-danger-gemini-web`、`baoyu-danger-x-to-markdown`：使用动态脚本路径显示用法
+- `baoyu-comic`、`baoyu-xhs-images`：通过 skill 接口调用图片生成，不再直接调用脚本
+
 ## 1.56.1 - 2026-03-08

 ### 修复
@@ -4,11 +4,11 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co

 ## Project Overview

-Claude Code marketplace plugin providing AI-powered content generation skills. Skills use Gemini Web API (reverse-engineered) for text/image generation and Chrome CDP for browser automation.
+Claude Code marketplace plugin providing AI-powered content generation skills. Current version: **1.59.1**. Skills use official AI APIs (OpenAI, Google, DashScope, Replicate) or the reverse-engineered Gemini Web API for text/image generation, and Chrome CDP for browser automation.

 ## Architecture

-Skills are organized into three plugin categories in `marketplace.json`:
+Skills are organized into three plugin categories in `.claude-plugin/marketplace.json`:

 ```
 skills/
@@ -19,16 +19,27 @@ skills/
 │   ├── baoyu-article-illustrator/ # Smart illustration placement
 │   ├── baoyu-comic/               # Knowledge comics (Logicomix/Ohmsha style)
 │   ├── baoyu-post-to-x/           # X/Twitter posting automation
-│   └── baoyu-post-to-wechat/      # WeChat Official Account posting
+│   ├── baoyu-post-to-wechat/      # WeChat Official Account posting
+│   ├── baoyu-post-to-weibo/       # Weibo posting (text, images, videos, articles)
+│   └── baoyu-infographic/         # Professional infographics (21 layouts × 20 styles)
 │
 ├── [ai-generation-skills]     # AI-powered generation backends
-│   └── baoyu-danger-gemini-web/   # Gemini API wrapper (text + image gen)
+│   ├── baoyu-danger-gemini-web/   # Gemini Web API wrapper (text + image gen)
+│   └── baoyu-image-gen/           # Official API image gen (OpenAI, Google, DashScope, Replicate)
 │
 └── [utility-skills]           # Utility tools for content processing
    ├── baoyu-danger-x-to-markdown/ # X/Twitter content to markdown
-    └── baoyu-compress-image/      # Image compression
+    ├── baoyu-compress-image/       # Image compression (WebP/PNG via sips/cwebp/Sharp)
+    ├── baoyu-url-to-markdown/      # Fetch any URL → markdown via Chrome CDP
+    ├── baoyu-format-markdown/      # Format/beautify plain text or markdown files
+    ├── baoyu-markdown-to-html/     # Markdown → styled HTML (WeChat-compatible themes)
+    └── baoyu-translate/            # Multi-mode translation (quick/normal/refined)
 ```

+Top-level `scripts/` directory contains repository maintenance utilities:
+- `scripts/sync-clawhub.sh` - Publish skills to ClawHub/OpenClaw registry
+- `scripts/sync-md-to-wechat.sh` - Sync markdown content to WeChat
+
 **Plugin Categories**:
 | Category | Description |
 |----------|-------------|
@@ -37,9 +48,10 @@ skills/
 | `utility-skills` | Helper tools for content processing (conversion, compression) |

 Each skill contains:
- `SKILL.md` - YAML front matter (name, description) + documentation
- `scripts/` - TypeScript implementations
- `prompts/system.md` - AI generation guidelines (optional)
+- `SKILL.md` - YAML front matter (name, description, version, openclaw metadata) + documentation
+- `scripts/` - TypeScript implementations (optional, pure-prompt skills omit this)
+- `references/` - Extended reference files linked from SKILL.md (optional)
+- `prompts/` - AI prompt templates (optional, used by some content skills)

 ## Running Skills

@@ -88,8 +100,9 @@ ${BUN_X} skills/baoyu-danger-gemini-web/scripts/main.ts --promptfiles system.md
 ## Key Dependencies

 - **Bun**: TypeScript runtime (native `bun` preferred, fallback `npx -y bun`)
- **Chrome**: Required for `baoyu-danger-gemini-web` auth and `baoyu-post-to-x` automation
- **No npm packages**: Self-contained TypeScript, no external dependencies
+- **Chrome**: Required for `baoyu-danger-gemini-web` auth, `baoyu-post-to-x`, `baoyu-post-to-wechat`, `baoyu-post-to-weibo`, and `baoyu-url-to-markdown`
+- **npm packages (per skill)**: Some skill subprojects include `package.json`/lockfiles and require dependency installation in their own `scripts/` directories
+- **Image generation APIs**: `baoyu-image-gen` requires at least one API key (OpenAI, Google, DashScope, or Replicate)

 ## Chrome Profile (Unified)

@@ -166,10 +179,40 @@ Skills that process external Markdown/HTML should treat content as untrusted:
 - Cookies cached in data directory
 - Force refresh: `--login` flag

+`baoyu-image-gen` uses official API keys configured in EXTEND.md (loaded at Step 0 before generation).
+
 ## Plugin Configuration

 `.claude-plugin/marketplace.json` defines plugin metadata and skill paths. Version follows semver.

+The file contains:
+- `name`: Plugin name (`baoyu-skills`)
+- `owner`: Author info
+- `metadata.version`: Semver version (currently `1.59.1`)
+- `plugins[]`: Array of plugin categories, each with `name`, `description`, `source`, `strict`, and `skills[]` paths
+
+## ClawHub / OpenClaw Publishing
+
+Skills include `metadata.openclaw` in their YAML front matter for registry compatibility:
+
+```yaml
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#<skill-name>
+    requires:          # optional — only for skills with scripts
+      anyBins:
+        - bun
+        - npx
+```
+
+To publish/sync skills to ClawHub registry:
+```bash
+bash scripts/sync-clawhub.sh           # sync all skills
+bash scripts/sync-clawhub.sh <skill>   # sync one skill
+```
+
+Requires `clawhub` CLI or `npx` (auto-downloads via npx if not installed).
+
 ## Skill Loading Rules

 **IMPORTANT**: When working in this project, follow these rules:
@@ -212,29 +255,50 @@ Skills that process external Markdown/HTML should treat content as untrusted:
 | **References** | Keep one level deep from SKILL.md; avoid nested references |
 | **No time-sensitive info** | Avoid dates/versions that become outdated |

+### SKILL.md Frontmatter Template
+
+```yaml
+---
+name: baoyu-<name>
+description: <Third-person description. What it does + when to use it.>
+version: <semver matching marketplace.json>
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-<name>
+    requires:          # include only if skill has scripts
+      anyBins:
+        - bun
+        - npx
+---
+```
+
 ### Steps

-1. Create `skills/baoyu-<name>/SKILL.md` with YAML front matter
+1. Create `skills/baoyu-<name>/SKILL.md` with YAML front matter (see template above)
   - Directory name: `baoyu-<name>`
   - SKILL.md `name` field: `baoyu-<name>`
-2. Add TypeScript in `skills/baoyu-<name>/scripts/`
+   - Always include `metadata.openclaw.homepage`
+   - Include `metadata.openclaw.requires.anyBins` only when the skill has executable scripts
+2. Add TypeScript in `skills/baoyu-<name>/scripts/` (if applicable)
 3. Add prompt templates in `skills/baoyu-<name>/prompts/` if needed
 4. **Choose the appropriate category** and register in `marketplace.json`:
   - `content-skills`: For content generation/publishing (images, slides, posts)
   - `ai-generation-skills`: For AI backend capabilities
   - `utility-skills`: For helper tools (conversion, compression)
   - If none fit, create a new category with descriptive name
-5. **Add Script Directory section** to SKILL.md (see template below)
+5. **Add Script Directory section** to SKILL.md (see template below) if skill has scripts
+6. **Add openclaw metadata** to SKILL.md frontmatter (required for ClawHub registry)

 ### Choosing a Category

 | If your skill... | Use category |
 |------------------|--------------|
-| Generates visual content (images, slides, comics) | `content-skills` |
-| Publishes to platforms (X, WeChat, etc.) | `content-skills` |
-| Provides AI generation backend | `ai-generation-skills` |
-| Converts or processes content | `utility-skills` |
+| Generates visual content (images, slides, comics, infographics) | `content-skills` |
+| Publishes to platforms (X, WeChat, Weibo, etc.) | `content-skills` |
+| Provides AI generation backend (official API or reverse-engineered) | `ai-generation-skills` |
+| Converts or processes content (URL→md, md→html, format) | `utility-skills` |
 | Compresses or optimizes files | `utility-skills` |
+| Translates documents | `utility-skills` |

 **Creating a new category**: If the skill doesn't fit existing categories, add a new plugin object to `marketplace.json` with:
 - `name`: Descriptive kebab-case name (e.g., `analytics-skills`)
@@ -266,10 +330,10 @@ Every SKILL.md with scripts MUST include this section after Usage:
 **Important**: All scripts are located in the `scripts/` subdirectory of this skill.

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
 3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
-4. Replace all `${SKILL_DIR}` and `${BUN_X}` in this document with actual values
+4. Replace all `{baseDir}` and `${BUN_X}` in this document with actual values

 **Script Reference**:
 | Script | Purpose |
@@ -278,7 +342,9 @@ Every SKILL.md with scripts MUST include this section after Usage:
 | `scripts/other.ts` | Other functionality |
 ```

-When referencing scripts in workflow sections, use `${BUN_X} ${SKILL_DIR}/scripts/<name>.ts` so agents can resolve the correct runtime and path.
+When referencing scripts in workflow sections, use `${BUN_X} {baseDir}/scripts/<name>.ts` so agents can resolve the correct runtime and path.
+
+> **Note**: The path variable was renamed from `SKILL_DIR` / `${SKILL_DIR}` to `baseDir` / `{baseDir}` (no `${}` wrapper) in v1.57.0. All existing SKILL.md files use `{baseDir}`.

 ### Progressive Disclosure

@@ -327,7 +393,7 @@ Use this template when implementing image generation in skills:
 ### Step N: Generate Images

 **Skill Selection**:
-1. Check available image generation skills (e.g., `baoyu-danger-gemini-web`)
+1. Check available image generation skills (`baoyu-image-gen` default, or `baoyu-danger-gemini-web`)
 2. Read selected skill's SKILL.md for parameter reference
 3. If multiple skills available, ask user to choose

@@ -336,11 +402,14 @@ Use this template when implementing image generation in skills:
   - Prompt file path (or inline prompt)
   - Output image path
   - Any skill-specific parameters (refer to skill's SKILL.md)
-2. Generate images sequentially (one at a time)
+2. Generate images sequentially by default (one at a time)
+   - Use batch parallel mode only when user already has multiple prompts or explicitly wants parallel throughput
 3. After each image, output progress: "Generated X/N"
 4. On failure, auto-retry once before reporting error
 ```

+**Batch Parallel Generation** (`baoyu-image-gen` only): supports concurrent workers with per-provider throttling. Configure via `batch.max_workers` and `batch.provider_limits` in EXTEND.md. Default: sequential.
+
 ### Output Path Convention

 Each session creates an independent directory. Even the same source file generates a new directory per session.
@@ -472,22 +541,27 @@ Check EXTEND.md existence (priority order):
 \`\`\`bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/<skill-name>/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/<skill-name>/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/<skill-name>/EXTEND.md" && echo "user"
 \`\`\`

 \`\`\`powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/<skill-name>/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/<skill-name>/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/<skill-name>/EXTEND.md") { "user" }
 \`\`\`

-┌────────────────────────────────────────────┬───────────────────┐
-│                    Path                    │     Location      │
-├────────────────────────────────────────────┼───────────────────┤
-│ .baoyu-skills/<skill-name>/EXTEND.md       │ Project directory │
-├────────────────────────────────────────────┼───────────────────┤
-│ $HOME/.baoyu-skills/<skill-name>/EXTEND.md │ User home         │
-└────────────────────────────────────────────┴───────────────────┘
+┌────────────────────────────────────────────────────────┬──────────────────────────┐
+│                          Path                          │         Location         │
+├────────────────────────────────────────────────────────┼──────────────────────────┤
+│ .baoyu-skills/<skill-name>/EXTEND.md                   │ Project directory        │
+├────────────────────────────────────────────────────────┼──────────────────────────┤
+│ $XDG_CONFIG_HOME/baoyu-skills/<skill-name>/EXTEND.md   │ XDG config (~/.config)   │
+├────────────────────────────────────────────────────────┼──────────────────────────┤
+│ $HOME/.baoyu-skills/<skill-name>/EXTEND.md             │ User home (legacy)       │
+└────────────────────────────────────────────────────────┴──────────────────────────┘

 ┌───────────┬───────────────────────────────────────────────────────────────────────────┐
 │  Result   │                                  Action                                   │
@@ -523,5 +597,6 @@ Custom configurations via EXTEND.md. See **Preferences** section for paths and s
 **Notes**:
 - Replace `<skill-name>` with actual skill name (e.g., `baoyu-cover-image`)
 - Use `$HOME` instead of `~` for cross-platform compatibility (macOS/Linux/WSL/PowerShell)
+- `$XDG_CONFIG_HOME` defaults to `~/.config` when unset
 - Use `test -f` (Bash) or `Test-Path` (PowerShell) for explicit file existence check
 - ASCII tables for clear visual formatting
@@ -17,6 +17,27 @@ Skills shared by Baoyu for improving daily work efficiency with Claude Code.
 npx skills add jimliu/baoyu-skills
 ```

+### Publish to ClawHub / OpenClaw
+
+This repository now supports publishing each `skills/baoyu-*` directory as an individual ClawHub skill.
+
+```bash
+# Preview what would be published
+./scripts/sync-clawhub.sh --dry-run
+
+# Publish all changed skills from ./skills
+./scripts/sync-clawhub.sh --all
+```
+
+ClawHub installs skills individually, not as one marketplace bundle. After publishing, users can install specific skills such as:
+
+```bash
+clawhub install baoyu-image-gen
+clawhub install baoyu-markdown-to-html
+```
+
+Publishing to ClawHub releases the published skill under `MIT-0`, per ClawHub's registry rules.
+
 ### Register as Plugin Marketplace

 Run the following command in Claude Code:
@@ -55,7 +76,7 @@ Simply tell Claude Code:
 |--------|-------------|--------|
 | **content-skills** | Content generation and publishing | [xhs-images](#baoyu-xhs-images), [infographic](#baoyu-infographic), [cover-image](#baoyu-cover-image), [slide-deck](#baoyu-slide-deck), [comic](#baoyu-comic), [article-illustrator](#baoyu-article-illustrator), [post-to-x](#baoyu-post-to-x), [post-to-wechat](#baoyu-post-to-wechat), [post-to-weibo](#baoyu-post-to-weibo) |
 | **ai-generation-skills** | AI-powered generation backends | [image-gen](#baoyu-image-gen), [danger-gemini-web](#baoyu-danger-gemini-web) |
-| **utility-skills** | Utility tools for content processing | [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [translate](#baoyu-translate) |
+| **utility-skills** | Utility tools for content processing | [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [markdown-to-html](#baoyu-markdown-to-html), [translate](#baoyu-translate) |

 ## Update Skills

@@ -777,6 +798,21 @@ Format plain text or markdown files with proper frontmatter, titles, summaries,
 | Code/commands | `` `inline` `` or ` ```block``` ` |
 | Quotes | `>` blockquote |

+#### baoyu-markdown-to-html
+
+Convert markdown files into styled HTML with WeChat-compatible themes, syntax highlighting, and optional bottom citations for external links.
+
+```bash
+# Basic conversion
+/baoyu-markdown-to-html article.md
+
+# Theme + color
+/baoyu-markdown-to-html article.md --theme grace --color red
+
+# Convert ordinary external links to bottom citations
+/baoyu-markdown-to-html article.md --cite
+```
+
 #### baoyu-translate

 Translate articles and documents between languages with three modes: quick (direct), normal (analysis-informed), and refined (full publication-quality workflow with review and polish).
@@ -17,6 +17,27 @@
 npx skills add jimliu/baoyu-skills
 ```

+### 发布到 ClawHub / OpenClaw
+
+现在这个仓库支持把每个 `skills/baoyu-*` 目录作为独立 ClawHub skill 发布。
+
+```bash
+# 预览将要发布的变更
+./scripts/sync-clawhub.sh --dry-run
+
+# 发布 ./skills 下所有已变更的 skill
+./scripts/sync-clawhub.sh --all
+```
+
+ClawHub 按“单个 skill”安装，不是把整个 marketplace 一次性装进去。发布后，用户可以按需安装：
+
+```bash
+clawhub install baoyu-image-gen
+clawhub install baoyu-markdown-to-html
+```
+
+根据 ClawHub 的 registry 规则，发布到 ClawHub 的 skill 会以 `MIT-0` 许可分发。
+
 ### 注册插件市场

 在 Claude Code 中运行：
@@ -55,7 +76,7 @@ npx skills add jimliu/baoyu-skills
 |------|------|----------|
 | **content-skills** | 内容生成和发布 | [xhs-images](#baoyu-xhs-images), [infographic](#baoyu-infographic), [cover-image](#baoyu-cover-image), [slide-deck](#baoyu-slide-deck), [comic](#baoyu-comic), [article-illustrator](#baoyu-article-illustrator), [post-to-x](#baoyu-post-to-x), [post-to-wechat](#baoyu-post-to-wechat), [post-to-weibo](#baoyu-post-to-weibo) |
 | **ai-generation-skills** | AI 生成后端 | [image-gen](#baoyu-image-gen), [danger-gemini-web](#baoyu-danger-gemini-web) |
-| **utility-skills** | 内容处理工具 | [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [translate](#baoyu-translate) |
+| **utility-skills** | 内容处理工具 | [url-to-markdown](#baoyu-url-to-markdown), [danger-x-to-markdown](#baoyu-danger-x-to-markdown), [compress-image](#baoyu-compress-image), [format-markdown](#baoyu-format-markdown), [markdown-to-html](#baoyu-markdown-to-html), [translate](#baoyu-translate) |

 ## 更新技能

@@ -777,6 +798,21 @@ AI 驱动的生成后端。
 | 代码/命令 | `` `行内` `` 或 ` ```代码块``` ` |
 | 引用 | `>` 引用块 |

+#### baoyu-markdown-to-html
+
+将 Markdown 文件转换为样式化 HTML，支持微信公众号兼容主题、代码高亮，以及可选的外链底部引用。
+
+```bash
+# 基础转换
+/baoyu-markdown-to-html article.md
+
+# 主题 + 颜色
+/baoyu-markdown-to-html article.md --theme grace --color red
+
+# 将普通外链转换为文末引用
+/baoyu-markdown-to-html article.md --cite
+```
+
 #### baoyu-translate

