{
  "markdown": "> [!IMPORTANT]\n> This repository is a generated compatibility mirror. The editable source, Issues, and contributions live in [zjp1997720/zhijian-skills](https://github.com/zjp1997720/zhijian-skills/tree/main/skills/wechat-article-search).\n\n# WeChat Article Search\n\n<p align=\"center\">\n  <img src=\"./assets/readme/hero.svg\" width=\"100%\" alt=\"WeChat Article Search turns a keyword into structured public-account article results\">\n</p>\n\n<p align=\"center\"><strong>Search WeChat public-account articles by keyword and return structured evidence without an API key.</strong></p>\n\n<p align=\"center\"><a href=\"./README.zh-CN.md\">简体中文</a> · <a href=\"https://github.com/zjp1997720/zhijian-skills/tree/main/skills/wechat-article-search\">Canonical source</a> · <a href=\"https://github.com/zjp1997720/wechat-article-search\">Standalone mirror</a></p>\n\nUse it for topic discovery when you know the keyword but not which WeChat public account published the useful article.\n\n## Agent Install\n\n```bash\nnpx skills add zjp1997720/wechat-article-search -g -a codex --skill wechat-article-search -y\n```\n\n## Requirements\n\n- Node.js 18+ (tested on Node 20)\n- One npm dependency: `cheerio`. Run `npm install` inside the skill folder after install.\n\n## What It Does\n\n- **Keyword search** across WeChat public accounts via Sogou WeChat Search — returns 1–50 articles per query.\n- **Structured output**: title, URL, summary, publish datetime, date text, relative time, source account name.\n- **Optional real-URL resolution** (`-r`): converts Sogou redirect links into `mp.weixin.qq.com` direct links when reachable.\n- **Optional file output** (`-o`): writes JSON to disk for archival.\n\n## How It Works\n\nThe skill drives a single self-contained Node.js script (`scripts/search_wechat.js`) that queries Sogou WeChat Search (`weixin.sogou.com`), parses the result HTML with `cheerio`, and emits structured JSON to stdout. No API keys, no MCP tools, no platform coupling — it works in any agent runtime that can run `node`.\n\n## Example Requests\n\n```\nSearch WeChat articles about \"Loop Engineering\", give me 10.\n```\n\n```\n搜一下\"AI培训\"相关的公众号文章，要 5 条，保存到 result.json。\n```\n\n## CLI Usage\n\n```bash\nnode scripts/search_wechat.js \"<keyword>\" [-n <count>] [-o <output.json>] [-r]\n```\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `query` | required | Search keyword |\n| `-n, --num` | 10 | Number of results (max 50) |\n| `-o, --output` | stdout | Write JSON to a file |\n| `-r, --resolve-url` | off | Resolve real `mp.weixin.qq.com` URLs (slower, may fail under anti-bot) |\n\nFirst run: `npm install` in the skill folder to pull `cheerio`.\n\n## Safety & Limits\n\n- Uses public Sogou WeChat Search as the data source. Anti-bot rate limiting can intermittently return empty results or block URL resolution — retry with a different keyword or wait.\n- `-r` URL resolution succeeds inconsistently under Sogou's anti-spider policy. Failures keep the Sogou redirect link and set `url_resolved: false`.\n- For study and research only. Do not use for large-scale commercial crawling. Excessive use may get your IP temporarily blocked.\n\n## Repository Layout\n\n```text\n.\n├── README.md\n├── README.zh-CN.md\n├── assets/readme/hero.svg\n├── LICENSE\n└── skills/wechat-article-search/\n    ├── SKILL.md\n    ├── agents/openai.yaml\n    ├── package.json\n    └── scripts/search_wechat.js\n```\n\n## License\n\nMIT\n",
  "bytes": 3355,
  "sha": "d10fad29ff6c7505505d7c3e017b994124c26198c76dad401d64f9c7d7651377",
  "repo_slug": "zjp1997720/wechat-article-search",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_zjp1997720_wechat_article_search_wechat__ac40d331/readme"
}