WeChat Article Search skill
A skill that searches WeChat public-account articles by keyword through Sogou and returns titles, links and dates as JSON
- 277 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- The Node.js script goes to the network and parses Sogou search pages, which may breach the service's rules
- With frequent requests the IP address may be temporarily blocked
- The `-o` flag writes a file to the given path
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/wechat-article-searchDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The Node.js script goes to the network and parses Sogou search pages, which may breach the service's rules
- With frequent requests the IP address may be temporarily blocked
- The `-o` flag writes a file to the given path
This is third-party code. Review the repository files before installing.
What it does
The `wechat-article-search` skill runs one Node.js script, `scripts/search_wechat.js`. The script requests the WeChat article search page on `weixin.sogou.com`, parses the HTML with `cheerio` and prints structured JSON. For each article it returns the title, link, summary, publish date with a text date and relative time, and the name of the source public account. A query returns 1 to 50 articles, 10 by default. The `-n` flag sets the count, `-o` writes the result to a file, and `-r` tries to replace Sogou's intermediate links with direct `mp.weixin.qq.com` addresses. A link does not always resolve; then the Sogou address stays and the record carries `url_resolved: false`. No API key is needed, there are no MCP tools and no platform coupling: the skill works in any agent that can run `node`. A typical request to the agent is to find articles on a topic and return 10. It helps when you know the topic but not which public account wrote about it.
Who it is for. For researchers, editors and marketers who need to find Chinese articles on a topic quickly and learn which public accounts write about it.
Good fit when
- You need ten recent WeChat articles for a keyword, for example on AI training
- You know the topic but not which public accounts write about it
- Search results should be saved to `result.json` for further processing
- You need direct `mp.weixin.qq.com` links and accept that some will not resolve
- The agent needs a search over Chinese publications with no API key and no MCP server
Not a fit when
- You need bulk commercial scraping: the author allows only study and research use, and heavy use may get the IP blocked
- You need to read the full text of articles: the skill returns the title and summary
- You need dependable output without retries: Sogou's anti-bot protection sometimes returns empty results
- You need to publish to a WeChat account: the skill only searches
Example request
Find 5 recent WeChat articles about "AI培训" and save the result to result.jsonLimitations
You need Node.js 18 or newer, tested on Node 20. After installing the skill run `npm install` in its folder to pull the single dependency, `cheerio`.
Data comes from Sogou's public search, which has anti-bot protection. Results sometimes come back empty; then try another keyword or wait. Resolving direct links with `-r` does not always work: that is normal, and on failure the Sogou link stays. Too many requests can lead to a temporary IP block.
The repository is generated automatically as a compatibility mirror. Edits and discussion happen in the main `zhijian-skills` repository. A Chinese README is available too.
How to disable. Delete the `wechat-article-search` skill folder from the agent's skills directory. Saved result files such as `result.json` sit wherever you pointed the `-o` flag.
FAQ
How do I install the WeChat search skill in Codex?
Run `npx skills add zjp1997720/wechat-article-search -g -a codex --skill wechat-article-search -y`. Then go to the skill folder and run `npm install`: the single dependency `cheerio` is not in the package yet.
Where does the skill get articles?
From Sogou's WeChat search on `weixin.sogou.com`. The script parses the results page and uses neither an official API nor keys.
What does the `-r` flag do?
It tries to turn Sogou links into direct `mp.weixin.qq.com` addresses, making an extra request per result. Because of anti-scraper protection this succeeds irregularly. If it fails, the Sogou link stays and the record carries `url_resolved: false`.
Can I save the result to a file?
Yes, `node scripts/search_wechat.js "keyword" -n 20 -o result.json` writes JSON with twenty articles to `result.json`.
What is the skill allowed to be used for?
The author states study and research purposes and asks not to use it for bulk commercial scraping, since the IP may be blocked.
Discussion
No questions or reviews yet.
Related
SkillsThe news-extractor skill pulls the title, text, images and metadata from a link on 12 news platforms and returns JSON or Markdown, with no browser
A skill that reads a link and hands the agent the full text as Markdown, picking a separate route for WeChat pages, Feishu docs, PDFs and arXiv papers
A skill that routes a question to the right AI platform and, via browser automation, collects the answer from its native search
A skill that gathers 30 days of discussion on eight Chinese platforms, ranks it and writes a cited report, and can also show the cross-platform hot lists
A skill for web search, X search and page fetching for models without web access: no signup or key, the answer is JSON with source links
A web search skill with no MCP server: four command-line clients search the web and 16 vertical domains, in batches and with page extraction
Comparison with similar tools
Entries that share the main search query, and how they differ.
README in short
The opening note says the repository is a mirror of the main source; the rest shows installation, requirements, features and how the script works. It follows with example requests, a flag table, a limits section and the folder layout.
README badge
Original SKILL.md
---
name: wechat-article-search
description: "搜索微信公众号文章技能。通过微信搜索获取文章列表，覆盖科技/AI、社会热点、财经、教育、职场等各类中文资讯；可按关键词检索并返回标题、概要、发布时间、来源公众号与链接。当用户需要查找微信公众号文章、整理参考资料或快速获取文章信息时使用此技能。"
description_zh: "搜索微信公众号文章（标题、摘要、发布时间、来源账号、链接）"
description_en: "Search WeChat public account articles by keyword"
version: 0.1.0
allowed-tools: Bash,Read
metadata:
clawdbot:
emoji: "\U0001F50E"
requires:
bins:
- node
display_name: "wechat-article-search"
display_name_en: "wechat-article-search"
visibility: "public"
---
# 微信公众号文章搜索说明
## 适用场景
- 用户说“帮我搜某个关键词的公众号文章/最近文章”
- 需要快速拿到：标题、摘要、发布时间、公众号名称、可访问链接
## 工作流程
### 步骤1: 确认已安装依赖包
该脚本依赖NodeJS依赖包 `cheerio`，建议先执行全局安装或在项目中安装：
```bash
npm install -g cheerio
```
### 步骤2: 确认搜索词语数量
1、 确认关键词与数量
### 步骤3: 执行搜索命令
1、执行常规搜索命令
```bash
node scripts/search_wechat.js "关键词"
```
## 特殊流程（可选）
1) 执行包含数量限制的搜索命令
```bash
node scripts/search_wechat.js "关键词" -n 15
```