 三模式翻译技能：快速（直接翻译）、标准（分析后翻译）、精翻（完整出版级工作流，含审校与润色）。
@@ -0,0 +1,528 @@
+#!/usr/bin/env node
+
+import crypto from "node:crypto";
+import fs from "node:fs/promises";
+import { existsSync } from "node:fs";
+import path from "node:path";
+import os from "node:os";
+
+const DEFAULT_REGISTRY = "https://clawhub.ai";
+const TEXT_EXTENSIONS = new Set([
+  "md",
+  "mdx",
+  "txt",
+  "json",
+  "json5",
+  "yaml",
+  "yml",
+  "toml",
+  "js",
+  "cjs",
+  "mjs",
+  "ts",
+  "tsx",
+  "jsx",
+  "py",
+  "sh",
+  "rb",
+  "go",
+  "rs",
+  "swift",
+  "kt",
+  "java",
+  "cs",
+  "cpp",
+  "c",
+  "h",
+  "hpp",
+  "sql",
+  "csv",
+  "ini",
+  "cfg",
+  "env",
+  "xml",
+  "html",
+  "css",
+  "scss",
+  "sass",
+  "svg",
+]);
+
+async function main() {
+  const options = parseArgs(process.argv.slice(2));
+  const config = await readClawhubConfig();
+  const registry = (
+    process.env.CLAWHUB_REGISTRY ||
+    process.env.CLAWDHUB_REGISTRY ||
+    config.registry ||
+    DEFAULT_REGISTRY
+  ).replace(/\/+$/, "");
+
+  if (!config.token) {
+    throw new Error("Not logged in. Run: clawhub login");
+  }
+
+  await apiJson(registry, config.token, "/api/v1/whoami");
+
+  const roots = options.roots.length > 0 ? options.roots : [path.resolve("skills")];
+  const skills = await findSkills(roots);
+
+  if (skills.length === 0) {
+    throw new Error("No skills found.");
+  }
+
+  console.log("ClawHub sync");
+  console.log(`Roots with skills: ${roots.join(", ")}`);
+
+  const locals = await mapWithConcurrency(skills, options.concurrency, async (skill) => {
+    const files = await listTextFiles(skill.folder);
+    const fingerprint = buildFingerprint(files);
+    return {
+      ...skill,
+      fileCount: files.length,
+      fingerprint,
+    };
+  });
+
+  const candidates = await mapWithConcurrency(locals, options.concurrency, async (skill) => {
+    const query = new URLSearchParams({
+      slug: skill.slug,
+      hash: skill.fingerprint,
+    });
+    const { status, body } = await apiJsonWithStatus(
+      registry,
+      config.token,
+      `/api/v1/resolve?${query.toString()}`
+    );
+
+    if (status === 404) {
+      return {
+        ...skill,
+        status: "new",
+        latestVersion: null,
+        matchVersion: null,
+      };
+    }
+
+    if (status !== 200) {
+      throw new Error(body?.message || `Resolve failed for ${skill.slug} (HTTP ${status})`);
+    }
+
+    const latestVersion = body?.latestVersion?.version ?? null;
+    const matchVersion = body?.match?.version ?? null;
+
+    if (!latestVersion) {
+      return {
+        ...skill,
+        status: "new",
+        latestVersion: null,
+        matchVersion: null,
+      };
+    }
+
+    return {
+      ...skill,
+      status: matchVersion ? "synced" : "update",
+      latestVersion,
+      matchVersion,
+    };
+  });
+
+  const actionable = candidates.filter((candidate) => candidate.status !== "synced");
+  if (actionable.length === 0) {
+    console.log("Nothing to sync.");
+    return;
+  }
+
+  console.log("");
+  console.log("To sync");
+  for (const candidate of actionable) {
+    console.log(`- ${formatCandidate(candidate, options.bump)}`);
+  }
+
+  if (options.dryRun) {
+    console.log("");
+    console.log(`Dry run: would upload ${actionable.length} skill(s).`);
+    return;
+  }
+
+  const tags = options.tags
+    .split(",")
+    .map((tag) => tag.trim())
+    .filter(Boolean);
+
+  for (const candidate of actionable) {
+    const version =
+      candidate.status === "new"
+        ? "1.0.0"
+        : bumpSemver(candidate.latestVersion, options.bump);
+
+    console.log(`Publishing ${candidate.slug}@${version}`);
+    const files = await listTextFiles(candidate.folder);
+    await publishSkill({
+      registry,
+      token: config.token,
+      skill: candidate,
+      files,
+      version,
+      changelog: options.changelog,
+      tags,
+    });
+  }
+
+  console.log("");
+  console.log(`Uploaded ${actionable.length} skill(s).`);
+}
+
+function parseArgs(argv) {
+  const options = {
+    roots: [],
+    dryRun: false,
+    bump: "patch",
+    changelog: "",
+    tags: "latest",
+    concurrency: 4,
+  };
+
+  for (let index = 0; index < argv.length; index += 1) {
+    const arg = argv[index];
+    if (arg === "--dry-run") {
+      options.dryRun = true;
+      continue;
+    }
+    if (arg === "--all") {
+      continue;
+    }
+    if (arg === "--root") {
+      const value = argv[index + 1];
+      if (!value) throw new Error("--root requires a directory");
+      options.roots.push(path.resolve(value));
+      index += 1;
+      continue;
+    }
+    if (arg === "--bump") {
+      const value = argv[index + 1];
+      if (!["patch", "minor", "major"].includes(value)) {
+        throw new Error("--bump must be patch, minor, or major");
+      }
+      options.bump = value;
+      index += 1;
+      continue;
+    }
+    if (arg === "--changelog") {
+      const value = argv[index + 1];
+      if (value == null) throw new Error("--changelog requires text");
+      options.changelog = value;
+      index += 1;
+      continue;
+    }
+    if (arg === "--tags") {
+      const value = argv[index + 1];
+      if (value == null) throw new Error("--tags requires a value");
+      options.tags = value;
+      index += 1;
+      continue;
+    }
+    if (arg === "--concurrency") {
+      const value = Number(argv[index + 1]);
+      if (!Number.isInteger(value) || value < 1 || value > 32) {
+        throw new Error("--concurrency must be an integer between 1 and 32");
+      }
+      options.concurrency = value;
+      index += 1;
+      continue;
+    }
+    if (arg === "-h" || arg === "--help") {
+      printUsage();
+      process.exit(0);
+    }
+    throw new Error(`Unknown argument: ${arg}`);
+  }
+
+  return options;
+}
+
+function printUsage() {
+  console.log(`Usage: sync-clawhub.mjs [options]
+
+Options:
+  --root <dir>         Extra skill root (repeatable)
+  --all                Accepted for compatibility
+  --dry-run            Show what would be uploaded
+  --bump <type>        patch | minor | major
+  --changelog <text>   Changelog for updates
+  --tags <tags>        Comma-separated tags
+  --concurrency <n>    Registry check concurrency (1-32)
+  -h, --help           Show help`);
+}
+
+async function readClawhubConfig() {
+  const configPath = getConfigPath();
+  try {
+    return JSON.parse(await fs.readFile(configPath, "utf8"));
+  } catch {
+    return {};
+  }
+}
+
+function getConfigPath() {
+  const override =
+    process.env.CLAWHUB_CONFIG_PATH?.trim() || process.env.CLAWDHUB_CONFIG_PATH?.trim();
+  if (override) {
+    return path.resolve(override);
+  }
+
+  const home = os.homedir();
+  if (process.platform === "darwin") {
+    const clawhub = path.join(home, "Library", "Application Support", "clawhub", "config.json");
+    const clawdhub = path.join(home, "Library", "Application Support", "clawdhub", "config.json");
+    return pathForExistingConfig(clawhub, clawdhub);
+  }
+
+  const xdg = process.env.XDG_CONFIG_HOME;
+  if (xdg) {
+    const clawhub = path.join(xdg, "clawhub", "config.json");
+    const clawdhub = path.join(xdg, "clawdhub", "config.json");
+    return pathForExistingConfig(clawhub, clawdhub);
+  }
+
+  if (process.platform === "win32" && process.env.APPDATA) {
+    const clawhub = path.join(process.env.APPDATA, "clawhub", "config.json");
+    const clawdhub = path.join(process.env.APPDATA, "clawdhub", "config.json");
+    return pathForExistingConfig(clawhub, clawdhub);
+  }
+
+  const clawhub = path.join(home, ".config", "clawhub", "config.json");
+  const clawdhub = path.join(home, ".config", "clawdhub", "config.json");
+  return pathForExistingConfig(clawhub, clawdhub);
+}
+
+function pathForExistingConfig(primary, legacy) {
+  if (existsSync(primary)) return path.resolve(primary);
+  if (existsSync(legacy)) return path.resolve(legacy);
+  return path.resolve(primary);
+}
+
+async function findSkills(roots) {
+  const deduped = new Map();
+  for (const root of roots) {
+    const folders = await findSkillFolders(root);
+    for (const folder of folders) {
+      deduped.set(folder.slug, folder);
+    }
+  }
+  return [...deduped.values()].sort((left, right) => left.slug.localeCompare(right.slug));
+}
+
+async function findSkillFolders(root) {
+  const stat = await safeStat(root);
+  if (!stat?.isDirectory()) return [];
+
+  if (await hasSkillMarker(root)) {
+    return [buildSkillEntry(root)];
+  }
+
+  const entries = await fs.readdir(root, { withFileTypes: true });
+  const found = [];
+  for (const entry of entries) {
+    if (!entry.isDirectory()) continue;
+    const folder = path.join(root, entry.name);
+    if (await hasSkillMarker(folder)) {
+      found.push(buildSkillEntry(folder));
+    }
+  }
+  return found;
+}
+
+function buildSkillEntry(folder) {
+  const base = path.basename(folder);
+  return {
+    folder,
+    slug: sanitizeSlug(base),
+    displayName: titleCase(base),
+  };
+}
+
+async function hasSkillMarker(folder) {
+  return Boolean(
+    (await safeStat(path.join(folder, "SKILL.md")))?.isFile() ||
+      (await safeStat(path.join(folder, "skill.md")))?.isFile()
+  );
+}
+
+async function listTextFiles(root) {
+  const files = [];
+
+  async function walk(folder) {
+    const entries = await fs.readdir(folder, { withFileTypes: true });
+    for (const entry of entries) {
+      if (entry.name.startsWith(".")) continue;
+      if (entry.name === "node_modules") continue;
+      if (entry.name === ".clawhub" || entry.name === ".clawdhub") continue;
+
+      const fullPath = path.join(folder, entry.name);
+      if (entry.isDirectory()) {
+        await walk(fullPath);
+        continue;
+      }
+      if (!entry.isFile()) continue;
+
+      const relPath = path.relative(root, fullPath).split(path.sep).join("/");
+      const ext = relPath.split(".").pop()?.toLowerCase() ?? "";
+      if (!TEXT_EXTENSIONS.has(ext)) continue;
+
+      const bytes = await fs.readFile(fullPath);
+      files.push({ relPath, bytes });
+    }
+  }
+
+  await walk(root);
+  files.sort((left, right) => left.relPath.localeCompare(right.relPath));
+  return files;
+}
+
+function buildFingerprint(files) {
+  const payload = files
+    .map((file) => `${file.relPath}:${sha256(file.bytes)}`)
+    .sort((left, right) => left.localeCompare(right))
+    .join("\n");
+  return crypto.createHash("sha256").update(payload).digest("hex");
+}
+
+function sha256(bytes) {
+  return crypto.createHash("sha256").update(bytes).digest("hex");
+}
+
+async function publishSkill({ registry, token, skill, files, version, changelog, tags }) {
+  const form = new FormData();
+  form.set(
+    "payload",
+    JSON.stringify({
+      slug: skill.slug,
+      displayName: skill.displayName,
+      version,
+      changelog,
+      tags,
+      acceptLicenseTerms: true,
+    })
+  );
+
+  for (const file of files) {
+    form.append("files", new Blob([file.bytes], { type: "text/plain" }), file.relPath);
+  }
+
+  const response = await fetch(`${registry}/api/v1/skills`, {
+    method: "POST",
+    headers: {
+      Accept: "application/json",
+      Authorization: `Bearer ${token}`,
+    },
+    body: form,
+  });
+
+  const text = await response.text();
+  if (!response.ok) {
+    throw new Error(text || `Publish failed for ${skill.slug} (HTTP ${response.status})`);
+  }
+
+  const result = text ? JSON.parse(text) : {};
+  console.log(`OK. Published ${skill.slug}@${version}${result.versionId ? ` (${result.versionId})` : ""}`);
+}
+
+async function apiJson(registry, token, requestPath) {
+  const { status, body } = await apiJsonWithStatus(registry, token, requestPath);
+  if (status < 200 || status >= 300) {
+    throw new Error(body?.message || `HTTP ${status}`);
+  }
+  return body;
+}
+
+async function apiJsonWithStatus(registry, token, requestPath) {
+  const response = await fetch(`${registry}${requestPath}`, {
+    headers: {
+      Accept: "application/json",
+      Authorization: `Bearer ${token}`,
+    },
+  });
+
+  const text = await response.text();
+  let body = null;
+  try {
+    body = text ? JSON.parse(text) : null;
+  } catch {
+    body = { message: text };
+  }
+  return { status: response.status, body };
+}
+
+async function mapWithConcurrency(items, limit, fn) {
+  const results = new Array(items.length);
+  let cursor = 0;
+
+  async function worker() {
+    while (cursor < items.length) {
+      const index = cursor;
+      cursor += 1;
+      results[index] = await fn(items[index], index);
+    }
+  }
+
+  const count = Math.min(Math.max(limit, 1), Math.max(items.length, 1));
+  await Promise.all(Array.from({ length: count }, () => worker()));
+  return results;
+}
+
+function formatCandidate(candidate, bump) {
+  if (candidate.status === "new") {
+    return `${candidate.slug}  NEW  (${candidate.fileCount} files)`;
+  }
+  return `${candidate.slug}  UPDATE ${candidate.latestVersion} -> ${bumpSemver(
+    candidate.latestVersion,
+    bump
+  )}  (${candidate.fileCount} files)`;
+}
+
+function bumpSemver(version, bump) {
+  const match = /^(\d+)\.(\d+)\.(\d+)$/.exec(version ?? "");
+  if (!match) {
+    throw new Error(`Invalid semver: ${version}`);
+  }
+  const major = Number(match[1]);
+  const minor = Number(match[2]);
+  const patch = Number(match[3]);
+
+  if (bump === "major") return `${major + 1}.0.0`;
+  if (bump === "minor") return `${major}.${minor + 1}.0`;
+  return `${major}.${minor}.${patch + 1}`;
+}
+
+function sanitizeSlug(value) {
+  return value
+    .trim()
+    .toLowerCase()
+    .replace(/[^a-z0-9-]+/g, "-")
+    .replace(/^-+/, "")
+    .replace(/-+$/, "")
+    .replace(/--+/g, "-");
+}
+
+function titleCase(value) {
+  return value
+    .trim()
+    .replace(/[-_]+/g, " ")
+    .replace(/\s+/g, " ")
+    .replace(/\b\w/g, (char) => char.toUpperCase());
+}
+
+async function safeStat(filePath) {
+  try {
+    return await fs.stat(filePath);
+  } catch {
+    return null;
+  }
+}
+
+main().catch((error) => {
+  console.error(error instanceof Error ? error.message : String(error));
+  process.exit(1);
+});
@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+SKILLS_DIR="${ROOT_DIR}/skills"
+
+if ! command -v node >/dev/null 2>&1; then
+  echo "Error: node is required."
+  exit 1
+fi
+
+if [ "$#" -eq 0 ]; then
+  set -- --all
+fi
+
+exec node "${ROOT_DIR}/scripts/sync-clawhub.mjs" --root "${SKILLS_DIR}" "$@"
@@ -1,6 +1,10 @@
 ---
 name: baoyu-article-illustrator
 description: Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-article-illustrator
 ---

 # Article Illustrator
@@ -51,12 +55,15 @@ See [references/styles.md](references/styles.md) for Core Styles, full gallery,
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-article-illustrator/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-article-illustrator/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-article-illustrator/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-article-illustrator/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-article-illustrator/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-article-illustrator/EXTEND.md") { "user" }
 ```

@@ -111,6 +118,8 @@ Full template: [references/workflow.md](references/workflow.md#step-4-generate-o

 ⛔ **BLOCKING: Prompt files MUST be saved before ANY image generation.**

+**Execution strategy**: When multiple illustrations have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` → `--batchfile`) over spawning subagents. Use subagents only when each image still needs separate prompt iteration or creative exploration.
+
 1. For each illustration, create a prompt file per [references/prompt-construction.md](references/prompt-construction.md)
 2. Save to `prompts/NN-{type}-{slug}.md` with YAML frontmatter
 3. Prompts **MUST** use type-specific templates with structured sections (ZONES / LABELS / COLORS / STYLE / ASPECT)
@@ -88,12 +88,15 @@ Check preferences and existing state, then ask ALL needed questions in ONE AskUs
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-article-illustrator/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-article-illustrator/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-article-illustrator/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-article-illustrator/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-article-illustrator/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-article-illustrator/EXTEND.md") { "user" }
 ```

@@ -312,6 +315,10 @@ Prompt Files:

 **DO NOT** pass ad-hoc inline text to `--prompt` without first saving prompt files. The generation command should either use `--promptfiles prompts/NN-{type}-{slug}.md` or read the saved file content for `--prompt`.

