agentleFS
blessonismblessonism/openclaw-skills/content-extract/SKILL.md

content-extract

Skill55 starsChanged 9 months agoMITView on GitHub

Robust URL-to-Markdown extraction for OpenClaw workflows. Use when the user wants to "extract/summarize/convert a webpage to markdown" (especially WeChat mp.weixin.qq.com) and web_fetch/browser is blocked or messy. Uses a cheap probe via web_fetch first, then falls back to the official MinerU API (via the local mineru-extract skill) and returns a traceable result contract with source links.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 2

    1. blessonism/openclaw-search-skills★ 43892% same
    2. blessonism/search-skills★ 43892% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Files
SKILL.md

content-extract — 上层内容解析入口(MCP 语义对齐,但不跑 MCP Server)

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):

  • 行为规约层:永远给出可追溯入口(原文 URL + 解析产物路径/链接),绝不编造来源。
  • Token 探针:先用低成本 probe 判断可不可以直接抓;不行再走重解析(MinerU)。
  • 反弹机制:失败时返回“下一步动作建议”,而不是一堆异常栈。

工作流(Decision Tree)

输入:url

  1. Domain Whitelist(跳过 probe):若 URL 属于高概率反爬/动态站点(微信/知乎等),直接走 MinerU
  • 白名单文件:references/domain-whitelist.md
  • 对命中白名单的 URL:强制 model_version=MinerU-HTML

0.5) GitHub Fast Path(跳过 probe 和 MinerU):若 URL 匹配 github.com/{owner}/{repo} 模式,直接走 GitHub API

  • GitHub repo 页面是 SPA(客户端渲染),web_fetch 只能拿到导航栏壳子
  • 用 GitHub API 获取 README、repo 元数据、文件树、Issues 等
  • 详见 references/heuristics.md 中的 GitHub fast path 章节
  • Auth: Authorization: token {GITHUB_PAT}(见 TOOLS.md)
  • 返回结果仍遵循统一 Result Contract(engine: "github-api")
  1. Probe(低成本):优先用 web_fetch(url)
  • 目标:拿到正文 markdown(便宜、快)
  • 判断“失败/不合格”条件(见 references/heuristics.md)包括:
    • 403/401/反爬
    • 只有“环境异常/验证码/请在微信打开”等提示
    • 内容极短/明显导航页/丢正文
  1. Fallback(高保真):走 MinerU 官方 API
  • 调用下游 driver:skills/mineru-extract/scripts/mineru_parse_documents.py
  • 对 HTML 页面(微信等):强制 model_version=MinerU-HTML
  1. 输出统一结果合同(Result Contract)

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、mineru 或 github-api。

MinerU 调用(给 agent 的确定性脚本)

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 /home/node/.openclaw/workspace/skills/mineru-extract/scripts/mineru_parse_documents.py \
  --file-sources "<URL>" \
  --model-version MinerU-HTML \
  --emit-markdown --max-chars 20000

交付规范(强制)

  • 输出必须包含 sources(原文入口 + 解析产物入口)。
  • 如果 MinerU 成功:必须把 markdown_path(本地路径)写进 sources,方便复查。
  • 如果两条链路都失败:必须明确失败原因,并给出下一步(例如:让 Boss 提供可访问镜像链接 / 允许我用浏览器 relay 导出 HTML / 走上传 HTML 文件解析的兜底方案)。

本 skill 自身不做什么

  • 不跑 MCP Server(避免常驻服务与运维负担)
  • 不试图绕过登录/验证码(这属于访问层问题;我们只做解析层和工作流路由)

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.