Takes a URL and returns clean Markdown, with smart routing under the hood. General pages hit r.jina.ai, YouTube goes through defuddle.md for transcript extraction, and paywalled Chinese sites like WeChat, Zhihu, and Feishu get a two-stage treatment: HTTP impersonation with cuimp first, then Puppeteer with browser fingerprinting if that fails. The fallback chain is sensible, it handles pre-proxied URLs correctly, and the JSON mode gives you provenance metadata so you know which backend actually worked. Useful when you're building agents that need to ingest web content reliably without maintaining your own anti-bot infrastructure for every regional platform.
npx skills add https://github.com/rookie-ricardo/erduo-skills --skill web-to-markdown