web-content-extraction

This skill extracts documentation and website content as markdown files. It uses a tiered approach: try the simplest method first, fall back to heavier tools only when needed.

User provides a URL to extract content from. This skill is appropriate when:

Before extracting content, discover all pages on the site. Try these methods in order:

從網站中提取文件和內容。支援 Mintlify、Starlight/Astro、Docusaurus、GitBook、ReadTheDocs、Sphinx 和通用網站。使用分層方法 - 首先嘗試最簡單的方法（直接捲曲，Jina AI Reader），然後再針對 JS 較多的站點回退到 Crawl4AI。 來源：nikhilmaddirala/gtd-cc。