qiaomu-markdown-proxy

Convert shared URLs to Markdown via proxy services with fallback routing.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/buer2233/my_openclaw --skill qiaomu-markdown-proxy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qiaomu-markdown-proxy
Source: https://github.com/buer2233/my_openclaw/tree/main/skills/qiaomu-markdown-proxy
Command: npx skills add https://github.com/buer2233/my_openclaw --skill qiaomu-markdown-proxy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires marker-pdf, pdftotext, pypdf, agent-fetch, requests, playwright, beautifulsoup4, lxml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill converts arbitrary URLs into clean Markdown by routing through proxy services or built-in scripts, enabling content capture when access is restricted.

Core Features & Use Cases

  • Route by URL type to dedicated fetch scripts (WeChat/MP Weixin articles, Feishu/Lark docs, YouTube) or browser-based scrapers when needed.
  • Proxy cascade with fallback: r.jina.ai, defuddle.md, and a local agent-fetch path, producing YAML frontmatter and Markdown output.
  • Supports PDFs (remote and local) and non-HTTP(s) pages, empowering automated content ingestion for knowledge bases or research workflows.

Quick Start

Share a URL with Claude to convert it to Markdown using the built-in proxy or scripts.

Frequently Asked Questions about qiaomu-markdown-proxy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a URL to Markdown when access is restricted?

To convert a URL to Markdown when access is restricted, this Skill routes links through proxy services like r.jina.ai and defuddle.md. It fetches the content and outputs clean Markdown with YAML frontmatter.

Can I extract content from login-protected Feishu or WeChat pages into Markdown?

Yes, you can extract content from login-protected Feishu docs and WeChat MP articles into Markdown. The Skill uses dedicated fetch scripts and browser-based scrapers to bypass restrictions and retrieve the text.

What is the best way to convert a remote PDF to Markdown format?

The best way to convert a remote PDF to Markdown format is by using dedicated local tools like marker-pdf or pdftotext. The system automatically routes PDF URLs to these extraction paths to produce clean text.

Does this URL to Markdown tool support YouTube video transcripts?

Yes, this URL to Markdown tool supports YouTube video transcripts. It routes YouTube URLs to dedicated fetch scripts that extract the transcript and format it directly into a usable Markdown body.

What happens if the primary proxy service fails to fetch the web page content?

If the primary proxy service fails to fetch the web page content, the system uses a proxy cascade fallback mechanism. It automatically tries alternatives like defuddle.md and a local agent-fetch path to ensure retrieval.

Do I need to install Playwright to scrape web pages and convert them to Markdown?

You need Playwright installed for browser-based scraping of complex web pages. The Skill relies on it alongside other dependencies like beautifulsoup4 and lxml to parse and convert HTML content into Markdown.