Fetch web pages and save them as local Markdown files.
npx skills add https://github.com/rungchan2/frontend-skills --skill web-to-markdown-rungchan2
Please help me install this Agent Skill. Skill: web-to-markdown Source: https://github.com/rungchan2/frontend-skills/tree/main/skills/web-to-markdown Command: npx skills add https://github.com/rungchan2/frontend-skills --skill web-to-markdown-rungchan2
Converts web documentation, blog posts, and reference pages into local Markdown files so developers and writers can archive, reference, and version-control external content without manual copy/paste.
Fetch the page at https://react.dev/reference/react/useState and save it as a Markdown file in the project's docs/ directory.
High-intent search queries and answers about installing and using this skill.
To convert web pages to Markdown files, fetch the URL and save the extracted content as an annotated .md file in your project's docs/ directory. It tries Cloudflare's text/markdown header first, falling back to HTML extraction and regex-based conversion.
Yes, you can scrape documentation pages and save them as Markdown using only the Python standard library. The tool fetches HTML, strips nav/footer/scripts, and converts headings, code blocks, tables, links, and images into Markdown format.
Converting HTML to Markdown does not require a Cloudflare API key. An optional CLOUDFLARE_API_KEY enables higher-quality native Markdown retrieval via the Accept: text/markdown header, but the tool falls back to standard HTML extraction without it.
The best way to archive API references and blog posts is to fetch the web pages and write them as Markdown files with source and timestamp metadata into the docs/ directory, enabling offline review and version control without manual copy/paste.
Web-to-markdown conversion might include stray navigation text if the heuristic extraction fails to isolate the main content. The tool attempts to strip nav, footer, and script tags before converting HTML to Markdown, but complex page layouts can affect extraction accuracy.
You should not use automated HTML to Markdown conversion when a web page relies heavily on dynamic JavaScript rendering, as the standard library fetch only captures static HTML and may miss dynamically loaded content.
Thanh-aperoGenerate llms.txt and llms-full.txt indexes from markdown directories or URLs.
endorphin-aiManage project documentation and work items using markdown files with Git.
marktantongcoExtract HTML content from URLs and convert it to markdown.
JKhyroExtract web page content from static, dynamic, and protected sites.