+**Execution choice**:
+- If multiple illustrations already have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` -> `main.ts --batchfile`)
+- Use subagents only when each illustration still needs separate prompt rewriting, style exploration, or other per-image reasoning before generation
+
 **CRITICAL - References in Frontmatter**:
 - Only add `references` field if files ACTUALLY EXIST in `references/` directory
 - If style/palette was extracted verbally (no file), append info to prompt BODY instead
@@ -0,0 +1,156 @@
+import path from "node:path";
+import process from "node:process";
+import { readdir, readFile, writeFile } from "node:fs/promises";
+
+type CliArgs = {
+  outlinePath: string | null;
+  promptsDir: string | null;
+  outputPath: string | null;
+  imagesDir: string | null;
+  provider: string;
+  model: string;
+  aspectRatio: string;
+  quality: string;
+  jobs: number | null;
+  help: boolean;
+};
+
+type OutlineEntry = {
+  index: number;
+  filename: string;
+};
+
+function printUsage(): void {
+  console.log(`Usage:
+  npx -y tsx scripts/build-batch.ts --outline outline.md --prompts prompts --output batch.json --images-dir attachments
+
+Options:
+  --outline <path>     Path to outline.md
+  --prompts <path>     Path to prompts directory
+  --output <path>      Path to output batch.json
+  --images-dir <path>  Directory for generated images
+  --provider <name>    Provider for baoyu-image-gen batch tasks (default: replicate)
+  --model <id>         Model for baoyu-image-gen batch tasks (default: google/nano-banana-pro)
+  --ar <ratio>         Aspect ratio for all tasks (default: 16:9)
+  --quality <level>    Quality for all tasks (default: 2k)
+  --jobs <count>       Recommended worker count metadata (optional)
+  -h, --help           Show help`);
+}
+
+function parseArgs(argv: string[]): CliArgs {
+  const args: CliArgs = {
+    outlinePath: null,
+    promptsDir: null,
+    outputPath: null,
+    imagesDir: null,
+    provider: "replicate",
+    model: "google/nano-banana-pro",
+    aspectRatio: "16:9",
+    quality: "2k",
+    jobs: null,
+    help: false,
+  };
+
+  for (let i = 0; i < argv.length; i++) {
+    const current = argv[i]!;
+    if (current === "--outline") args.outlinePath = argv[++i] ?? null;
+    else if (current === "--prompts") args.promptsDir = argv[++i] ?? null;
+    else if (current === "--output") args.outputPath = argv[++i] ?? null;
+    else if (current === "--images-dir") args.imagesDir = argv[++i] ?? null;
+    else if (current === "--provider") args.provider = argv[++i] ?? args.provider;
+    else if (current === "--model") args.model = argv[++i] ?? args.model;
+    else if (current === "--ar") args.aspectRatio = argv[++i] ?? args.aspectRatio;
+    else if (current === "--quality") args.quality = argv[++i] ?? args.quality;
+    else if (current === "--jobs") {
+      const value = argv[++i];
+      args.jobs = value ? parseInt(value, 10) : null;
+    } else if (current === "--help" || current === "-h") {
+      args.help = true;
+    }
+  }
+  return args;
+}
+
+function parseOutline(content: string): OutlineEntry[] {
+  const entries: OutlineEntry[] = [];
+  const blocks = content.split(/^## Illustration\s+/m).slice(1);
+
+  for (const block of blocks) {
+    const indexMatch = block.match(/^(\d+)/);
+    const filenameMatch = block.match(/\*\*Filename\*\*:\s*(.+)/);
+    if (indexMatch && filenameMatch) {
+      entries.push({
+        index: parseInt(indexMatch[1]!, 10),
+        filename: filenameMatch[1]!.trim(),
+      });
+    }
+  }
+  return entries;
+}
+
+async function findPromptFile(promptsDir: string, entry: OutlineEntry): Promise<string | null> {
+  const files = await readdir(promptsDir);
+  const prefix = String(entry.index).padStart(2, "0");
+  const match = files.find((f) => f.startsWith(prefix) && f.endsWith(".md"));
+  return match ? path.join(promptsDir, match) : null;
+}
+
+async function main(): Promise<void> {
+  const args = parseArgs(process.argv.slice(2));
+  if (args.help) {
+    printUsage();
+    return;
+  }
+
+  if (!args.outlinePath) {
+    console.error("Error: --outline is required");
+    process.exit(1);
+  }
+  if (!args.promptsDir) {
+    console.error("Error: --prompts is required");
+    process.exit(1);
+  }
+  if (!args.outputPath) {
+    console.error("Error: --output is required");
+    process.exit(1);
+  }
+
+  const outlineContent = await readFile(args.outlinePath, "utf8");
+  const entries = parseOutline(outlineContent);
+
+  if (entries.length === 0) {
+    console.error("No illustration entries found in outline.");
+    process.exit(1);
+  }
+
+  const tasks = [];
+  for (const entry of entries) {
+    const promptFile = await findPromptFile(args.promptsDir, entry);
+    if (!promptFile) {
+      console.error(`Warning: No prompt file found for illustration ${entry.index}, skipping.`);
+      continue;
+    }
+
+    const imageDir = args.imagesDir ?? path.dirname(args.outputPath);
+    tasks.push({
+      id: `illustration-${String(entry.index).padStart(2, "0")}`,
+      promptFiles: [promptFile],
+      image: path.join(imageDir, entry.filename),
+      provider: args.provider,
+      model: args.model,
+      ar: args.aspectRatio,
+      quality: args.quality,
+    });
+  }
+
+  const output: Record<string, unknown> = { tasks };
+  if (args.jobs) output.jobs = args.jobs;
+
+  await writeFile(args.outputPath, JSON.stringify(output, null, 2) + "\n");
+  console.log(`Batch file written: ${args.outputPath} (${tasks.length} tasks)`);
+}
+
+main().catch((error) => {
+  console.error(error instanceof Error ? error.message : String(error));
+  process.exit(1);
+});
@@ -1,6 +1,14 @@
 ---
 name: baoyu-comic
 description: Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-comic
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Knowledge Comic Creator
@@ -104,9 +112,9 @@ Details: [references/auto-selection.md](references/auto-selection.md)
 **Important**: All scripts are located in the `scripts/` subdirectory of this skill.

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
-3. Replace all `${SKILL_DIR}` in this document with the actual path
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
+3. Replace all `{baseDir}` in this document with the actual path
 4. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun

 **Script Reference**:
@@ -208,12 +216,11 @@ Analyze → [Check Existing?] → [Confirm: Style + Reviews] → Storyboard →

 **7.1 Generate character sheet first**:
 - **Backup rule**: If `characters/characters.png` exists, rename to `characters/characters-backup-YYYYMMDD-HHMMSS.png`
-```bash
-# Use Reference Sheet Prompt from characters/characters.md
-${BUN_X} ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
-  --promptfiles characters/characters.md \
-  --image characters/characters.png --ar 4:3
-```
+- Invoke an installed image generation skill such as `baoyu-image-gen`
+- Read that skill's `SKILL.md` and follow its documented interface rather than calling its scripts directly
+- Use `characters/characters.md` as the prompt-file input
+- Save output to `characters/characters.png`
+- Use aspect ratio `4:3`

 **Compress character sheet** (recommended):
 Compress to reduce token usage when used as reference image:
@@ -231,14 +238,11 @@ Compress to reduce token usage when used as reference image:
 **Backup rules for page generation**:
 - If prompt file exists: rename to `prompts/NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.md`
 - If image file exists: rename to `NN-{cover|page}-[slug]-backup-YYYYMMDD-HHMMSS.png`
-
-```bash
-# Example: ALWAYS include --ref for consistency
-${BUN_X} ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
-  --promptfiles prompts/01-page-xxx.md \
-  --image 01-page-xxx.png --ar 3:4 \
-  --ref characters/characters.png
-```
+- Invoke the installed image generation skill for each page
+- Use `prompts/01-page-xxx.md` as the prompt-file input
+- Save output to `01-page-xxx.png`
+- Use aspect ratio `3:4`
+- If the chosen skill supports reference images, pass `characters/characters.png` as `--ref`

 **Full workflow details**: [references/workflow.md](references/workflow.md)

@@ -39,12 +39,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-comic/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-comic/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-comic/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-comic/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-comic/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-comic/EXTEND.md") { "user" }
 ```

@@ -433,14 +436,12 @@ With confirmed prompts from Step 5/6:

 **Strategy A: Using `--ref` parameter** (e.g., baoyu-image-gen)

-```bash
-# Each page generation MUST include --ref
-${BUN_X} ${SKILL_DIR}/../baoyu-image-gen/scripts/main.ts \
-  --promptfiles prompts/01-page-xxx.md \
-  --image 01-page-xxx.png \
-  --ar 3:4 \
-  --ref characters/characters.png
-```
+- Read the chosen image generation skill's `SKILL.md`
+- Invoke that installed skill via its documented interface, not by calling its scripts directly
+- For every page, use `prompts/01-page-xxx.md` as the prompt-file input
+- Save output to `01-page-xxx.png`
+- Use aspect ratio `3:4`
+- Pass `characters/characters.png` as `--ref` on every page generation

 **Strategy B: Embedding character descriptions in prompt**

@@ -478,7 +479,7 @@ If image generation skill supports `--sessionId`:
 After all images generated:

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/merge-to-pdf.ts <comic-dir>
+${BUN_X} {baseDir}/scripts/merge-to-pdf.ts <comic-dir>
 ```

 Creates `{topic-slug}.pdf` with all pages as full-page images.
@@ -1,6 +1,14 @@
 ---
 name: baoyu-compress-image
 description: Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-compress-image
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Image Compressor
@@ -9,7 +17,7 @@ Compresses images using best available tool (sips → cwebp → ImageMagick →

 ## Script Directory

-Scripts in `scripts/` subdirectory. `${SKILL_DIR}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `${SKILL_DIR}` and `${BUN_X}` with actual values.
+Scripts in `scripts/` subdirectory. `{baseDir}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `{baseDir}` and `${BUN_X}` with actual values.

 | Script | Purpose |
 |--------|---------|
@@ -22,12 +30,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-compress-image/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-compress-image/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-compress-image/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-compress-image/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-compress-image/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-compress-image/EXTEND.md") { "user" }
 ```

@@ -52,7 +63,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-compress-image/EXTEND.md") { "user" }
 ## Usage

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <input> [options]
+${BUN_X} {baseDir}/scripts/main.ts <input> [options]
 ```

 ## Options
@@ -71,16 +82,16 @@ ${BUN_X} ${SKILL_DIR}/scripts/main.ts <input> [options]

 ```bash
 # Single file → WebP (replaces original)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts image.png
+${BUN_X} {baseDir}/scripts/main.ts image.png

 # Keep PNG format
-${BUN_X} ${SKILL_DIR}/scripts/main.ts image.png -f png --keep
+${BUN_X} {baseDir}/scripts/main.ts image.png -f png --keep

 # Directory recursive
-${BUN_X} ${SKILL_DIR}/scripts/main.ts ./images/ -r -q 75
+${BUN_X} {baseDir}/scripts/main.ts ./images/ -r -q 75

 # JSON output
-${BUN_X} ${SKILL_DIR}/scripts/main.ts image.png --json
+${BUN_X} {baseDir}/scripts/main.ts image.png --json
 ```

 **Output**:
@@ -1,6 +1,10 @@
 ---
 name: baoyu-cover-image
 description: Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 10 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-cover-image
 ---

 # Cover Image Generator
@@ -130,12 +134,15 @@ Check EXTEND.md existence (priority: project → user):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-cover-image/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-cover-image/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-cover-image/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md") { "user" }
 ```

@@ -1,6 +1,14 @@
 ---
 name: baoyu-danger-gemini-web
 description: Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-danger-gemini-web
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Gemini Web Client
@@ -12,10 +20,10 @@ Text/image generation via Gemini Web API. Supports reference images and multi-tu
 **Important**: All scripts are located in the `scripts/` subdirectory of this skill.

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
 3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
-4. Replace all `${SKILL_DIR}` and `${BUN_X}` in this document with actual values
+4. Replace all `{baseDir}` and `${BUN_X}` in this document with actual values

 **Script Reference**:
 | Script | Purpose |
@@ -49,12 +57,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-danger-gemini-web/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-danger-gemini-web/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md") { "user" }
 ```

@@ -80,23 +91,23 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md") { "user"

 ```bash
 # Text generation
-${BUN_X} ${SKILL_DIR}/scripts/main.ts "Your prompt"
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "Your prompt" --model gemini-3-flash
+${BUN_X} {baseDir}/scripts/main.ts "Your prompt"
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Your prompt" --model gemini-3-flash

 # Image generation
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cute cat" --image cat.png
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --promptfiles system.md content.md --image out.png
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cute cat" --image cat.png
+${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png

 # Vision input (reference images)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "Describe this" --reference image.png
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "Create variation" --reference a.png --image out.png
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Describe this" --reference image.png
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Create variation" --reference a.png --image out.png

 # Multi-turn conversation
-${BUN_X} ${SKILL_DIR}/scripts/main.ts "Remember: 42" --sessionId session-abc
-${BUN_X} ${SKILL_DIR}/scripts/main.ts "What number?" --sessionId session-abc
+${BUN_X} {baseDir}/scripts/main.ts "Remember: 42" --sessionId session-abc
+${BUN_X} {baseDir}/scripts/main.ts "What number?" --sessionId session-abc

 # JSON output
-${BUN_X} ${SKILL_DIR}/scripts/main.ts "Hello" --json
+${BUN_X} {baseDir}/scripts/main.ts "Hello" --json
 ```

 ## Options
@@ -59,16 +59,31 @@ function normalizeSessionMetadata(input: unknown): Array<string | null> {
  return [null, null, null];
 }

+function formatScriptCommand(fallback: string): string {
+  const raw = process.argv[1];
+  const displayPath = raw
+    ? (() => {
+        const relative = path.relative(process.cwd(), raw);
+        return relative && !relative.startsWith("..") ? relative : raw;
+      })()
+    : fallback;
+  const quotedPath = displayPath.includes(" ")
+    ? `"${displayPath.replace(/"/g, '\\"')}"`
+    : displayPath;
+  return `npx -y bun ${quotedPath}`;
+}
+
 function printUsage(cookiePath: string, profileDir: string): void {
+  const cmd = formatScriptCommand("scripts/main.ts");
  console.log(`Usage:
-  npx -y bun skills/baoyu-danger-gemini-web/scripts/main.ts --prompt "Hello"
-  npx -y bun skills/baoyu-danger-gemini-web/scripts/main.ts "Hello"
-  npx -y bun skills/baoyu-danger-gemini-web/scripts/main.ts --prompt "A cute cat" --image generated.png
-  npx -y bun skills/baoyu-danger-gemini-web/scripts/main.ts --promptfiles system.md content.md --image out.png
+  ${cmd} --prompt "Hello"
+  ${cmd} "Hello"
+  ${cmd} --prompt "A cute cat" --image generated.png
+  ${cmd} --promptfiles system.md content.md --image out.png

 Multi-turn conversation (agent generates unique sessionId):
-  npx -y bun skills/baoyu-danger-gemini-web/scripts/main.ts "Remember 42" --sessionId abc123
-  npx -y bun skills/baoyu-danger-gemini-web/scripts/main.ts "What number?" --sessionId abc123
+  ${cmd} "Remember 42" --sessionId abc123
+  ${cmd} "What number?" --sessionId abc123

 Options:
  -p, --prompt <text>       Prompt text
@@ -1,6 +1,14 @@
 ---
 name: baoyu-danger-x-to-markdown
 description: Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-danger-x-to-markdown
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # X to Markdown
@@ -14,8 +22,8 @@ Converts X content to markdown:
 Scripts located in `scripts/` subdirectory.

 **Path Resolution**:
-1. `SKILL_DIR` = this SKILL.md's directory
-2. Script path = `${SKILL_DIR}/scripts/main.ts`
+1. `{baseDir}` = this SKILL.md's directory
+2. Script path = `{baseDir}/scripts/main.ts`
 3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun

 ## Consent Requirement
@@ -75,12 +83,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-danger-x-to-markdown/EXTEND.md") { "user" }
 ```

@@ -140,10 +151,10 @@ Full reference: [references/config/first-time-setup.md](references/config/first-
 ## Usage

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url>
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> -o output.md
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> --download-media
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> --json
+${BUN_X} {baseDir}/scripts/main.ts <url>
+${BUN_X} {baseDir}/scripts/main.ts <url> -o output.md
+${BUN_X} {baseDir}/scripts/main.ts <url> --download-media
+${BUN_X} {baseDir}/scripts/main.ts <url> --json
 ```

 ## Options
@@ -30,8 +30,22 @@ type ConsentRecord = {

 const DISCLAIMER_VERSION = "1.0";

+function formatScriptCommand(fallback: string): string {
+  const raw = process.argv[1];
+  const displayPath = raw
+    ? (() => {
+        const relative = path.relative(process.cwd(), raw);
+        return relative && !relative.startsWith("..") ? relative : raw;
+      })()
+    : fallback;
+  const quotedPath = displayPath.includes(" ")
+    ? `"${displayPath.replace(/"/g, '\\"')}"`
+    : displayPath;
+  return `npx -y bun ${quotedPath}`;
+}
+
 function printUsage(exitCode: number): never {
-  const cmd = "npx -y bun skills/baoyu-danger-x-to-markdown/scripts/main.ts";
+  const cmd = formatScriptCommand("scripts/main.ts");
  console.log(`X (Twitter) to Markdown

 Usage:
@@ -36,6 +36,20 @@ function normalizeInputUrl(input: string): string {
  }
 }

+function formatScriptCommand(fallback: string): string {
+  const raw = process.argv[1];
+  const displayPath = raw
+    ? (() => {
+        const relative = path.relative(process.cwd(), raw);
+        return relative && !relative.startsWith("..") ? relative : raw;
+      })()
+    : fallback;
+  const quotedPath = displayPath.includes(" ")
+    ? `"${displayPath.replace(/"/g, '\\"')}"`
+    : displayPath;
+  return `npx -y bun ${quotedPath}`;
+}
+
 function parseTweetId(input: string): string | null {
  const trimmed = input.trim();
  if (!trimmed) return null;
@@ -179,7 +193,7 @@ async function main() {
  const { url } = parseArgs();
  if (!url) {
    console.error("Usage:");
-    console.error("  npx -y bun skills/baoyu-danger-x-to-markdown/scripts/tweet-to-markdown.ts <tweet url>");
+    console.error(`  ${formatScriptCommand("scripts/tweet-to-markdown.ts")} <tweet url>`);
    process.exit(1);
  }

@@ -1,6 +1,14 @@
 ---
 name: baoyu-format-markdown
 description: Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-format-markdown
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Markdown Formatter
@@ -11,7 +19,7 @@ Transforms plain text or markdown into well-structured, reader-friendly markdown

 ## Script Directory

-Scripts in `scripts/` subdirectory. `${SKILL_DIR}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `${SKILL_DIR}` and `${BUN_X}` with actual values.
+Scripts in `scripts/` subdirectory. `{baseDir}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `{baseDir}` and `${BUN_X}` with actual values.

 | Script | Purpose |
 |--------|---------|
@@ -26,12 +34,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-format-markdown/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-format-markdown/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-format-markdown/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-format-markdown/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-format-markdown/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-format-markdown/EXTEND.md") { "user" }
 ```

@@ -296,7 +307,7 @@ fi
 Run the formatting script on the output file:

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/main.ts {output-file-path} [options]
+${BUN_X} {baseDir}/scripts/main.ts {output-file-path} [options]
 ```

 **Script Options:**
@@ -314,13 +325,13 @@ ${BUN_X} ${SKILL_DIR}/scripts/main.ts {output-file-path} [options]

 ```bash
 # Default: spacing + emphasis enabled, quotes disabled
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md
+${BUN_X} {baseDir}/scripts/main.ts article.md

 # Enable all features including quote replacement
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --quotes
+${BUN_X} {baseDir}/scripts/main.ts article.md --quotes

 # Only fix emphasis issues, skip spacing
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --no-spacing
+${BUN_X} {baseDir}/scripts/main.ts article.md --no-spacing
 ```

