From agi-super-team
Extracts web page content to clean Markdown with a probe-then-fallback strategy. Uses web_fetch first, then MinerU API for blocked or dynamic sites like WeChat. Returns a traceable result contract with source links.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agi-super-team:content-extractThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Author: Daniel Li
目标:把“给我一个 URL → 产出可读 Markdown + 可追溯入口”变成一个统一入口,供后续所有业务 skill(github-explorer、写作类 skills、日报等)复用。
核心原则(来自你发的 Excel Skill 拆解文章的启发):
输入:url
references/domain-whitelist.mdmodel_version=MinerU-HTMLweb_fetch(url)references/heuristics.md)包括:
skills/mineru-extract/scripts/mineru_parse_documents.pymodel_version=MinerU-HTML无论用 probe 还是 MinerU,都返回同一套结构:
{
"ok": true,
"source_url": "...",
"engine": "web_fetch" ,
"markdown": "...",
"artifacts": {
"out_dir": "...",
"markdown_path": "...",
"zip_path": "..."
},
"sources": [
"原文URL",
"(如使用MinerU)MinerU full_zip_url",
"(如使用MinerU)本地markdown_path"
],
"notes": ["任何重要限制/失败原因/下一步建议"]
}
注意:
engine可能是web_fetch或mineru。
当需要 MinerU 时,用这个命令(返回 JSON,且可把 markdown 内联进 JSON,便于下游总结):
python3 mineru-extract/scripts/mineru_parse_documents.py \
--file-sources "<URL>" \
--model-version MinerU-HTML \
--emit-markdown --max-chars 20000
路径说明: 上述命令假设你在 skills 安装根目录下执行。如果 mineru-extract 安装在其他位置,请替换为实际路径。
sources(原文入口 + 解析产物入口)。markdown_path(本地路径)写进 sources,方便复查。npx claudepluginhub aaaaqwq/agi-super-team --plugin agi-super-teamFetches web content as clean Markdown with 80% fewer tokens than raw HTML. Handles JS-heavy sites, documentation, and articles via auto, AI, or browser rendering.
Fetches any URL and returns clean Markdown via local trafilatura, with Exa MCP fallback for JS-rendered or anti-bot pages. Use instead of built-in WebFetch for reading, scraping, or summarizing web pages.
Extracts clean Markdown from any URL using ezycopy CLI. Handles JS-rendered pages with headless Chrome, retries on failure, and auto-installs tool if needed.