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
2026-07-13 22:29:48 +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
43 changed files with 1822 additions and 253 deletions
@@ -6,7 +6,7 @@
  },
  "metadata": {
    "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.57.0"
+    "version": "1.59.1"
  },
  "plugins": [
    {
@@ -2,6 +2,45 @@

 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
@@ -2,6 +2,45 @@

 [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
@@ -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
@@ -76,7 +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

@@ -798,6 +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).
@@ -76,7 +76,7 @@ clawhub install baoyu-markdown-to-html
 |------|------|----------|
 | **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

@@ -798,6 +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);
+});
@@ -4,13 +4,8 @@ set -euo pipefail
 ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 SKILLS_DIR="${ROOT_DIR}/skills"

-if command -v clawhub >/dev/null 2>&1; then
-  CLAWHUB_CMD=(clawhub)
-elif command -v npx >/dev/null 2>&1; then
-  CLAWHUB_CMD=(npx -y clawhub)
-else
-  echo "Error: neither clawhub nor npx is available."
-  echo "See https://docs.openclaw.ai/zh-CN/tools/clawhub"
+if ! command -v node >/dev/null 2>&1; then
+  echo "Error: node is required."
  exit 1
 fi

@@ -18,4 +13,4 @@ if [ "$#" -eq 0 ]; then
  set -- --all
 fi

-exec "${CLAWHUB_CMD[@]}" sync --root "${SKILLS_DIR}" "$@"
+exec node "${ROOT_DIR}/scripts/sync-clawhub.mjs" --root "${SKILLS_DIR}" "$@"
@@ -55,12 +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" }
 ```

@@ -115,6 +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);
+});
@@ -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" }
 ```

@@ -30,12 +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" }
 ```

@@ -134,12 +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" }
 ```

@@ -57,12 +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" }
 ```

@@ -83,12 +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" }
 ```

@@ -34,12 +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" }
 ```

@@ -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 "${filePath}"`, { stdio: "inherit" });
-    return true;
-  } catch {
-    return false;
-  }
+  const npxCmd = process.platform === "win32" ? "npx.cmd" : "npx";
+  const result = spawnSync(npxCmd, ["autocorrect-node", "--fix", filePath], {
+    stdio: "inherit",
+  });
+  return result.status === 0;
 }
@@ -1,6 +1,6 @@
 ---
 name: baoyu-image-gen
-description: AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.
+description: AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
 version: 1.56.1
 metadata:
  openclaw:
@@ -31,12 +31,15 @@ Check EXTEND.md existence (priority: project → user):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-image-gen/EXTEND.md && echo "project"
+test -f "${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" }
 ```

@@ -52,7 +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`

@@ -88,22 +91,57 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r

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

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

 | Option | Description |
 |--------|-------------|
 | `--prompt <text>`, `-p` | Prompt text |
 | `--promptfiles <files...>` | Read prompt from files (concatenated) |
-| `--image <path>` | Output image path (required) |
-| `--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 |

@@ -123,6 +161,9 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 | `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`

@@ -167,10 +208,10 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r

 ## 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`

@@ -179,41 +220,48 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 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;
+        }
+      >
+    >;
+  };
 };
@@ -147,12 +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" }
 ```

@@ -30,12 +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" }
 ```

@@ -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) {
@@ -36,12 +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" }
 ```

@@ -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.');
  }
@@ -40,12 +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" }
 ```

@@ -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: ${err instanceof Error ? err.message : String(err)}`);
+    process.exit(1);
+  });
+}
@@ -44,12 +44,15 @@ Check EXTEND.md existence (priority order):
 ```bash
 # macOS, Linux, WSL, Git Bash
 test -f .baoyu-skills/baoyu-post-to-x/EXTEND.md && echo "project"
+test -f "${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" }
 ```

@@ -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' });
@@ -203,12 +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" }
 ```

@@ -30,12 +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" }
 ```

@@ -185,7 +188,7 @@ Before translating chunks:
   - 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)
@@ -209,9 +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

@@ -220,7 +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**."
@@ -247,6 +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)
@@ -258,6 +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).

@@ -38,12 +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" }
 ```

@@ -278,12 +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" }
 ```
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
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