 **Script performs (based on options):**
@@ -1,10 +1,10 @@
-import { execSync } from "child_process";
+import { spawnSync } from "node:child_process";
+import process from "node:process";

 export function applyAutocorrect(filePath: string): boolean {
-  try {
-    execSync(`npx autocorrect-node --fix "${filePath}"`, { stdio: "inherit" });
-    return true;
-  } catch {
-    return false;
-  }
+  const npxCmd = process.platform === "win32" ? "npx.cmd" : "npx";
+  const result = spawnSync(npxCmd, ["autocorrect-node", "--fix", filePath], {
+    stdio: "inherit",
+  });
+  return result.status === 0;
 }
@@ -1,6 +1,14 @@
 ---
 name: baoyu-image-gen
-description: AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.
+description: AI image generation with OpenAI, Google, DashScope 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: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-image-gen
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Image Generation (AI SDK)
@@ -10,8 +18,8 @@ Official API-based image generation. Supports OpenAI, Google, DashScope (阿里
 ## Script Directory

 **Agent Execution**:
-1. `SKILL_DIR` = this SKILL.md file's directory
-2. Script path = `${SKILL_DIR}/scripts/main.ts`
+1. `{baseDir}` = this SKILL.md file's directory
+2. Script path = `{baseDir}/scripts/main.ts`
 3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun

 ## Step 0: Load Preferences ⛔ BLOCKING
@@ -23,12 +31,15 @@ Check EXTEND.md existence (priority: project → user):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-image-gen/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-image-gen/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-image-gen/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md") { "user" }
 ```

@@ -44,7 +55,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md") { "user" }
 | `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Project directory |
 | `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | User home |

-**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models
+**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits

 Schema: `references/config/preferences-schema.md`

@@ -52,50 +63,85 @@ Schema: `references/config/preferences-schema.md`

 ```bash
 # Basic
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image cat.png
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image cat.png

 # With aspect ratio
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9

 # High quality
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --quality 2k

 # From prompt files
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --promptfiles system.md content.md --image out.png
+${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png

 # With reference images (Google multimodal or OpenAI edits)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png

 # With reference images (explicit provider/model)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png
+${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --provider google --model gemini-3-pro-image-preview --ref source.png

 # Specific provider
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider openai
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider openai

 # DashScope (阿里通义万象)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope
+${BUN_X} {baseDir}/scripts/main.ts --prompt "一只可爱的猫" --image out.png --provider dashscope

 # Replicate (google/nano-banana-pro)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate

 # Replicate with specific model
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+
+# Batch mode with saved prompt files
+${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
+
+# Batch mode with explicit worker count
+${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
 ```

+### Batch File Format
+
+```json
+{
+  "jobs": 4,
+  "tasks": [
+    {
+      "id": "hero",
+      "promptFiles": ["prompts/hero.md"],
+      "image": "out/hero.png",
+      "provider": "replicate",
+      "model": "google/nano-banana-pro",
+      "ar": "16:9",
+      "quality": "2k"
+    },
+    {
+      "id": "diagram",
+      "promptFiles": ["prompts/diagram.md"],
+      "image": "out/diagram.png",
+      "ref": ["references/original.png"]
+    }
+  ]
+}
+```
+
+Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch file's directory. `jobs` is optional (overridden by CLI `--jobs`). Top-level array format (without `jobs` wrapper) is also accepted.
+
 ## Options

 | Option | Description |
 |--------|-------------|
 | `--prompt <text>`, `-p` | Prompt text |
 | `--promptfiles <files...>` | Read prompt from files (concatenated) |
-| `--image <path>` | Output image path (required) |
-| `--provider google\|openai\|dashscope\|replicate` | Force provider (default: google) |
-| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; OpenAI: `gpt-image-1.5`) |
+| `--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\|dashscope\|replicate` | Force provider (default: auto-detect) |
+| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; OpenAI: `gpt-image-1.5`, `gpt-image-1`) |
 | `--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) |
+| `--quality normal\|2k` | Quality preset (default: `2k`) |
 | `--imageSize 1K\|2K\|4K` | Image size for Google (default: from quality) |
-| `--ref <files...>` | Reference images. Supported by Google multimodal (`gemini-3-pro-image-preview`, `gemini-3-flash-preview`, `gemini-3.1-flash-image-preview`) and OpenAI edits (GPT Image models). If provider omitted: Google first, then OpenAI |
+| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, and Replicate |
 | `--n <count>` | Number of images |
 | `--json` | JSON output |

@@ -115,6 +161,9 @@ ${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provide
 | `GOOGLE_BASE_URL` | Custom Google endpoint |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint |
+| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |

 **Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`

@@ -144,10 +193,10 @@ Examples:

 ```bash
 # Use Replicate default model
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate

 # Override model explicitly
-${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
 ```

 ## Provider Selection
@@ -159,10 +208,10 @@ ${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provide

 ## Quality Presets

-| Preset | Google imageSize | OpenAI Size | Use Case |
-|--------|------------------|-------------|----------|
-| `normal` | 1K | 1024px | Quick previews |
-| `2k` (default) | 2K | 2048px | Covers, illustrations, infographics |
+| Preset | Google imageSize | OpenAI Size | Replicate resolution | Use Case |
+|--------|------------------|-------------|----------------------|----------|
+| `normal` | 1K | 1024px | 1K | Quick previews |
+| `2k` (default) | 2K | 2048px | 2K | Covers, illustrations, infographics |

 **Google imageSize**: Can be overridden with `--imageSize 1K|2K|4K`

@@ -171,41 +220,48 @@ ${BUN_X} ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provide
 Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`

 - Google multimodal: uses `imageConfig.aspectRatio`
- Google Imagen: uses `aspectRatio` parameter
 - OpenAI: maps to closest supported size
+- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`

 ## Generation Mode

-**Default**: Sequential generation (one image at a time). This ensures stable output and easier debugging.
+**Default**: Sequential generation.

-**Parallel Generation**: Only use when user explicitly requests parallel/concurrent generation.
+**Batch Parallel Generation**: When `--batchfile` contains 2 or more pending tasks, the script automatically enables parallel generation.

 | Mode | When to Use |
 |------|-------------|
 | Sequential (default) | Normal usage, single images, small batches |
-| Parallel | User explicitly requests, large batches (10+) |
+| Parallel batch | Batch mode with 2+ tasks |

-**Parallel Settings** (when requested):
+Execution choice:

-| Setting | Value |
-|---------|-------|
-| Recommended concurrency | 4 subagents |
-| Max concurrency | 8 subagents |
-| Use case | Large batch generation when user requests parallel |
+| Situation | Preferred approach | Why |
+|-----------|--------------------|-----|
+| One image, or 1-2 simple images | Sequential | Lower coordination overhead and easier debugging |
+| Multiple images already have saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, and gives predictable throughput |
+| Each image still needs separate reasoning, prompt writing, or style exploration | Subagents | The work is still exploratory, so each image may need independent analysis before generation |
+| Output comes from `baoyu-article-illustrator` with `outline.md` + `prompts/` | Batch (`build-batch.ts` -> `--batchfile`) | That workflow already produces prompt files, so direct batch execution is the intended path |

-**Agent Implementation** (parallel mode only):
-```
-# Launch multiple generations in parallel using Task tool
-# Each Task runs as background subagent with run_in_background=true
-# Collect results via TaskOutput when all complete
-```
+Rule of thumb:
+
+- Prefer batch over subagents once prompt files are already saved and the task is "generate all of these"
+- Use subagents only when generation is coupled with per-image thinking, rewriting, or divergent creative exploration
+
+Parallel behavior:
+
+- Default worker count is automatic, capped by config, built-in default 10
+- Provider-specific throttling is applied only in batch mode, and the built-in defaults are tuned for faster throughput while still avoiding obvious RPM bursts
+- You can override worker count with `--jobs <count>`
+- Each image retries automatically up to 3 attempts
+- Final output includes success count, failure count, and per-image failure reasons

 ## Error Handling

 - Missing API key → error with setup instructions
- Generation failure → auto-retry once
+- Generation failure → auto-retry up to 3 attempts per image
 - Invalid aspect ratio → warning, proceed with default
- Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; or OpenAI GPT Image edits)
+- Reference images with unsupported provider/model → error with fix hint

 ## Extension Support

@@ -21,9 +21,25 @@ default_image_size: null    # 1K|2K|4K|null (Google only, overrides quality)

 default_model:
  google: null              # e.g., "gemini-3-pro-image-preview", "gemini-3.1-flash-image-preview"
-  openai: null              # e.g., "gpt-image-1.5"
+  openai: null              # e.g., "gpt-image-1.5", "gpt-image-1"
  dashscope: null           # e.g., "z-image-turbo"
  replicate: null           # e.g., "google/nano-banana-pro"
+
+batch:
+  max_workers: 10
+  provider_limits:
+    replicate:
+      concurrency: 5
+      start_interval_ms: 700
+    google:
+      concurrency: 3
+      start_interval_ms: 1100
+    openai:
+      concurrency: 3
+      start_interval_ms: 1100
+    dashscope:
+      concurrency: 3
+      start_interval_ms: 1100
 ---
 ```

@@ -40,6 +56,9 @@ default_model:
 | `default_model.openai` | string\|null | null | OpenAI default model |
 | `default_model.dashscope` | string\|null | null | DashScope 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 |
+| `batch.provider_limits.<provider>.start_interval_ms` | int\|null | provider default | Minimum gap between request starts per provider |

