Markdown Proxy Url Fetcher

What This Skill Does

The Markdown Proxy URL Fetcher is a robust utility designed to bridge the gap between unstructured web content and actionable data. At its core, the skill provides a sophisticated proxy cascade mechanism that automatically attempts multiple retrieval methods to convert any given URL into clean, readable Markdown. This ensures that you can ingest content from complex platforms that typically resist traditional scraping methods, such as WeChat public articles, protected Feishu/Lark documents, and various X/Twitter posts, while handling standard websites with ease. By routing requests through specialized services like r.jina.ai and defuddle.md, it preserves critical formatting, images, and structure, allowing you to feed high-quality data directly into your LLM workflows.

Installation

To integrate this skill into your OpenClaw environment, ensure you have Node.js and npm installed. Run the following command in your terminal:

npx skills add joeseesun/markdown-proxy

After installation, verify the setup by locating the configuration file: ls ~/.claude/skills/markdown-proxy/SKILL.md. For specific platform scraping, ensure your environment is prepared. WeChat scraping requires Python 3 with Playwright installed: pip install playwright beautifulsoup4 lxml followed by playwright install chromium. For Feishu/Lark integration, configure your credentials via system environment variables: FEISHU_APP_ID and FEISHU_APP_SECRET.

Use Cases

This skill is perfect for researchers, developers, and content analysts who need to automate the aggregation of information. Use it to centralize documentation from disparate company wikis, summarize long-form articles found on social media without navigating away from your chat interface, or bypass aggressive anti-scraping measures on major publishing platforms. It is particularly effective for teams who rely on internal Feishu document management but need to incorporate that data into external AI-driven report generation.

Example Prompts

1. "Read this article for me and summarize the core arguments: https://example.com/deep-dive-article"
2. "Can you scrape this WeChat article and extract the key takeaways in a bulleted list: https://mp.weixin.qq.com/s/sample-wechat-link"
3. "Convert this internal Feishu doc to markdown so I can include it in my project documentation: https://company.feishu.cn/docx/sample-doc-id"

Tips & Limitations

Always prioritize the use of official APIs where available, such as for Feishu, to ensure compliance with platform terms of service. Note that this skill is not designed for YouTube content, which requires a dedicated media-fetching skill. If a site is highly dynamic, the Playwright fallback for WeChat is your most reliable option, though it is more resource-intensive. Keep your environment variables secure if working with sensitive Feishu documentation access tokens.