
Qiaomu Markdown Proxy
This is a URL-to-Markdown converter that routes different content types through specialized scrapers. It handles paywalled or login-required platforms like WeChat articles, Feishu docs, and Twitter posts by using proxy services (r.jina.ai, defuddle.md) or Playwright for JavaScript-heavy pages. PDFs get OCR treatment, and everything else goes through a fallback cascade. The routing logic is smart: it pattern-matches the URL first, then picks the right extraction method. Saves everything to ~/Downloads with YAML frontmatter by default. You'll need to set up Feishu API keys if you work with those docs, and install Playwright for WeChat. Good for research workflows where you're pulling content from all over the Chinese and English web into a local knowledge base.
- skills.sh installs
- 176
- GitHub stars
- 462
- last updated
- Jun 3, 2026
Install
$ npx -y skills add joeseesun/markdown-proxy --skill qiaomu-markdown-proxy --agent claude-codeInstalls into .claude/skills of the current project.
Files
Markdown Proxy - URL to Markdown
将任意 URL 转为干净的 Markdown。支持需要登录的页面、PDF、专有平台。
Trigger Priority(先触发,再分流)
- 用户给出 URL 并要求“读取、抓取、提取、解析、转 Markdown”时,优先使用本 Skill。
- 用户要求“读取这篇链接后再写稿、总结、翻译、做播客或分析”时,先用本 Skill 取回原文,再把 Markdown 交给下游 Skill;不要因为最终任务是写作而跳过抓取。
mp.weixin.qq.com和飞书文档属于专用路由。不要先试普通网页打开或通用内容解析器。- 用户已经贴出全文时不触发。YouTube 交给
qiaomu-youtube-download,普通搜索问题交给搜索工具。
URL Routing (先判断再执行)
收到 URL 后,先判断类型,不同类型走不同通道:
| URL Pattern | Route To | Reason |
|---|---|---|
mp.weixin.qq.com | scripts/fetch_weixin.sh | 先代理,验证码页自动回退 Playwright |
feishu.cn/docx/ feishu.cn/wiki/ larksuite.com/docx/ | scripts/fetch_feishu.py | 需飞书 API 认证 |
youtube.com youtu.be | qiaomu-youtube-download skill | YouTube 有专用工具链 |
huggingface.co/papers/ | 提取 arXiv ID → scripts/extract_tex.py | HuggingFace 论文页实际是 arXiv 镜像,先找到 arXiv 链接再走 LaTeX 提取 |
arxiv.org/abs/ arxiv.org/pdf/ | scripts/extract_tex.py | 从 LaTeX 源码提取结构化内容 (章节/图表/公式) |
.pdf (URL or local path) | scripts/extract_pdf.sh | PDF 专用提取 |
| All other URLs | scripts/fetch.sh | 代理级联自动 fallback |
Workflow
Step 1: Route by URL Type
Sponsors
Details
- Repository
- github.com/joeseesun/markdown-proxy
- Category
- Backend & APIs
- First seen
- Jun 3, 2026