 ## Examples

@@ -65,5 +84,11 @@ default_model:
  openai: "gpt-image-1.5"
  dashscope: "z-image-turbo"
  replicate: "google/nano-banana-pro"
+batch:
+  max_workers: 10
+  provider_limits:
+    replicate:
+      concurrency: 5
+      start_interval_ms: 700
 ---
 ```
@@ -2,34 +2,108 @@ import path from "node:path";
 import process from "node:process";
 import { homedir } from "node:os";
 import { access, mkdir, readFile, writeFile } from "node:fs/promises";
-import type { CliArgs, Provider, ExtendConfig } from "./types";
+import type {
+  BatchFile,
+  BatchTaskInput,
+  CliArgs,
+  ExtendConfig,
+  Provider,
+} from "./types";
+
+type ProviderModule = {
+  getDefaultModel: () => string;
+  generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
+};
+
+type PreparedTask = {
+  id: string;
+  prompt: string;
+  args: CliArgs;
+  provider: Provider;
+  model: string;
+  outputPath: string;
+  providerModule: ProviderModule;
+};
+
+type TaskResult = {
+  id: string;
+  provider: Provider;
+  model: string;
+  outputPath: string;
+  success: boolean;
+  attempts: number;
+  error: string | null;
+};
+
+type ProviderRateLimit = {
+  concurrency: number;
+  startIntervalMs: number;
+};
+
+type LoadedBatchTasks = {
+  tasks: BatchTaskInput[];
+  jobs: number | null;
+  batchDir: string;
+};
+
+const MAX_ATTEMPTS = 3;
+const DEFAULT_MAX_WORKERS = 10;
+const POLL_WAIT_MS = 250;
+const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
+  replicate: { concurrency: 5, startIntervalMs: 700 },
+  google: { concurrency: 3, startIntervalMs: 1100 },
+  openai: { concurrency: 3, startIntervalMs: 1100 },
+  dashscope: { concurrency: 3, startIntervalMs: 1100 },
+};

 function printUsage(): void {
  console.log(`Usage:
  npx -y bun scripts/main.ts --prompt "A cat" --image cat.png
-  npx -y bun scripts/main.ts --prompt "A landscape" --image landscape.png --ar 16:9
  npx -y bun scripts/main.ts --promptfiles system.md content.md --image out.png
+  npx -y bun scripts/main.ts --batchfile batch.json

 Options:
  -p, --prompt <text>       Prompt text
  --promptfiles <files...>  Read prompt from files (concatenated)
-  --image <path>            Output image path (required)
+  --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|dashscope|replicate  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 (default: from quality)
-  --ref <files...>          Reference images (Google multimodal or OpenAI edits)
-  --n <count>               Number of images (default: 1)
+  --ref <files...>          Reference images (Google multimodal, OpenAI GPT Image edits, or Replicate)
+  --n <count>               Number of images for the current task (default: 1)
  --json                    JSON output
  -h, --help                Show help

+Batch file format:
+  {
+    "jobs": 4,
+    "tasks": [
+      {
+        "id": "hero",
+        "promptFiles": ["prompts/hero.md"],
+        "image": "out/hero.png",
+        "provider": "replicate",
+        "model": "google/nano-banana-pro",
+        "ar": "16:9"
+      }
+    ]
+  }
+
+Behavior:
+  - Batch mode automatically runs in parallel when pending tasks >= 2
+  - Each image retries automatically up to 3 attempts
+  - Batch summary reports success count, failure count, and per-image errors
+
 Environment variables:
  OPENAI_API_KEY            OpenAI API key
  GOOGLE_API_KEY            Google API key
  GEMINI_API_KEY            Gemini API key (alias for GOOGLE_API_KEY)
-  DASHSCOPE_API_KEY         DashScope API key (阿里云通义万象)
+  DASHSCOPE_API_KEY         DashScope API key
  REPLICATE_API_TOKEN       Replicate API token
  OPENAI_IMAGE_MODEL        Default OpenAI model (gpt-image-1.5)
  GOOGLE_IMAGE_MODEL        Default Google model (gemini-3-pro-image-preview)
@@ -40,6 +114,9 @@ Environment variables:
  GOOGLE_BASE_URL           Custom Google endpoint
  DASHSCOPE_BASE_URL        Custom DashScope endpoint
  REPLICATE_BASE_URL        Custom Replicate endpoint
+  BAOYU_IMAGE_GEN_MAX_WORKERS  Override batch worker cap
+  BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY  Override provider concurrency
+  BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS  Override provider start gap in ms

 Env file load order: CLI args > EXTEND.md > process.env > <cwd>/.baoyu-skills/.env > ~/.baoyu-skills/.env`);
 }
@@ -57,6 +134,8 @@ function parseArgs(argv: string[]): CliArgs {
    imageSize: null,
    referenceImages: [],
    n: 1,
+    batchFile: null,
+    jobs: null,
    json: false,
    help: false,
  };
@@ -110,9 +189,26 @@ function parseArgs(argv: string[]): CliArgs {
      continue;
    }

+    if (a === "--batchfile") {
+      const v = argv[++i];
+      if (!v) throw new Error("Missing value for --batchfile");
+      out.batchFile = v;
+      continue;
+    }
+
+    if (a === "--jobs") {
+      const v = argv[++i];
+      if (!v) throw new Error("Missing value for --jobs");
+      out.jobs = parseInt(v, 10);
+      if (isNaN(out.jobs) || out.jobs < 1) throw new Error(`Invalid worker count: ${v}`);
+      continue;
+    }
+
    if (a === "--provider") {
      const v = argv[++i];
-      if (v !== "google" && v !== "openai" && v !== "dashscope" && v !== "replicate") throw new Error(`Invalid provider: ${v}`);
+      if (v !== "google" && v !== "openai" && v !== "dashscope" && v !== "replicate") {
+        throw new Error(`Invalid provider: ${v}`);
+      }
      out.provider = v;
      continue;
    }
@@ -228,9 +324,11 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
  const config: Partial<ExtendConfig> = {};
  const lines = yaml.split("\n");
  let currentKey: string | null = null;
+  let currentProvider: Provider | null = null;

  for (const line of lines) {
    const trimmed = line.trim();
+    const indent = line.match(/^\s*/)?.[0].length ?? 0;
    if (!trimmed || trimmed.startsWith("#")) continue;

    if (trimmed.includes(":") && !trimmed.startsWith("-")) {
@@ -247,18 +345,57 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
      } else if (key === "default_provider") {
        config.default_provider = value === "null" ? null : (value as Provider);
      } else if (key === "default_quality") {
-        config.default_quality = value === "null" ? null : (value as "normal" | "2k");
+        config.default_quality = value === "null" ? null : value as "normal" | "2k";
      } else if (key === "default_aspect_ratio") {
        const cleaned = value.replace(/['"]/g, "");
        config.default_aspect_ratio = cleaned === "null" ? null : cleaned;
      } else if (key === "default_image_size") {
-        config.default_image_size = value === "null" ? null : (value as "1K" | "2K" | "4K");
+        config.default_image_size = value === "null" ? null : value as "1K" | "2K" | "4K";
      } else if (key === "default_model") {
        config.default_model = { google: null, openai: null, dashscope: null, replicate: null };
        currentKey = "default_model";
-      } else if (currentKey === "default_model" && (key === "google" || key === "openai" || key === "dashscope" || key === "replicate")) {
+        currentProvider = null;
+      } else if (key === "batch") {
+        config.batch = {};
+        currentKey = "batch";
+        currentProvider = null;
+      } else if (currentKey === "batch" && indent >= 2 && key === "max_workers") {
+        config.batch ??= {};
+        config.batch.max_workers = value === "null" ? null : parseInt(value, 10);
+      } else if (currentKey === "batch" && indent >= 2 && key === "provider_limits") {
+        config.batch ??= {};
+        config.batch.provider_limits ??= {};
+        currentKey = "provider_limits";
+        currentProvider = null;
+      } else if (
+        currentKey === "provider_limits" &&
+        indent >= 4 &&
+        (key === "google" || key === "openai" || key === "dashscope" || key === "replicate")
+      ) {
+        config.batch ??= {};
+        config.batch.provider_limits ??= {};
+        config.batch.provider_limits[key] ??= {};
+        currentProvider = key;
+      } else if (
+        currentKey === "default_model" &&
+        (key === "google" || key === "openai" || key === "dashscope" || key === "replicate")
+      ) {
        const cleaned = value.replace(/['"]/g, "");
        config.default_model![key] = cleaned === "null" ? null : cleaned;
+      } else if (
+        currentKey === "provider_limits" &&
+        currentProvider &&
+        indent >= 6 &&
+        (key === "concurrency" || key === "start_interval_ms")
+      ) {
+        config.batch ??= {};
+        config.batch.provider_limits ??= {};
+        const providerLimit = (config.batch.provider_limits[currentProvider] ??= {});
+        if (key === "concurrency") {
+          providerLimit.concurrency = value === "null" ? null : parseInt(value, 10);
+        } else {
+          providerLimit.start_interval_ms = value === "null" ? null : parseInt(value, 10);
+        }
      }
    }
  }
@@ -280,7 +417,6 @@ async function loadExtendConfig(): Promise<Partial<ExtendConfig>> {
      const content = await readFile(p, "utf8");
      const yaml = extractYamlFrontMatter(content);
      if (!yaml) continue;
-
      return parseSimpleYaml(yaml);
    } catch {
      continue;
@@ -300,6 +436,57 @@ function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
  };
 }

+function parsePositiveInt(value: string | undefined): number | null {
+  if (!value) return null;
+  const parsed = parseInt(value, 10);
+  return Number.isFinite(parsed) && parsed > 0 ? parsed : null;
+}
+
+function parsePositiveBatchInt(value: unknown): number | null {
+  if (value === null || value === undefined) return null;
+  if (typeof value === "number") {
+    return Number.isInteger(value) && value > 0 ? value : null;
+  }
+  if (typeof value === "string") {
+    return parsePositiveInt(value);
+  }
+  return null;
+}
+
+function getConfiguredMaxWorkers(extendConfig: Partial<ExtendConfig>): number {
+  const envValue = parsePositiveInt(process.env.BAOYU_IMAGE_GEN_MAX_WORKERS);
+  const configValue = extendConfig.batch?.max_workers ?? null;
+  return Math.max(1, envValue ?? configValue ?? DEFAULT_MAX_WORKERS);
+}
+
+function getConfiguredProviderRateLimits(
+  extendConfig: Partial<ExtendConfig>
+): Record<Provider, ProviderRateLimit> {
+  const configured: Record<Provider, ProviderRateLimit> = {
+    replicate: { ...DEFAULT_PROVIDER_RATE_LIMITS.replicate },
+    google: { ...DEFAULT_PROVIDER_RATE_LIMITS.google },
+    openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
+    dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
+  };
+
+  for (const provider of ["replicate", "google", "openai", "dashscope"] as Provider[]) {
+    const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
+    const extendLimit = extendConfig.batch?.provider_limits?.[provider];
+    configured[provider] = {
+      concurrency:
+        parsePositiveInt(process.env[`${envPrefix}_CONCURRENCY`]) ??
+        extendLimit?.concurrency ??
+        configured[provider].concurrency,
+      startIntervalMs:
+        parsePositiveInt(process.env[`${envPrefix}_START_INTERVAL_MS`]) ??
+        extendLimit?.start_interval_ms ??
+        configured[provider].startIntervalMs,
+    };
+  }
+
+  return configured;
+}
+
 async function readPromptFromFiles(files: string[]): Promise<string> {
  const parts: string[] = [];
  for (const f of files) {
@@ -311,9 +498,12 @@ async function readPromptFromFiles(files: string[]): Promise<string> {
 async function readPromptFromStdin(): Promise<string | null> {
  if (process.stdin.isTTY) return null;
  try {
-    const t = await Bun.stdin.text();
-    const v = t.trim();
-    return v.length > 0 ? v : null;
+    const chunks: Buffer[] = [];
+    for await (const chunk of process.stdin) {
+      chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
+    }
+    const value = Buffer.concat(chunks).toString("utf8").trim();
+    return value.length > 0 ? value : null;
  } catch {
    return null;
  }
@@ -327,7 +517,13 @@ function normalizeOutputImagePath(p: string): string {
 }

 function detectProvider(args: CliArgs): Provider {
-  if (args.referenceImages.length > 0 && args.provider && args.provider !== "google" && args.provider !== "openai" && args.provider !== "replicate") {
+  if (
+    args.referenceImages.length > 0 &&
+    args.provider &&
+    args.provider !== "google" &&
+    args.provider !== "openai" &&
+    args.provider !== "replicate"
+  ) {
    throw new Error(
      "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), or --provider replicate."
    );
@@ -349,7 +545,12 @@ function detectProvider(args: CliArgs): Provider {
    );
  }

-  const available = [hasGoogle && "google", hasOpenai && "openai", hasDashscope && "dashscope", hasReplicate && "replicate"].filter(Boolean) as Provider[];
+  const available = [
+    hasGoogle && "google",
+    hasOpenai && "openai",
+    hasDashscope && "dashscope",
+    hasReplicate && "replicate",
+  ].filter(Boolean) as Provider[];

  if (available.length === 1) return available[0]!;
  if (available.length > 1) return available[0]!;
@@ -371,11 +572,6 @@ async function validateReferenceImages(referenceImages: string[]): Promise<void>
  }
 }

-type ProviderModule = {
-  getDefaultModel: () => string;
-  generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
-};
-
 function isRetryableGenerationError(error: unknown): boolean {
  const msg = error instanceof Error ? error.message : String(error);
  const nonRetryableMarkers = [
@@ -384,26 +580,353 @@ function isRetryableGenerationError(error: unknown): boolean {
    "only supported",
    "No API key found",
    "is required",
+    "Invalid ",
+    "Unexpected ",
+    "API error (400)",
+    "API error (401)",
+    "API error (402)",
+    "API error (403)",
+    "API error (404)",
+    "temporarily disabled",
  ];
  return !nonRetryableMarkers.some((marker) => msg.includes(marker));
 }

 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 === "replicate") {
-    return (await import("./providers/replicate")) as ProviderModule;
-  }
+  if (provider === "google") return (await import("./providers/google")) as ProviderModule;
+  if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
+  if (provider === "replicate") return (await import("./providers/replicate")) as ProviderModule;
  return (await import("./providers/openai")) as ProviderModule;
 }

+async function loadPromptForArgs(args: CliArgs): Promise<string | null> {
+  let prompt: string | null = args.prompt;
+  if (!prompt && args.promptFiles.length > 0) {
+    prompt = await readPromptFromFiles(args.promptFiles);
+  }
+  return prompt;
+}
+
+function getModelForProvider(
+  provider: Provider,
+  requestedModel: string | null,
+  extendConfig: Partial<ExtendConfig>,
+  providerModule: ProviderModule
+): string {
+  if (requestedModel) return requestedModel;
+  if (extendConfig.default_model) {
+    if (provider === "google" && extendConfig.default_model.google) return extendConfig.default_model.google;
+    if (provider === "openai" && extendConfig.default_model.openai) return extendConfig.default_model.openai;
+    if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
+    if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
+  }
+  return providerModule.getDefaultModel();
+}
+
+async function prepareSingleTask(args: CliArgs, extendConfig: Partial<ExtendConfig>): Promise<PreparedTask> {
+  if (!args.quality) args.quality = "2k";
+
+  const prompt = (await loadPromptForArgs(args)) ?? (await readPromptFromStdin());
+  if (!prompt) throw new Error("Prompt is required");
+  if (!args.imagePath) throw new Error("--image is required");
+  if (args.referenceImages.length > 0) await validateReferenceImages(args.referenceImages);
+
+  const provider = detectProvider(args);
+  const providerModule = await loadProviderModule(provider);
+  const model = getModelForProvider(provider, args.model, extendConfig, providerModule);
+
+  return {
+    id: "single",
+    prompt,
+    args,
+    provider,
+    model,
+    outputPath: normalizeOutputImagePath(args.imagePath),
+    providerModule,
+  };
+}
+
+async function loadBatchTasks(batchFilePath: string): Promise<LoadedBatchTasks> {
+  const resolvedBatchFilePath = path.resolve(batchFilePath);
+  const content = await readFile(resolvedBatchFilePath, "utf8");
+  const parsed = JSON.parse(content.replace(/^\uFEFF/, "")) as BatchFile;
+  const batchDir = path.dirname(resolvedBatchFilePath);
+  if (Array.isArray(parsed)) {
+    return {
+      tasks: parsed,
+      jobs: null,
+      batchDir,
+    };
+  }
+  if (parsed && typeof parsed === "object" && Array.isArray(parsed.tasks)) {
+    const jobs = parsePositiveBatchInt(parsed.jobs);
+    if (parsed.jobs !== undefined && parsed.jobs !== null && jobs === null) {
+      throw new Error("Invalid batch file. jobs must be a positive integer when provided.");
+    }
+    return {
+      tasks: parsed.tasks,
+      jobs,
+      batchDir,
+    };
+  }
+  throw new Error("Invalid batch file. Expected an array of tasks or an object with a tasks array.");
+}
+
+function resolveBatchPath(batchDir: string, filePath: string): string {
+  return path.isAbsolute(filePath) ? filePath : path.resolve(batchDir, filePath);
+}
+
+function createTaskArgs(baseArgs: CliArgs, task: BatchTaskInput, batchDir: string): CliArgs {
+  return {
+    ...baseArgs,
+    prompt: task.prompt ?? null,
+    promptFiles: task.promptFiles ? task.promptFiles.map((filePath) => resolveBatchPath(batchDir, filePath)) : [],
+    imagePath: task.image ? resolveBatchPath(batchDir, task.image) : null,
+    provider: task.provider ?? baseArgs.provider ?? null,
+    model: task.model ?? baseArgs.model ?? null,
+    aspectRatio: task.ar ?? baseArgs.aspectRatio ?? null,
+    size: task.size ?? baseArgs.size ?? null,
+    quality: task.quality ?? baseArgs.quality ?? null,
+    imageSize: task.imageSize ?? baseArgs.imageSize ?? null,
+    referenceImages: task.ref ? task.ref.map((filePath) => resolveBatchPath(batchDir, filePath)) : [],
+    n: task.n ?? baseArgs.n,
+    batchFile: null,
+    jobs: baseArgs.jobs,
+    json: baseArgs.json,
+    help: false,
+  };
+}
+
+async function prepareBatchTasks(
+  args: CliArgs,
+  extendConfig: Partial<ExtendConfig>
+): Promise<{ tasks: PreparedTask[]; jobs: number | null }> {
+  if (!args.batchFile) throw new Error("--batchfile is required in batch mode");
+  const { tasks: taskInputs, jobs: batchJobs, batchDir } = await loadBatchTasks(args.batchFile);
+  if (taskInputs.length === 0) throw new Error("Batch file does not contain any tasks.");
+
+  const prepared: PreparedTask[] = [];
+  for (let i = 0; i < taskInputs.length; i++) {
+    const task = taskInputs[i]!;
+    const taskArgs = createTaskArgs(args, task, batchDir);
+    const prompt = await loadPromptForArgs(taskArgs);
+    if (!prompt) throw new Error(`Task ${i + 1} is missing prompt or promptFiles.`);
+    if (!taskArgs.imagePath) throw new Error(`Task ${i + 1} is missing image output path.`);
+    if (taskArgs.referenceImages.length > 0) await validateReferenceImages(taskArgs.referenceImages);
+
+    const provider = detectProvider(taskArgs);
+    const providerModule = await loadProviderModule(provider);
+    const model = getModelForProvider(provider, taskArgs.model, extendConfig, providerModule);
+    prepared.push({
+      id: task.id || `task-${String(i + 1).padStart(2, "0")}`,
+      prompt,
+      args: taskArgs,
+      provider,
+      model,
+      outputPath: normalizeOutputImagePath(taskArgs.imagePath),
+      providerModule,
+    });
+  }
+
+  return {
+    tasks: prepared,
+    jobs: args.jobs ?? batchJobs,
+  };
+}
+
+async function writeImage(outputPath: string, imageData: Uint8Array): Promise<void> {
+  await mkdir(path.dirname(outputPath), { recursive: true });
+  await writeFile(outputPath, imageData);
+}
+
+async function generatePreparedTask(task: PreparedTask): Promise<TaskResult> {
+  console.error(`Using ${task.provider} / ${task.model} for ${task.id}`);
+  console.error(
+    `Switch model: --model <id> | EXTEND.md default_model.${task.provider} | env ${task.provider.toUpperCase()}_IMAGE_MODEL`
+  );
+
+  let attempts = 0;
+  while (attempts < MAX_ATTEMPTS) {
+    attempts += 1;
+    try {
+      const imageData = await task.providerModule.generateImage(task.prompt, task.model, task.args);
+      await writeImage(task.outputPath, imageData);
+      return {
+        id: task.id,
+        provider: task.provider,
+        model: task.model,
+        outputPath: task.outputPath,
+        success: true,
+        attempts,
+        error: null,
+      };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error);
+      const canRetry = attempts < MAX_ATTEMPTS && isRetryableGenerationError(error);
+      if (canRetry) {
+        console.error(`[${task.id}] Attempt ${attempts}/${MAX_ATTEMPTS} failed, retrying...`);
+        continue;
+      }
+      return {
+        id: task.id,
+        provider: task.provider,
+        model: task.model,
+        outputPath: task.outputPath,
+        success: false,
+        attempts,
+        error: message,
+      };
+    }
+  }
+
+  return {
+    id: task.id,
+    provider: task.provider,
+    model: task.model,
+    outputPath: task.outputPath,
+    success: false,
+    attempts: MAX_ATTEMPTS,
+    error: "Unknown failure",
+  };
+}
+
+function createProviderGate(providerRateLimits: Record<Provider, ProviderRateLimit>) {
+  const state = new Map<Provider, { active: number; lastStartedAt: number }>();
+
+  return async function acquire(provider: Provider): Promise<() => void> {
+    const limit = providerRateLimits[provider];
+    while (true) {
+      const current = state.get(provider) ?? { active: 0, lastStartedAt: 0 };
+      const now = Date.now();
+      const enoughCapacity = current.active < limit.concurrency;
+      const enoughGap = now - current.lastStartedAt >= limit.startIntervalMs;
+      if (enoughCapacity && enoughGap) {
+        state.set(provider, { active: current.active + 1, lastStartedAt: now });
+        return () => {
+          const latest = state.get(provider) ?? { active: 1, lastStartedAt: now };
+          state.set(provider, {
+            active: Math.max(0, latest.active - 1),
+            lastStartedAt: latest.lastStartedAt,
+          });
+        };
+      }
+      await new Promise((resolve) => setTimeout(resolve, POLL_WAIT_MS));
+    }
+  };
+}
+
+function getWorkerCount(taskCount: number, jobs: number | null, maxWorkers: number): number {
+  const requested = jobs ?? Math.min(taskCount, maxWorkers);
+  return Math.max(1, Math.min(requested, taskCount, maxWorkers));
+}
+
+async function runBatchTasks(
+  tasks: PreparedTask[],
+  jobs: number | null,
+  extendConfig: Partial<ExtendConfig>
+): Promise<TaskResult[]> {
+  if (tasks.length === 1) {
+    return [await generatePreparedTask(tasks[0]!)];
+  }
+
+  const maxWorkers = getConfiguredMaxWorkers(extendConfig);
+  const providerRateLimits = getConfiguredProviderRateLimits(extendConfig);
+  const acquireProvider = createProviderGate(providerRateLimits);
+  const workerCount = getWorkerCount(tasks.length, jobs, maxWorkers);
+  console.error(`Batch mode: ${tasks.length} tasks, ${workerCount} workers, parallel mode enabled.`);
+  for (const provider of ["replicate", "google", "openai", "dashscope"] as Provider[]) {
+    const limit = providerRateLimits[provider];
+    console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
+  }
+
+  let nextIndex = 0;
+  const results: TaskResult[] = new Array(tasks.length);
+
+  const worker = async (): Promise<void> => {
+    while (true) {
+      const currentIndex = nextIndex;
+      nextIndex += 1;
+      if (currentIndex >= tasks.length) return;
+
+      const task = tasks[currentIndex]!;
+      const release = await acquireProvider(task.provider);
+      try {
+        results[currentIndex] = await generatePreparedTask(task);
+      } finally {
+        release();
+      }
+    }
+  };
+
+  await Promise.all(Array.from({ length: workerCount }, () => worker()));
+  return results;
+}
+
+function printBatchSummary(results: TaskResult[]): void {
+  const successCount = results.filter((result) => result.success).length;
+  const failureCount = results.length - successCount;
+
+  console.error("");
+  console.error("Batch generation summary:");
+  console.error(`- Total: ${results.length}`);
+  console.error(`- Succeeded: ${successCount}`);
+  console.error(`- Failed: ${failureCount}`);
+
+  if (failureCount > 0) {
+    console.error("Failure reasons:");
+    for (const result of results.filter((item) => !item.success)) {
+      console.error(`- ${result.id}: ${result.error}`);
+    }
+  }
+}
+
+function emitJson(payload: unknown): void {
+  console.log(JSON.stringify(payload, null, 2));
+}
+
+async function runSingleMode(args: CliArgs, extendConfig: Partial<ExtendConfig>): Promise<void> {
+  const task = await prepareSingleTask(args, extendConfig);
+  const result = await generatePreparedTask(task);
+  if (!result.success) {
+    throw new Error(result.error || "Generation failed");
+  }
+
+  if (args.json) {
+    emitJson({
+      savedImage: result.outputPath,
+      provider: result.provider,
+      model: result.model,
+      attempts: result.attempts,
+      prompt: task.prompt.slice(0, 200),
+    });
+    return;
+  }
+
+  console.log(result.outputPath);
+}
+
+async function runBatchMode(args: CliArgs, extendConfig: Partial<ExtendConfig>): Promise<void> {
+  const { tasks, jobs } = await prepareBatchTasks(args, extendConfig);
+  const results = await runBatchTasks(tasks, jobs, extendConfig);
+  printBatchSummary(results);
+
+  if (args.json) {
+    emitJson({
+      mode: "batch",
+      total: results.length,
+      succeeded: results.filter((item) => item.success).length,
+      failed: results.filter((item) => !item.success).length,
+      results,
+    });
+  }
+
+  if (results.some((item) => !item.success)) {
+    process.exitCode = 1;
+  }
+}
+
 async function main(): Promise<void> {
  const args = parseArgs(process.argv.slice(2));
-
  if (args.help) {
    printUsage();
    return;
@@ -412,86 +935,18 @@ async function main(): Promise<void> {
  await loadEnv();
  const extendConfig = await loadExtendConfig();
  const mergedArgs = mergeConfig(args, extendConfig);
-
  if (!mergedArgs.quality) mergedArgs.quality = "2k";

-  let prompt: string | null = mergedArgs.prompt;
-  if (!prompt && mergedArgs.promptFiles.length > 0) prompt = await readPromptFromFiles(mergedArgs.promptFiles);
-  if (!prompt) prompt = await readPromptFromStdin();
-
-  if (!prompt) {
-    console.error("Error: Prompt is required");
-    printUsage();
-    process.exitCode = 1;
+  if (mergedArgs.batchFile) {
+    await runBatchMode(mergedArgs, extendConfig);
    return;
  }

-  if (!mergedArgs.imagePath) {
-    console.error("Error: --image is required");
-    printUsage();
-    process.exitCode = 1;
-    return;
-  }
-
-  if (mergedArgs.referenceImages.length > 0) {
-    await validateReferenceImages(mergedArgs.referenceImages);
-  }
-
-  const provider = detectProvider(mergedArgs);
-  const providerModule = await loadProviderModule(provider);
-
-  let model = mergedArgs.model;
-  if (!model && extendConfig.default_model) {
-    if (provider === "google") model = extendConfig.default_model.google ?? null;
-    if (provider === "openai") model = extendConfig.default_model.openai ?? null;
-    if (provider === "dashscope") model = extendConfig.default_model.dashscope ?? null;
-    if (provider === "replicate") model = extendConfig.default_model.replicate ?? null;
-  }
-  model = model || providerModule.getDefaultModel();
-
-  const outputPath = normalizeOutputImagePath(mergedArgs.imagePath);
-
-  let imageData: Uint8Array;
-  let retried = false;
-
-  while (true) {
-    try {
-      imageData = await providerModule.generateImage(prompt, model, mergedArgs);
-      break;
-    } catch (e) {
-      if (!retried && isRetryableGenerationError(e)) {
-        retried = true;
-        console.error("Generation failed, retrying...");
-        continue;
-      }
-      throw e;
-    }
-  }
-
-  const dir = path.dirname(outputPath);
-  await mkdir(dir, { recursive: true });
-  await writeFile(outputPath, imageData);
-
-  if (mergedArgs.json) {
-    console.log(
-      JSON.stringify(
-        {
-          savedImage: outputPath,
-          provider,
-          model,
-          prompt: prompt.slice(0, 200),
-        },
-        null,
-        2
-      )
-    );
-  } else {
-    console.log(outputPath);
-  }
+  await runSingleMode(mergedArgs, extendConfig);
 }

-main().catch((e) => {
-  const msg = e instanceof Error ? e.message : String(e);
-  console.error(msg);
+main().catch((error) => {
+  const message = error instanceof Error ? error.message : String(error);
+  console.error(message);
  process.exit(1);
 });
@@ -1,6 +1,6 @@
 import path from "node:path";
 import { readFile } from "node:fs/promises";
-import { execSync } from "node:child_process";
+import { execFileSync } from "node:child_process";
 import type { CliArgs } from "../types";

 const GOOGLE_MULTIMODAL_MODELS = [
@@ -76,14 +76,43 @@ async function postGoogleJsonViaCurl<T>(
 ): Promise<T> {
  const proxy = getHttpProxy();
  const bodyStr = JSON.stringify(body);
-  const proxyArgs = proxy ? `-x "${proxy}"` : "";
+  const args = [
+    "-s",
+    "--connect-timeout",
+    "30",
+    "--max-time",
+    "300",
+    ...(proxy ? ["-x", proxy] : []),
+    url,
+    "-H",
+    "Content-Type: application/json",
+    "-H",
+    `x-goog-api-key: ${apiKey}`,
+    "-d",
+    "@-",
+  ];

-  const result = execSync(
-    `curl -s --connect-timeout 30 --max-time 300 ${proxyArgs} "${url}" -H "Content-Type: application/json" -H "x-goog-api-key: ${apiKey}" -d @-`,
-    { input: bodyStr, maxBuffer: 100 * 1024 * 1024, timeout: 310000 },
-  );
+  let result = "";
+  try {
+    result = execFileSync("curl", args, {
+      input: bodyStr,
+      encoding: "utf8",
+      maxBuffer: 100 * 1024 * 1024,
+      timeout: 310000,
+    });
+  } catch (error) {
+    const e = error as { message?: string; stderr?: string | Buffer };
+    const stderrText =
+      typeof e.stderr === "string"
+        ? e.stderr
+        : e.stderr
+          ? e.stderr.toString("utf8")
+          : "";
+    const details = stderrText.trim() || e.message || "curl request failed";
+    throw new Error(`Google API request failed via curl: ${details}`);
+  }

-  const parsed = JSON.parse(result.toString()) as any;
+  const parsed = JSON.parse(result) as any;
  if (parsed.error) {
    throw new Error(
      `Google API error (${parsed.error.code}): ${parsed.error.message}`,
@@ -68,7 +68,11 @@ export async function generateImage(
  const baseURL = process.env.OPENAI_BASE_URL || "https://api.openai.com/v1";
  const apiKey = process.env.OPENAI_API_KEY;

-  if (!apiKey) throw new Error("OPENAI_API_KEY is required");
+  if (!apiKey) {
+    throw new Error(
+      "OPENAI_API_KEY is required. Codex/ChatGPT desktop login does not automatically grant OpenAI Images API access to this script."
+    );
+  }

  if (process.env.OPENAI_IMAGE_USE_CHAT === "true") {
    return generateWithChatCompletions(baseURL, apiKey, prompt, model);
@@ -36,22 +36,24 @@ function buildInput(prompt: string, args: CliArgs, referenceImages: string[]): R

  if (args.aspectRatio) {
    input.aspect_ratio = args.aspectRatio;
+  } else if (referenceImages.length > 0) {
+    input.aspect_ratio = "match_input_image";
  }

  if (args.n > 1) {
    input.number_of_images = args.n;
  }

+  if (args.quality === "normal") {
+    input.resolution = "1K";
+  } else if (args.quality === "2k") {
+    input.resolution = "2K";
+  }
+
  input.output_format = "png";

  if (referenceImages.length > 0) {
-    if (referenceImages.length === 1) {
-      input.image = referenceImages[0];
-    } else {
-      for (let i = 0; i < referenceImages.length; i++) {
-        input[`image${i > 0 ? i + 1 : ""}`] = referenceImages[i];
-      }
-    }
+    input.image_input = referenceImages;
  }

  return input;
@@ -13,10 +13,34 @@ export type CliArgs = {
  imageSize: string | null;
  referenceImages: string[];
  n: number;
+  batchFile: string | null;
+  jobs: number | null;
  json: boolean;
  help: boolean;
 };

+export type BatchTaskInput = {
+  id?: string;
+  prompt?: string | null;
+  promptFiles?: string[];
+  image?: string;
+  provider?: Provider | null;
+  model?: string | null;
+  ar?: string | null;
+  size?: string | null;
+  quality?: Quality | null;
+  imageSize?: "1K" | "2K" | "4K" | null;
+  ref?: string[];
+  n?: number;
+};
+
+export type BatchFile =
+  | BatchTaskInput[]
+  | {
+      tasks: BatchTaskInput[];
+      jobs?: number | null;
+    };
+
 export type ExtendConfig = {
  version: number;
  default_provider: Provider | null;
@@ -29,4 +53,16 @@ export type ExtendConfig = {
    dashscope: string | null;
    replicate: string | null;
  };
+  batch?: {
+    max_workers?: number | null;
+    provider_limits?: Partial<
+      Record<
+        Provider,
+        {
+          concurrency?: number | null;
+          start_interval_ms?: number | null;
+        }
+      >
+    >;
+  };
 };
@@ -1,6 +1,10 @@
 ---
 name: baoyu-infographic
 description: Generates professional infographics with 21 layout types and 20 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-infographic
 ---

 # Infographic Generator
@@ -143,12 +147,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-infographic/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-infographic/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-infographic/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-infographic/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-infographic/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-infographic/EXTEND.md") { "user" }
 ```

