Publish Markdown/HTML articles to WeChat Official Account (微信公众号) drafts via API
npx skills add https://github.com/iamzifei/wechat-article-publisher-skill --skill wechat-article-publisher
Publish Markdown or HTML content to WeChat Official Account drafts via API, with automatic format conversion.
Located in ~/.claude/skills/wechat-article-publisher/scripts/:
WeChat API client for listing accounts and publishing articles:
# List authorized accounts
python wechat_api.py list-accounts
# Publish from markdown file
python wechat_api.py publish --appid <wechat_appid> --markdown /path/to/article.md
# Publish from HTML file (preserves formatting)
python wechat_api.py publish --appid <wechat_appid> --html /path/to/article.html
# Publish with custom options
python wechat_api.py publish --appid <appid> --markdown /path/to/article.md --type newspic
Parse Markdown and extract structured data (optional, for advanced use):
python parse_markdown.py <markdown_file> [--output json|html]
Strategy: "API-First Publishing"
Unlike browser-based publishing, this skill uses direct API calls for reliable, fast publishing.
Supported File Formats:
.md files → Parsed as Markdown, converted by WeChat API.html files → Sent as HTML, formatting preservedBefore any operation, verify the API key is available:
# Check if .env file exists and contains WECHAT_API_KEY
cat .env | grep WECHAT_API_KEY
If not set, remind user to:
.env.example to .envWECHAT_API_KEY valueGet the list of authorized WeChat accounts:
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py list-accounts
Output example:
{
"success": true,
"data": {
"accounts": [
{
"name": "我的公众号",
"wechatAppid": "wx1234567890",
"username": "gh_abc123",
"type": "subscription",
"verified": true,
"status": "active"
}
],
"total": 1
}
}
Important:
wechatAppid for publishingFor Markdown files:
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py publish \
--appid <wechatAppid> \
--markdown /path/to/article.md
For HTML files (preserves formatting):
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py publish \
--appid <wechatAppid> \
--html /path/to/article.html
For 小绿书 (image-text mode):
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py publish \
--appid <wechatAppid> \
--markdown /path/to/article.md \
--type newspic
Success response:
{
"success": true,
"data": {
"publicationId": "uuid-here",
"materialId": "uuid-here",
"mediaId": "wechat-media-id",
"status": "published",
"message": "文章已成功发布到公众号草稿箱"
}
}
After successful publishing:
All API requests require the X-API-Key header:
X-API-Key: WECHAT_API_KEY
POST https://wx.limyai.com/api/openapi/wechat-accounts
POST https://wx.limyai.com/api/openapi/wechat-publish
Parameters:
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| wechatAppid | string | Yes | WeChat AppID |
| title | string | Yes | Article title (max 64 chars) |
| content | string | Yes | Article content (Markdown/HTML) |
| summary | string | No | Article summary (max 120 chars) |
| coverImage | string | No | Cover image URL |
| author | string | No | Author name |
| contentFormat | string | No | 'markdown' (default) or 'html' |
| articleType | string | No | 'news' (default) or 'newspic' |
| Code | Description |
|------|-------------|
| API_KEY_MISSING | API key not provided |
| API_KEY_INVALID | API key invalid |
| ACCOUNT_NOT_FOUND | Account not found or unauthorized |
| ACCOUNT_TOKEN_EXPIRED | Account authorization expired |
| INVALID_PARAMETER | Invalid parameter |
| WECHAT_API_ERROR | WeChat API call failed |
| INTERNAL_ERROR | Server error |
... )<title> or <h1> → Article title<img> tags → Images auto-uploaded to WeChat<p> → Auto-extracted as summaryHTML Title Extraction Priority:
<title> tag content<h1> tag contentHTML Content Extraction:
<body> exists, uses body content<html>, <head>, <!DOCTYPE> and uses remaining contentUser: "把 ~/articles/ai-tools.md 发布到微信公众号"
# Step 1: Verify API key
cat .env | grep WECHAT_API_KEY
# Step 2: List accounts
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py list-accounts
# Step 3: Publish (assuming single account with appid wx1234567890)
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py publish \
--appid wx1234567890 \
--markdown ~/articles/ai-tools.md
# Step 4: Report
# "文章已成功发布到公众号草稿箱!请登录微信公众平台预览并发布。"
User: "把这个HTML文章发布到公众号:~/articles/newsletter.html"
# Step 1: Verify API key
cat .env | grep WECHAT_API_KEY
# Step 2: List accounts
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py list-accounts
# Step 3: Publish HTML (auto-detects format)
python ~/.claude/skills/wechat-article-publisher/scripts/wechat_api.py publish \
--appid wx1234567890 \
--html ~/articles/newsletter.html
# Step 4: Report
# "文章已成功发布到公众号草稿箱!HTML格式已保留。请登录微信公众平台预览并发布。"
Error: WECHAT_API_KEY environment variable not set.
Solution: Ask user to set up .env file with their API key.
Error: ACCOUNT_NOT_FOUND - 公众号不存在或未授权
Solution: Ask user to authorize their account on wx.limyai.com.
Error: ACCOUNT_TOKEN_EXPIRED - 公众号授权已过期
Solution: Ask user to re-authorize on wx.limyai.com.
Error: WECHAT_API_ERROR - 微信接口调用失败
Solution: May be temporary issue, retry or check WeChat service status.
Minimal workflow (1 command):
- list-accounts → get appid → publish → done
Full workflow (with verification):
1. Check .env → list accounts → confirm with user
2. Publish with options → report result
A: Register and authorize your WeChat account at wx.limyai.com to get your API key.
A: Yes, use list-accounts to see all authorized accounts, then specify the target --appid.
A: Ensure images are accessible URLs. Local images are auto-uploaded but may fail if path is incorrect.
A: WeChat limits titles to 64 characters. The script will use the first 64 chars of H1.
A: news is standard article format; newspic (小绿书) is image-focused with limited text.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take iamzifei/wechat-article-publisher from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.