@@ -1,6 +1,14 @@
 ---
 name: baoyu-markdown-to-html
 description: Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md转html", "微信外链转底部引用", or needs styled HTML output from markdown.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-markdown-to-html
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Markdown to HTML Converter
@@ -9,7 +17,7 @@ Converts Markdown files to beautifully styled HTML with inline CSS, optimized fo

 ## Script Directory

-**Agent Execution**: Determine this SKILL.md directory as `SKILL_DIR`. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `${SKILL_DIR}` and `${BUN_X}` with actual values.
+**Agent Execution**: Determine this SKILL.md directory as `{baseDir}`. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `{baseDir}` and `${BUN_X}` with actual values.

 | Script | Purpose |
 |--------|---------|
@@ -22,12 +30,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-markdown-to-html/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-markdown-to-html/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-markdown-to-html/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-markdown-to-html/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-markdown-to-html/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-markdown-to-html/EXTEND.md") { "user" }
 ```

@@ -117,7 +128,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-post-to-wechat/EXTEND.md") { Select-Str
 ### Step 2: Convert

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <markdown_file> --theme <theme> [--cite]
+${BUN_X} {baseDir}/scripts/main.ts <markdown_file> --theme <theme> [--cite]
 ```

 ### Step 3: Report Result
@@ -127,7 +138,7 @@ Display the output path from JSON result. If backup was created, mention it.
 ## Usage

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <markdown_file> [options]
+${BUN_X} {baseDir}/scripts/main.ts <markdown_file> [options]
 ```

 **Options:**
@@ -165,22 +176,22 @@ ${BUN_X} ${SKILL_DIR}/scripts/main.ts <markdown_file> [options]

 ```bash
 # Basic conversion (uses default theme, removes first heading)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md
+${BUN_X} {baseDir}/scripts/main.ts article.md

 # With specific theme
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --theme grace
+${BUN_X} {baseDir}/scripts/main.ts article.md --theme grace

 # Theme with custom color
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --theme modern --color red
+${BUN_X} {baseDir}/scripts/main.ts article.md --theme modern --color red

 # Enable bottom citations for ordinary external links
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --cite
+${BUN_X} {baseDir}/scripts/main.ts article.md --cite

 # Keep the first heading in content
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --keep-title
+${BUN_X} {baseDir}/scripts/main.ts article.md --keep-title

 # Override title
-${BUN_X} ${SKILL_DIR}/scripts/main.ts article.md --title "My Article"
+${BUN_X} {baseDir}/scripts/main.ts article.md --title "My Article"
 ```

 ## Output
@@ -37,6 +37,10 @@ function parseExtendYaml(yaml: string): Partial<ExtendConfig> {
 export function loadExtendConfig(): Partial<ExtendConfig> {
  const paths = [
    path.join(process.cwd(), ".baoyu-skills", "baoyu-markdown-to-html", "EXTEND.md"),
+    path.join(
+      process.env.XDG_CONFIG_HOME || path.join(homedir(), ".config"),
+      "baoyu-skills", "baoyu-markdown-to-html", "EXTEND.md"
+    ),
    path.join(homedir(), ".baoyu-skills", "baoyu-markdown-to-html", "EXTEND.md"),
  ];
  for (const p of paths) {
@@ -1,6 +1,14 @@
 ---
 name: baoyu-post-to-wechat
 description: Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-post-to-wechat
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Post to WeChat Official Account
@@ -11,7 +19,7 @@ description: Posts content to WeChat Official Account (微信公众号) via API

 ## Script Directory

-**Agent Execution**: Determine this SKILL.md directory as `SKILL_DIR`, then use `${SKILL_DIR}/scripts/<name>.ts`. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun.
+**Agent Execution**: Determine this SKILL.md directory as `{baseDir}`, then use `{baseDir}/scripts/<name>.ts`. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun.

 | Script | Purpose |
 |--------|---------|
@@ -28,12 +36,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-post-to-wechat/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-post-to-wechat/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-post-to-wechat/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-post-to-wechat/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-post-to-wechat/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-post-to-wechat/EXTEND.md") { "user" }
 ```

@@ -92,7 +103,7 @@ chrome_profile_path: /path/to/chrome/profile
 Before first use, suggest running the environment check. User can skip if they prefer.

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/check-permissions.ts
+${BUN_X} {baseDir}/scripts/check-permissions.ts
 ```

 Checks: Chrome, profile isolation, Bun, Accessibility, clipboard, paste keystroke, API credentials, Chrome conflicts.
@@ -115,8 +126,8 @@ Checks: Chrome, profile isolation, Bun, Accessibility, clipboard, paste keystrok
 For short posts with multiple images (up to 9):

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/wechat-browser.ts --markdown article.md --images ./images/
-${BUN_X} ${SKILL_DIR}/scripts/wechat-browser.ts --title "标题" --content "内容" --image img.png --submit
+${BUN_X} {baseDir}/scripts/wechat-browser.ts --markdown article.md --images ./images/
+${BUN_X} {baseDir}/scripts/wechat-browser.ts --title "标题" --content "内容" --image img.png --submit
 ```

 See [references/image-text-posting.md](references/image-text-posting.md) for details.
@@ -260,7 +271,7 @@ WECHAT_APP_SECRET=<user_input>
 **API method** (accepts `.md` or `.html`):

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/wechat-api.ts <file> --theme <theme> [--color <color>] [--title <title>] [--summary <summary>] [--author <author>] [--cover <cover_path>] [--no-cite]
+${BUN_X} {baseDir}/scripts/wechat-api.ts <file> --theme <theme> [--color <color>] [--title <title>] [--summary <summary>] [--author <author>] [--cover <cover_path>] [--no-cite]
 ```

 **CRITICAL**: Always include `--theme` parameter. Never omit it, even if using `default`. Only include `--color` if explicitly set by user or EXTEND.md.
@@ -279,8 +290,8 @@ If script parameters do not expose the two comment fields, still ensure final AP
 **Browser method** (accepts `--markdown` or `--html`):

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/wechat-article.ts --markdown <markdown_file> --theme <theme> [--color <color>] [--no-cite]
-${BUN_X} ${SKILL_DIR}/scripts/wechat-article.ts --html <html_file>
+${BUN_X} {baseDir}/scripts/wechat-article.ts --markdown <markdown_file> --theme <theme> [--color <color>] [--no-cite]
+${BUN_X} {baseDir}/scripts/wechat-article.ts --html <html_file>
 ```

 ### Step 5: Completion Report
@@ -37,6 +37,10 @@ function parseExtendYaml(yaml: string): Partial<ExtendConfig> {
 export function loadExtendConfig(): Partial<ExtendConfig> {
  const paths = [
    path.join(process.cwd(), ".baoyu-skills", "baoyu-markdown-to-html", "EXTEND.md"),
+    path.join(
+      process.env.XDG_CONFIG_HOME || path.join(homedir(), ".config"),
+      "baoyu-skills", "baoyu-markdown-to-html", "EXTEND.md"
+    ),
    path.join(homedir(), ".baoyu-skills", "baoyu-markdown-to-html", "EXTEND.md"),
  ];
  for (const p of paths) {
@@ -1,4 +1,4 @@
-import { execSync, spawnSync } from 'node:child_process';
+import { spawnSync } from 'node:child_process';
 import fs from 'node:fs';
 import path from 'node:path';
 import process from 'node:process';
@@ -10,30 +10,51 @@ function sleep(ms: number): Promise<void> {
  return new Promise((resolve) => setTimeout(resolve, ms));
 }

-function ab(cmd: string, json = false): string {
-  const fullCmd = `agent-browser --session ${SESSION} ${cmd}${json ? ' --json' : ''}`;
-  console.log(`[ab] ${fullCmd}`);
-  try {
-    const result = execSync(fullCmd, { encoding: 'utf8', stdio: ['pipe', 'pipe', 'pipe'] });
-    return result.trim();
-  } catch (e: unknown) {
-    const err = e as { stdout?: string; stderr?: string; message?: string };
-    console.error(`[ab] Error: ${err.stderr || err.message}`);
-    return err.stdout || '';
-  }
+function quoteForLog(arg: string): string {
+  return /[\s"'\\]/.test(arg) ? JSON.stringify(arg) : arg;
 }

-function abRaw(args: string[]): { success: boolean; output: string } {
+function toSafeJsStringLiteral(value: string): string {
+  return JSON.stringify(value)
+    .replace(/\u2028/g, '\\u2028')
+    .replace(/\u2029/g, '\\u2029');
+}
+
+function runAgentBrowser(args: string[]): {
+  success: boolean;
+  output: string;
+  spawnError?: string;
+} {
  const result = spawnSync('agent-browser', ['--session', SESSION, ...args], {
    encoding: 'utf8',
    stdio: ['pipe', 'pipe', 'pipe']
  });
+  const spawnError = result.error?.message?.trim();
+  const output = result.stdout || result.stderr || '';
  return {
    success: result.status === 0,
-    output: result.stdout || result.stderr || ''
+    output: output || spawnError || '',
+    spawnError
  };
 }

+function ab(args: string[], json = false): string {
+  const fullArgs = json ? [...args, '--json'] : args;
+  console.log(`[ab] agent-browser --session ${SESSION} ${fullArgs.map(quoteForLog).join(' ')}`);
+  const result = runAgentBrowser(fullArgs);
+  if (result.spawnError) {
+    throw new Error(`agent-browser failed to start: ${result.spawnError}`);
+  }
+  if (!result.success) {
+    console.error(`[ab] Error: ${result.output.trim()}`);
+  }
+  return result.output.trim();
+}
+
+function abRaw(args: string[]): { success: boolean; output: string } {
+  return runAgentBrowser(args);
+}
+
 interface SnapshotElement {
  ref: string;
  role: string;
@@ -99,17 +120,17 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
  }

  console.log('[wechat] Opening WeChat Official Account...');
-  ab(`open ${WECHAT_URL} --headed`);
+  ab(['open', WECHAT_URL, '--headed']);
  await sleep(5000);

  console.log('[wechat] Checking login status...');
-  let url = ab('get url');
+  let url = ab(['get', 'url']);
  console.log(`[wechat] Current URL: ${url}`);

  const waitForLogin = async (timeoutMs = 120_000): Promise<boolean> => {
    const start = Date.now();
    while (Date.now() - start < timeoutMs) {
-      url = ab('get url');
+      url = ab(['get', 'url']);
      if (url.includes('/cgi-bin/home')) return true;
      console.log('[wechat] Waiting for login...');
      await sleep(3000);
@@ -126,7 +147,7 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
  await sleep(2000);

  console.log('[wechat] Getting page snapshot...');
-  let snapshot = ab('snapshot');
+  let snapshot = ab(['snapshot']);
  console.log(snapshot);

  console.log('[wechat] Looking for "图文" menu...');
@@ -134,16 +155,16 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {

  if (!tuWenRef) {
    console.log('[wechat] Using eval to find and click menu...');
-    ab(`eval "document.querySelectorAll('.new-creation__menu .new-creation__menu-item')[2].click()"`);
+    ab(['eval', "document.querySelectorAll('.new-creation__menu .new-creation__menu-item')[2].click()"]);
  } else {
    console.log(`[wechat] Clicking menu ref: ${tuWenRef}`);
-    ab(`click ${tuWenRef}`);
+    ab(['click', tuWenRef]);
  }

  await sleep(4000);

  console.log('[wechat] Checking for new tab...');
-  const tabsOutput = ab('tab');
+  const tabsOutput = ab(['tab']);
  console.log(`[wechat] Tabs: ${tabsOutput}`);

  const tabLines = tabsOutput.split('\n');
@@ -153,14 +174,14 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
    const tabMatch = tabsOutput.match(/\[(\d+)\].*(?:appmsg|edit)/i);
    if (tabMatch) {
      console.log(`[wechat] Switching to editor tab ${tabMatch[1]}...`);
-      ab(`tab ${tabMatch[1]}`);
+      ab(['tab', tabMatch[1]]);
    } else {
      const lastTabMatch = tabsOutput.match(/\[(\d+)\]/g);
      if (lastTabMatch && lastTabMatch.length > 1) {
        const lastTab = lastTabMatch[lastTabMatch.length - 1].match(/\d+/)?.[0];
        if (lastTab) {
          console.log(`[wechat] Switching to last tab ${lastTab}...`);
-          ab(`tab ${lastTab}`);
+          ab(['tab', lastTab]);
        }
      }
    }
@@ -168,38 +189,44 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {

  await sleep(3000);

-  url = ab('get url');
+  url = ab(['get', 'url']);
  console.log(`[wechat] Editor URL: ${url}`);

  console.log('[wechat] Getting editor snapshot...');
-  snapshot = ab('snapshot');
+  snapshot = ab(['snapshot']);
  console.log(snapshot.substring(0, 2000));

  console.log('[wechat] Uploading images...');
  const fileInputSelector = '.js_upload_btn_container input[type=file]';
+  const fileInputSelectorJs = toSafeJsStringLiteral(fileInputSelector);

-  ab(`eval "document.querySelector('${fileInputSelector}').style.display = 'block'"`);
+  ab(['eval', `{
+    const input = document.querySelector(${fileInputSelectorJs});
+    if (input) input.style.display = 'block';
+  }`]);
  await sleep(500);

-  const uploadResult = abRaw(['upload', `"${fileInputSelector}"`, ...absoluteImages]);
+  const uploadResult = abRaw(['upload', fileInputSelector, ...absoluteImages]);
  console.log(`[wechat] Upload result: ${uploadResult.output}`);

  if (!uploadResult.success) {
    console.log('[wechat] Using alternative upload method...');
    for (const img of absoluteImages) {
      console.log(`[wechat] Uploading: ${img}`);
-      ab(`eval "
-        const input = document.querySelector('${fileInputSelector}');
+      const imgUrlJs = toSafeJsStringLiteral(`file://${img}`);
+      const imgFileNameJs = toSafeJsStringLiteral(path.basename(img));
+      ab(['eval', `
+        const input = document.querySelector(${fileInputSelectorJs});
        if (input) {
          const dt = new DataTransfer();
-          fetch('file://${img}').then(r => r.blob()).then(b => {
-            const file = new File([b], '${path.basename(img)}', { type: 'image/png' });
+          fetch(${imgUrlJs}).then(r => r.blob()).then(b => {
+            const file = new File([b], ${imgFileNameJs}, { type: 'image/png' });
            dt.items.add(file);
            input.files = dt.files;
            input.dispatchEvent(new Event('change', { bubbles: true }));
          });
        }
-      "`);
+      `]);
      await sleep(2000);
    }
  }
@@ -208,13 +235,14 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
  await sleep(10000);

  console.log('[wechat] Filling title...');
-  snapshot = ab('snapshot -i');
+  snapshot = ab(['snapshot', '-i']);
  const titleRef = findElementByText(snapshot, 'title') || findElementByText(snapshot, '标题');

  if (titleRef) {
-    ab(`fill ${titleRef} "${title.replace(/"/g, '\\"')}"`);
+    ab(['fill', titleRef, title]);
  } else {
-    ab(`eval "const t = document.querySelector('#title'); if(t) { t.value = '${title.replace(/'/g, "\\'")}'; t.dispatchEvent(new Event('input', {bubbles: true})); }"`);
+    const titleJs = toSafeJsStringLiteral(title);
+    ab(['eval', `const t = document.querySelector('#title'); if(t) { t.value = ${titleJs}; t.dispatchEvent(new Event('input', {bubbles: true})); }`]);
  }
  await sleep(500);

@@ -222,9 +250,9 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
  const editorRef = findElementByText(snapshot, 'js_pmEditorArea') || findElementByText(snapshot, 'textbox');

  if (editorRef) {
-    ab(`click ${editorRef}`);
+    ab(['click', editorRef]);
  } else {
-    ab(`eval "document.querySelector('.js_pmEditorArea')?.click()"`);
+    ab(['eval', "document.querySelector('.js_pmEditorArea')?.click()"]);
  }
  await sleep(500);

@@ -233,11 +261,11 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
  for (let i = 0; i < lines.length; i++) {
    const line = lines[i];
    if (line.length > 0) {
-      const escapedLine = line.replace(/"/g, '\\"').replace(/'/g, "\\'");
-      ab(`eval "document.execCommand('insertText', false, '${escapedLine}')"`);
+      const lineJs = toSafeJsStringLiteral(line);
+      ab(['eval', `document.execCommand('insertText', false, ${lineJs})`]);
    }
    if (i < lines.length - 1) {
-      ab('press Enter');
+      ab(['press', 'Enter']);
    }
    await sleep(100);
  }
@@ -249,9 +277,9 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {
    console.log('[wechat] Saving as draft...');
    const submitRef = findElementByText(snapshot, 'js_submit') || findElementByText(snapshot, '保存');
    if (submitRef) {
-      ab(`click ${submitRef}`);
+      ab(['click', submitRef]);
    } else {
-      ab(`eval "document.querySelector('#js_submit')?.click()"`);
+      ab(['eval', "document.querySelector('#js_submit')?.click()"]);
    }
    await sleep(3000);
    console.log('[wechat] Draft saved!');
@@ -261,7 +289,7 @@ async function postToWeChat(options: WeChatOptions): Promise<void> {

  if (!keepOpen) {
    console.log('[wechat] Closing browser...');
-    ab('close');
+    ab(['close']);
  } else {
    console.log('[wechat] Done. Browser window left open.');
  }
@@ -1,6 +1,14 @@
 ---
 name: baoyu-post-to-weibo
 description: Posts content to Weibo (微博). Supports regular posts with text, images, and videos, and headline articles (头条文章) with Markdown input via Chrome CDP. Use when user asks to "post to Weibo", "发微博", "发布微博", "publish to Weibo", "share on Weibo", "写微博", or "微博头条文章".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-post-to-weibo
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Post to Weibo
@@ -12,9 +20,9 @@ Posts text, images, videos, and long-form articles to Weibo via real Chrome brow
 **Important**: All scripts are located in the `scripts/` subdirectory of this skill.

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
-3. Replace all `${SKILL_DIR}` in this document with the actual path
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
+3. Replace all `{baseDir}` in this document with the actual path
 4. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun

 **Script Reference**:
@@ -32,12 +40,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-post-to-weibo/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-post-to-weibo/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-post-to-weibo/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-post-to-weibo/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-post-to-weibo/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-post-to-weibo/EXTEND.md") { "user" }
 ```

@@ -72,8 +83,8 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-post-to-weibo/EXTEND.md") { "user" }
 Text + images/videos (max 18 files total). Posted on Weibo homepage.

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/weibo-post.ts "Hello Weibo!" --image ./photo.png
-${BUN_X} ${SKILL_DIR}/scripts/weibo-post.ts "Watch this" --video ./clip.mp4
+${BUN_X} {baseDir}/scripts/weibo-post.ts "Hello Weibo!" --image ./photo.png
+${BUN_X} {baseDir}/scripts/weibo-post.ts "Watch this" --video ./clip.mp4
 ```

 **Parameters**:
@@ -93,8 +104,8 @@ ${BUN_X} ${SKILL_DIR}/scripts/weibo-post.ts "Watch this" --video ./clip.mp4
 Long-form Markdown articles published at `https://card.weibo.com/article/v3/editor`.

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/weibo-article.ts article.md
-${BUN_X} ${SKILL_DIR}/scripts/weibo-article.ts article.md --cover ./cover.jpg
+${BUN_X} {baseDir}/scripts/weibo-article.ts article.md
+${BUN_X} {baseDir}/scripts/weibo-article.ts article.md --cover ./cover.jpg
 ```

 **Parameters**:
@@ -446,7 +446,9 @@ Options:
  }
 }

-await main().catch((err) => {
-  console.error(`Error: ${err instanceof Error ? err.message : String(err)}`);
-  process.exit(1);
-});
+if (import.meta.main ?? (process.argv[1] && path.resolve(process.argv[1]) === path.resolve(import.meta.filename ?? ''))) {
+  await main().catch((err) => {
+    console.error(`Error: ${err instanceof Error ? err.message : String(err)}`);
+    process.exit(1);
+  });
+}
@@ -1,6 +1,14 @@
 ---
 name: baoyu-post-to-x
 description: Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-post-to-x
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Post to X (Twitter)
@@ -12,9 +20,9 @@ Posts text, images, videos, and long-form articles to X via real Chrome browser
 **Important**: All scripts are located in the `scripts/` subdirectory of this skill.

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
-3. Replace all `${SKILL_DIR}` in this document with the actual path
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
+3. Replace all `{baseDir}` in this document with the actual path
 4. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun

 **Script Reference**:
@@ -36,12 +44,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-post-to-x/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-post-to-x/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-post-to-x/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-post-to-x/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-post-to-x/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-post-to-x/EXTEND.md") { "user" }
 ```

@@ -74,7 +85,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-post-to-x/EXTEND.md") { "user" }
 Before first use, suggest running the environment check. User can skip if they prefer.

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/check-paste-permissions.ts
+${BUN_X} {baseDir}/scripts/check-paste-permissions.ts
 ```

 Checks: Chrome, profile isolation, Bun, Accessibility, clipboard, paste keystroke, Chrome conflicts.
@@ -107,7 +118,7 @@ Unless the user explicitly specifies the post type:
 ## Regular Posts

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/x-browser.ts "Hello!" --image ./photo.png
+${BUN_X} {baseDir}/scripts/x-browser.ts "Hello!" --image ./photo.png
 ```

 **Parameters**:
@@ -126,7 +137,7 @@ ${BUN_X} ${SKILL_DIR}/scripts/x-browser.ts "Hello!" --image ./photo.png
 Text + video file.

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/x-video.ts "Check this out!" --video ./clip.mp4
+${BUN_X} {baseDir}/scripts/x-video.ts "Check this out!" --video ./clip.mp4
 ```

 **Parameters**:
@@ -147,7 +158,7 @@ ${BUN_X} ${SKILL_DIR}/scripts/x-video.ts "Check this out!" --video ./clip.mp4
 Quote an existing tweet with comment.

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/x-quote.ts https://x.com/user/status/123 "Great insight!"
+${BUN_X} {baseDir}/scripts/x-quote.ts https://x.com/user/status/123 "Great insight!"
 ```

 **Parameters**:
@@ -166,8 +177,8 @@ ${BUN_X} ${SKILL_DIR}/scripts/x-quote.ts https://x.com/user/status/123 "Great in
 Long-form Markdown articles (requires X Premium).

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/x-article.ts article.md
-${BUN_X} ${SKILL_DIR}/scripts/x-article.ts article.md --cover ./cover.jpg
+${BUN_X} {baseDir}/scripts/x-article.ts article.md
+${BUN_X} {baseDir}/scripts/x-article.ts article.md --cover ./cover.jpg
 ```

 **Parameters**:
@@ -12,13 +12,13 @@ Publish Markdown articles to X Articles editor with rich text formatting and ima

 ```bash
 # Publish markdown article (preview mode)
-${BUN_X} ${SKILL_DIR}/scripts/x-article.ts article.md
+${BUN_X} {baseDir}/scripts/x-article.ts article.md

 # With custom cover image
-${BUN_X} ${SKILL_DIR}/scripts/x-article.ts article.md --cover ./cover.jpg
+${BUN_X} {baseDir}/scripts/x-article.ts article.md --cover ./cover.jpg

 # Actually publish
-${BUN_X} ${SKILL_DIR}/scripts/x-article.ts article.md --submit
+${BUN_X} {baseDir}/scripts/x-article.ts article.md --submit
 ```

 ## Markdown Format
@@ -76,13 +76,13 @@ Convert markdown and inspect structure:

 ```bash
 # Get JSON with all metadata
-${BUN_X} ${SKILL_DIR}/scripts/md-to-html.ts article.md
+${BUN_X} {baseDir}/scripts/md-to-html.ts article.md

 # Output HTML only
-${BUN_X} ${SKILL_DIR}/scripts/md-to-html.ts article.md --html-only
+${BUN_X} {baseDir}/scripts/md-to-html.ts article.md --html-only

 # Save HTML to file
-${BUN_X} ${SKILL_DIR}/scripts/md-to-html.ts article.md --save-html /tmp/article.html
+${BUN_X} {baseDir}/scripts/md-to-html.ts article.md --save-html /tmp/article.html
 ```

 JSON output:
@@ -161,7 +161,7 @@ Claude:
 - **No create button**: Ensure X Premium subscription is active
 - **Cover upload fails**: Check file path and format (PNG, JPEG)
 - **Images not inserting**: Verify placeholders exist in pasted content
- **Content not pasting**: Check HTML clipboard: `${BUN_X} ${SKILL_DIR}/scripts/copy-to-clipboard.ts html --file /tmp/test.html`
+- **Content not pasting**: Check HTML clipboard: `${BUN_X} {baseDir}/scripts/copy-to-clipboard.ts html --file /tmp/test.html`

 ## How It Works

@@ -9,20 +9,20 @@ If you prefer step-by-step control:
 ### Step 1: Copy Image to Clipboard

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/copy-to-clipboard.ts image /path/to/image.png
+${BUN_X} {baseDir}/scripts/copy-to-clipboard.ts image /path/to/image.png
 ```

 ### Step 2: Paste from Clipboard

 ```bash
 # Simple paste to frontmost app
-${BUN_X} ${SKILL_DIR}/scripts/paste-from-clipboard.ts
+${BUN_X} {baseDir}/scripts/paste-from-clipboard.ts

 # Paste to Chrome with retries
-${BUN_X} ${SKILL_DIR}/scripts/paste-from-clipboard.ts --app "Google Chrome" --retries 5
+${BUN_X} {baseDir}/scripts/paste-from-clipboard.ts --app "Google Chrome" --retries 5

 # Quick paste with shorter delay
-${BUN_X} ${SKILL_DIR}/scripts/paste-from-clipboard.ts --delay 200
+${BUN_X} {baseDir}/scripts/paste-from-clipboard.ts --delay 200
 ```

 ### Step 3: Use Playwright MCP (if Chrome session available)
@@ -59,7 +59,7 @@ mcp__playwright__browser_take_screenshot filename="preview.png"
 User: /post-to-x "Hello from Claude!" --image ./screenshot.png

 Claude:
-1. Runs: ${BUN_X} ${SKILL_DIR}/scripts/x-browser.ts "Hello from Claude!" --image ./screenshot.png
+1. Runs: ${BUN_X} {baseDir}/scripts/x-browser.ts "Hello from Claude!" --image ./screenshot.png
 2. Chrome opens with X compose page
 3. Text is typed into editor
 4. Image is copied to clipboard and pasted
@@ -72,7 +72,7 @@ Claude:
 - **Chrome not found**: Set `X_BROWSER_CHROME_PATH` environment variable
 - **Not logged in**: First run opens Chrome - log in manually, cookies are saved
 - **Image paste fails**:
-  - Verify clipboard script: `${BUN_X} ${SKILL_DIR}/scripts/copy-to-clipboard.ts image <path>`
+  - Verify clipboard script: `${BUN_X} {baseDir}/scripts/copy-to-clipboard.ts image <path>`
  - On macOS, grant "Accessibility" permission to Terminal/iTerm in System Settings > Privacy & Security > Accessibility
  - Keep Chrome window visible and in front during paste operations
 - **osascript permission denied**: Grant Terminal accessibility permissions in System Preferences
@@ -114,7 +114,6 @@ export async function publishArticle(options: ArticleOptions): Promise<void> {
      `--user-data-dir=${profileDir}`,
      '--no-first-run',
      '--no-default-browser-check',
-      '--disable-blink-features=AutomationControlled',
      '--start-maximized',
      X_ARTICLES_URL,
    ];
@@ -41,7 +41,6 @@ export async function postToX(options: XBrowserOptions): Promise<void> {
    `--user-data-dir=${profileDir}`,
    '--no-first-run',
    '--no-default-browser-check',
-    '--disable-blink-features=AutomationControlled',
    '--start-maximized',
    X_COMPOSE_URL,
  ], { stdio: 'ignore' });
@@ -45,7 +45,6 @@ export async function quotePost(options: QuoteOptions): Promise<void> {
    `--user-data-dir=${profileDir}`,
    '--no-first-run',
    '--no-default-browser-check',
-    '--disable-blink-features=AutomationControlled',
    '--start-maximized',
    tweetUrl,
  ], { stdio: 'ignore' });
@@ -45,7 +45,6 @@ export async function postVideoToX(options: XVideoOptions): Promise<void> {
    `--user-data-dir=${profileDir}`,
    '--no-first-run',
    '--no-default-browser-check',
-    '--disable-blink-features=AutomationControlled',
    '--start-maximized',
    X_COMPOSE_URL,
  ], { stdio: 'ignore' });
@@ -1,6 +1,14 @@
 ---
 name: baoyu-slide-deck
 description: Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-slide-deck
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Slide Deck Generator
@@ -22,8 +30,8 @@ Transform content into professional slide deck images.
 ## Script Directory

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
 3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun

 | Script | Purpose |
@@ -195,12 +203,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-slide-deck/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-slide-deck/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-slide-deck/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-slide-deck/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-slide-deck/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-slide-deck/EXTEND.md") { "user" }
 ```

@@ -555,8 +566,8 @@ options:
 ### Step 8: Merge to PPTX and PDF

 ```bash
-${BUN_X} ${SKILL_DIR}/scripts/merge-to-pptx.ts <slide-deck-dir>
-${BUN_X} ${SKILL_DIR}/scripts/merge-to-pdf.ts <slide-deck-dir>
+${BUN_X} {baseDir}/scripts/merge-to-pptx.ts <slide-deck-dir>
+${BUN_X} {baseDir}/scripts/merge-to-pdf.ts <slide-deck-dir>
 ```

 ### Step 9: Output Summary
@@ -1,6 +1,14 @@
 ---
 name: baoyu-translate
 description: Translates articles and documents between languages with three modes - quick (direct), normal (analyze then translate), and refined (analyze, translate, review, polish). Supports custom glossaries and terminology consistency via EXTEND.md. Use when user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese/English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", or needs any document translation. Also triggers for "refined translation", "精细翻译", "proofread translation", "快速翻译", "快翻", "这篇文章翻译一下", or when a URL or file is provided with translation intent.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-translate
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # Translator
@@ -9,7 +17,7 @@ Three-mode translation skill: **quick** for direct translation, **normal** for a

 ## Script Directory

-Scripts in `scripts/` subdirectory. `${SKILL_DIR}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `${SKILL_DIR}` and `${BUN_X}` with actual values.
+Scripts in `scripts/` subdirectory. `{baseDir}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `{baseDir}` and `${BUN_X}` with actual values.

 | Script | Purpose |
 |--------|---------|
@@ -22,12 +30,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-translate/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-translate/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-translate/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-translate/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-translate/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-translate/EXTEND.md") { "user" }
 ```

@@ -172,12 +183,12 @@ Before translating chunks:

 1. **Extract terminology**: Scan entire document for proper nouns, technical terms, recurring phrases
 2. **Build session glossary**: Merge extracted terms with loaded glossaries, establish consistent translations
-3. **Split into chunks**: Use `${BUN_X} ${SKILL_DIR}/scripts/chunk.ts <file> [--max-words <chunk_max_words>] [--output-dir <output-dir>]`
+3. **Split into chunks**: Use `${BUN_X} {baseDir}/scripts/chunk.ts <file> [--max-words <chunk_max_words>] [--output-dir <output-dir>]`
   - Parses markdown AST (headings, paragraphs, lists, code blocks, tables, etc.)
   - Splits at markdown block boundaries to preserve structure
   - If a single block exceeds the threshold, falls back to line splitting, then word splitting
 4. **Assemble translation prompt**:
-   - Main agent reads `01-analysis.md` (if exists) and assembles shared context using Part 1 of [references/subagent-prompt-template.md](references/subagent-prompt-template.md) — inlining content background, merged glossary, and comprehension challenges
+   - Main agent reads `01-analysis.md` (if exists) and assembles shared context using Part 1 of [references/subagent-prompt-template.md](references/subagent-prompt-template.md) — inlining the resolved style preset (from `--style` flag, EXTEND.md `style` setting, or default `storytelling`), content background, merged glossary, and comprehension challenges
   - Save as `02-prompt.md` in the output directory (shared context only, no task instructions)
 5. **Draft translation via subagents** (if Agent tool available):
   - Spawn one subagent **per chunk**, all in parallel (Part 2 of the template)
@@ -201,9 +212,10 @@ Before translating chunks:
 - **Natural flow**: Use idiomatic target language word order and sentence patterns; break or restructure sentences freely when the source structure doesn't work naturally in the target language
 - **Terminology**: Use standard translations; annotate with original term in parentheses on first occurrence
 - **Preserve format**: Keep all markdown formatting (headings, bold, italic, images, links, code blocks)
+- **Image-language awareness**: Preserve image references exactly during translation, but after the translation is complete, review referenced images and check whether their likely main text language still matches the translated article language
 - **Frontmatter transformation**: If the source has YAML frontmatter, preserve it in the translation with these changes: (1) Rename metadata fields that describe the *source* article — `url`→`sourceUrl`, `title`→`sourceTitle`, `description`→`sourceDescription`, `author`→`sourceAuthor`, `date`→`sourceDate`, and any similar origin-metadata fields — by adding a `source` prefix (camelCase). (2) Translate the values of text fields (title, description, etc.) and add them as new top-level fields. (3) Keep other fields (tags, categories, custom fields) as-is, translating their values where appropriate
 - **Respect original**: Maintain original meaning and intent; do not add, remove, or editorialize — but sentence structure and imagery may be adapted freely to serve the meaning
- **Translator's notes**: For terms, concepts, or cultural references that target readers may not understand — due to jargon, cultural gaps, or domain-specific knowledge — add a concise explanatory note in parentheses immediately after the term. The note should explain *what it means* in plain language, not just provide the English original. Format: `译文（English original，通俗解释）`. Calibrate annotation depth to the target audience: general readers need more notes than technical readers. Only add notes where genuinely needed; do not over-annotate obvious terms.
+- **Translator's notes**: For terms, concepts, or cultural references that target readers may not understand — due to jargon, cultural gaps, or domain-specific knowledge — add a concise explanatory note in parentheses immediately after the term. The note should explain *what it means* in plain language, not just provide the English original. Format: `译文（English original，通俗解释）`. Calibrate annotation depth to the target audience: general readers need more notes than technical readers. For short texts (< 5 sentences), further reduce annotations — only annotate non-common terms that the target audience is unlikely to know; skip terms that are widely recognized or self-explanatory in context. Only add notes where genuinely needed; do not over-annotate obvious terms.

 #### Quick Mode

@@ -212,7 +224,7 @@ Translate directly → save to `translation.md`. No analysis file, but still app
 #### Normal Mode

 1. **Analyze** → `01-analysis.md` (domain, tone, audience, terminology, reader comprehension challenges, figurative language & metaphor mapping)
-2. **Assemble prompt** → `02-prompt.md` (translation instructions with inlined context)
+2. **Assemble prompt** → `02-prompt.md` (translation instructions with inlined style preset, content background, glossary, and comprehension challenges)
 3. **Translate** (following `02-prompt.md`) → `translation.md`

 After completion, prompt user: "Translation saved. To further review and polish, reply **继续润色** or **refine**."
@@ -239,6 +251,20 @@ Each step reads the previous step's file and builds on it.

 Final translation is always at `translation.md` in the output directory.

+After the final translation is written, do a lightweight image-language pass:
+
+1. Collect image references from the translated article
+2. Identify likely text-heavy images such as covers, screenshots, diagrams, charts, frameworks, and infographics
+3. If any image likely contains a main text language that does not match the translated article language, proactively remind the user
+4. The reminder must be a list only. Do not automatically localize those images unless the user asks
+
+Reminder format (use whatever image syntax the article already uses — standard markdown or wikilink):
+```text
+Possible image localization needed:
+- ![example cover](attachments/example-cover.png): likely still contains source-language text while the article is now in target language
+- ![example diagram](attachments/example-diagram.png): likely text-heavy framework graphic, check whether labels need translation
+```
+
 Display summary:
 ```
 **Translation complete** ({mode} mode)
@@ -250,6 +276,8 @@ Final: {output-dir}/translation.md
 Glossary terms applied: {count}
 ```

+If mismatched image-language candidates were found, append a short note after the summary telling the user that some embedded images may still need image-text localization, followed by the candidate list.
+
 ## Extension Support

 Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.
@@ -121,7 +121,7 @@ Implicit assumptions: [unstated premises]

 ## Step 2: Assemble Translation Prompt

-Main agent reads `01-analysis.md` and assembles a complete translation prompt using [references/subagent-prompt-template.md](subagent-prompt-template.md). Inline content background, merged glossary, and comprehension challenges into the prompt. Save to `02-prompt.md`.
+Main agent reads `01-analysis.md` and assembles a complete translation prompt using [references/subagent-prompt-template.md](subagent-prompt-template.md). Inline the resolved style preset (from `--style` flag, EXTEND.md `style` setting, or default `storytelling`), content background, merged glossary, and comprehension challenges into the prompt. Save to `02-prompt.md`.

 This prompt is used by the subagent (chunked) or by the main agent itself (non-chunked).

@@ -1,6 +1,14 @@
 ---
 name: baoyu-url-to-markdown
 description: Fetch any URL and convert to markdown using Chrome CDP. Saves the rendered HTML snapshot alongside the markdown, and automatically falls back to the pre-Defuddle HTML-to-Markdown pipeline when Defuddle fails. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-url-to-markdown
+    requires:
+      anyBins:
+        - bun
+        - npx
 ---

 # URL to Markdown
@@ -12,10 +20,10 @@ Fetches any URL via Chrome CDP, saves the rendered HTML snapshot, and converts i
 **Important**: All scripts are located in the `scripts/` subdirectory of this skill.

 **Agent Execution Instructions**:
-1. Determine this SKILL.md file's directory path as `SKILL_DIR`
-2. Script path = `${SKILL_DIR}/scripts/<script-name>.ts`
+1. Determine this SKILL.md file's directory path as `{baseDir}`
+2. Script path = `{baseDir}/scripts/<script-name>.ts`
 3. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun
-4. Replace all `${SKILL_DIR}` and `${BUN_X}` in this document with actual values
+4. Replace all `{baseDir}` and `${BUN_X}` in this document with actual values

 **Script Reference**:
 | Script | Purpose |
@@ -30,12 +38,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-url-to-markdown/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-url-to-markdown/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-url-to-markdown/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-url-to-markdown/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-url-to-markdown/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-url-to-markdown/EXTEND.md") { "user" }
 ```

@@ -112,19 +123,19 @@ Full reference: [references/config/first-time-setup.md](references/config/first-

 ```bash
 # Auto mode (default) - capture when page loads
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url>
+${BUN_X} {baseDir}/scripts/main.ts <url>

 # Wait mode - wait for user signal before capture
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> --wait
+${BUN_X} {baseDir}/scripts/main.ts <url> --wait

 # Save to specific file
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> -o output.md
+${BUN_X} {baseDir}/scripts/main.ts <url> -o output.md

 # Save to a custom output directory (auto-generates filename)
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> --output-dir ./posts/
+${BUN_X} {baseDir}/scripts/main.ts <url> --output-dir ./posts/

 # Download images and videos to local directories
-${BUN_X} ${SKILL_DIR}/scripts/main.ts <url> --download-media
+${BUN_X} {baseDir}/scripts/main.ts <url> --download-media
 ```

 ## Options
@@ -1,6 +1,10 @@
 ---
 name: baoyu-xhs-images
 description: Generates Xiaohongshu (Little Red Book) infographic series with 11 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
+version: 1.56.1
+metadata:
+  openclaw:
+    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-xhs-images
 ---

 # Xiaohongshu Infographic Series Generator
@@ -274,12 +278,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-xhs-images/EXTEND.md && echo "project"
+test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-xhs-images/EXTEND.md" && echo "xdg"
 test -f "$HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md" && echo "user"
 ```

 ```powershell
 # PowerShell (Windows)
 if (Test-Path .baoyu-skills/baoyu-xhs-images/EXTEND.md) { "project" }
+$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
+if (Test-Path "$xdg/baoyu-skills/baoyu-xhs-images/EXTEND.md") { "xdg" }
 if (Test-Path "$HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md") { "user" }
 ```

@@ -211,13 +211,9 @@ If preferences include watermark:
 When generating multiple images in a series:

 1. **Image 1 (cover)**: Generate without `--ref` — this establishes the visual anchor
-2. **Images 2+**: Always pass image 1 as `--ref` to the image generation skill:
-   ```bash
-   ${BUN_X} ${SKILL_DIR}/scripts/main.ts \
-     --promptfiles prompts/02-content-xxx.md \
-     --ref path/to/01-cover-xxx.png \
-     --image 02-content-xxx.png --ar 3:4 --quality 2k
-   ```
+2. **Images 2+**: Always pass image 1 as `--ref` to the installed image generation skill.
+   Read that skill's `SKILL.md` and use its documented interface rather than calling its scripts directly.
+   For each later image, use the assembled prompt file as input, set the output image path, keep aspect ratio `3:4`, use quality `2k`, and pass image 1 as the reference.
   This ensures the AI maintains the same character design, illustration style, and color rendering across the series.

 ### Step 6: Combine
Author	SHA1	Message	Date
Jim Liu 宝玉	1cb54420e0	chore: release v1.59.1	2026-03-11 17:08:33 -05:00
Jim Liu 宝玉	6363bd83e2	refactor(scripts): replace clawhub CLI with local sync-clawhub.mjs	2026-03-11 16:45:57 -05:00
Jim Liu 宝玉	7b8247544d	refactor(baoyu-post-to-weibo): add entry point guard to md-to-html.ts	2026-03-11 16:45:56 -05:00
Jim Liu 宝玉	a9576ebc67	fix(baoyu-post-to-x): remove disable-blink-features Chrome flag	2026-03-11 16:45:55 -05:00
Jim Liu 宝玉	79ca378229	fix(baoyu-translate): improve annotation density and style preset passing - Add short text (<5 sentences) annotation reduction rule to translator's notes - Explicitly pass resolved style preset to 02-prompt.md assembly in all modes	2026-03-11 16:45:51 -05:00
Jim Liu 宝玉	e1a1fe23cb	Merge pull request #77 from jackL1020/claude/claude-md-mmlh0po6953zhhbf-D8rFo docs: Update CLAUDE.md with v1.59.0 features and skill registry	2026-03-11 13:40:27 -05:00
Claude	3d85a7e663	docs: fix marketplace.json path (it's in .claude-plugin/, not root) https://claude.ai/code/session_01DREj1A7KKhNVE1RXjmg9ZH	2026-03-11 03:28:56 +00:00
Claude	10aabb39f8	docs: update CLAUDE.md to reflect v1.59.0 codebase state - Add 8 missing skills to architecture tree (baoyu-post-to-weibo, baoyu-infographic, baoyu-image-gen, baoyu-url-to-markdown, baoyu-format-markdown, baoyu-markdown-to-html, baoyu-translate) - Fix marketplace.json path (root, not .claude-plugin/) - Rename SKILL_DIR → baseDir in Script Directory template (v1.57.0 change) - Add ClawHub/OpenClaw publishing section with sync-clawhub.sh usage - Add openclaw frontmatter template and requirement for new skills - Document baoyu-image-gen batch parallel generation capability - Update Project Overview to mention all AI providers - Expand Key Dependencies and Choosing a Category tables - Add image-gen API key requirement note https://claude.ai/code/session_01DREj1A7KKhNVE1RXjmg9ZH	2026-03-11 03:28:14 +00:00
Jim Liu 宝玉	661c74cce4	docs: add contributor credit to v1.59.0 changelog	2026-03-09 00:58:14 -05:00
Jim Liu 宝玉	82445f2a39	chore: release v1.59.0	2026-03-09 00:55:52 -05:00
Jim Liu 宝玉	df9ce95c46	fix: restore Google as default provider when multiple keys available EXTEND.md default_provider still takes priority over auto-detect. Priority: CLI --provider > EXTEND.md default_provider > auto-detect (Google first).	2026-03-09 00:52:53 -05:00
Jim Liu 宝玉	88b433d565	docs: improve skill documentation clarity - Fix Provider Selection: default to Replicate when multiple keys available (matches code) - Add Replicate column to Quality Presets table (normal→1K, 2k→2K) - Add Replicate aspect ratio behavior (match_input_image when --ref without --ar) - Remove stale Google Imagen reference from Aspect Ratios - Add batch file format example with JSON schema to SKILL.md - Note that batch paths resolve relative to batch file directory - Move batch execution strategy in article-illustrator before numbered steps - Fix translate image-language reminder to use standard markdown syntax with note to match article's own image syntax convention	2026-03-09 00:43:05 -05:00
Jim Liu 宝玉	5acef7151b	feat: add batch parallel image generation and provider-level throttling - Add --batchfile and --jobs flags for multi-image parallel generation with per-provider concurrency control and rate limiting - Refactor main.ts into prepareSingleTask/prepareBatchTasks/runBatchTasks with worker pool pattern and up to 3 retries per image - Fix Replicate provider: use image_input array (nano-banana-pro schema), add match_input_image aspect ratio, add quality-to-resolution mapping - Improve OpenAI error message for missing API key (Codex auth hint) - Expand non-retryable error detection (4xx codes, disabled models) - Add batch config to EXTEND.md schema (max_workers, provider_limits) - Add build-batch.ts for article-illustrator batch workflow integration - Add image-language awareness pass to baoyu-translate Co-authored-by: 敖氏 <aoshi@MacBook-Air.local>	2026-03-09 00:07:45 -05:00
Jim Liu 宝玉	e4d4ec8334	chore: release v1.58.0	2026-03-08 22:30:46 -05:00
Jim Liu 宝玉	4935dc8b1a	fix: surface agent-browser startup errors	2026-03-08 22:25:34 -05:00
Jim Liu 宝玉	c43ed57ffc	Merge pull request #69 from liby/feat/xdg-config-path feat: add XDG config path support for EXTEND.md	2026-03-08 22:19:52 -05:00
Jim Liu 宝玉	d96368492e	Merge pull request #66 from luojiyin1987/fix/harden-command-exec-and-js-escaping fix: harden command execution and JS literal escaping	2026-03-08 22:10:45 -05:00
Jim Liu 宝玉	cfc647fd38	Merge pull request #68 from luojiyin1987/docs/sync-readme-and-claude-deps docs: sync README utility skills and CLAUDE dependency notes	2026-03-08 22:04:40 -05:00
Jim Liu 宝玉	5144335916	chore: release v1.57.0	2026-03-08 19:24:45 -05:00
Jim Liu 宝玉	fa82c3d910	refactor(baoyu-xhs-images): use skill interface instead of direct script invocation for image generation	2026-03-08 19:24:03 -05:00
Jim Liu 宝玉	90730bc551	refactor(baoyu-comic): use skill interface instead of direct script invocation for image generation	2026-03-08 19:24:02 -05:00
Jim Liu 宝玉	154ccfe3ff	refactor: add openclaw metadata and rename SKILL_DIR to baseDir across all skills	2026-03-08 19:22:24 -05:00
Jim Liu 宝玉	93efa5aeb1	refactor(baoyu-comic): add openclaw metadata, baseDir rename, and decouple image skill path	2026-03-08 19:22:19 -05:00
Jim Liu 宝玉	40ccbed74a	refactor(baoyu-danger-x-to-markdown): add openclaw metadata, baseDir rename, and dynamic script path	2026-03-08 19:22:18 -05:00
Jim Liu 宝玉	fbf2bc02c5	refactor(baoyu-danger-gemini-web): add openclaw metadata, baseDir rename, and dynamic script path	2026-03-08 19:22:18 -05:00
Jim Liu 宝玉	a37c80e142	feat: add ClawHub/OpenClaw publishing support	2026-03-08 19:22:13 -05:00
Bryan Lee	a702513487	feat: add XDG config path support for EXTEND.md Add $XDG_CONFIG_HOME/baoyu-skills/<skill>/EXTEND.md as second priority path between project-level and legacy $HOME/.baoyu-skills/ paths. Priority order: 1. .baoyu-skills/<skill>/EXTEND.md (project) 2. $XDG_CONFIG_HOME/baoyu-skills/<skill>/EXTEND.md (XDG, new) 3. $HOME/.baoyu-skills/<skill>/EXTEND.md (legacy fallback) Updated: CLAUDE.md template, 16 SKILL.md files, 2 workflow.md references, and 2 extend-config.ts runtime loaders.	2026-03-09 04:54:26 +08:00
luojiyin	6b2b28b421	docs: fix CLAUDE dependency statement	2026-03-08 21:21:54 +08:00
luojiyin	0df63c3a0b	docs: add markdown-to-html to README.zh utility skills	2026-03-08 21:21:54 +08:00
luojiyin	7834d632e0	docs: add markdown-to-html to README utility skills	2026-03-08 21:21:47 +08:00
luojiyin	ca9a0a1404	fix: harden wechat agent-browser command and eval handling	2026-03-08 20:34:43 +08:00
luojiyin	366e7b5403	fix: use execFileSync for google curl requests	2026-03-08 20:34:39 +08:00
luojiyin	709e026be1	fix: use spawnSync for autocorrect command	2026-03-08 20:34:35 +08:00