
URL to Markdown
Turn any web page into clean markdown, using a real Chrome browser and site-specific adapters.
- Repository
- JimLiu/baoyu-skills
- Stars
- 27,191
- Licence
- MIT
- Files
- 15 files
What it does
Once installed, the agent can open a web address in a Chrome browser it controls, pull out the readable content, and save it as a markdown text file. It has special handling for X/Twitter posts, YouTube transcripts, Hacker News threads, and a generic fallback for other pages. It can also pause so you can log in or solve a CAPTCHA, then continue the capture.
Great for
- People who want to archive or save articles and threads as markdown notes
- Developers or researchers collecting web content for later analysis or AI context
- Users who need content from pages that require a login they can complete in a visible browser
Skip it if
- Scraping large volumes of pages or bypassing paywalls and access controls, since the skill runs real browser sessions and may store login state in a Chrome profile folder
- Sensitive or private pages where you do not want the content or session data written to disk or sent to third-party services
- Users who cannot install Bun and Chrome, since the skill will not run without them
Try asking
- “Save this article as markdown: https://example.com/post”
- “Convert this Hacker News thread to markdown with comments and save it to ./notes/hn.md”
- “Fetch this X post and download its images locally”
- “Grab the transcript of this YouTube video as markdown”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 15 original files, the MIT licence and an attribution note.
baoyu-url-to-markdown.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip baoyu-url-to-markdown.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip baoyu-url-to-markdown.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Review the saved markdown after each run, since headless capture can silently return low-quality content on some sites; the skill's quality gate describes how to retry with a visible browser.
- Use --output and a dedicated output folder so media downloads and files stay organized, and keep the Chrome profile directory private because it may hold login sessions.
- Answer the first-time setup questions once to store preferences in EXTEND.md, and choose the project-level location if you do not want settings shared across projects.
What's inside
- references/adapters.md
- references/config/first-time-setup.md
- references/quality-gate.md
- scripts/lib/adapters/generic/index.ts
- scripts/lib/adapters/hn/index.ts
- scripts/lib/adapters/index.ts
- scripts/lib/adapters/types.ts
- scripts/lib/adapters/x/article.ts
- scripts/lib/adapters/x/index.ts
- scripts/lib/adapters/x/login.ts
- scripts/lib/adapters/x/match.ts
- scripts/lib/adapters/x/payloads.ts
- scripts/lib/adapters/x/session.ts
- scripts/lib/adapters/x/shared.ts
- SKILL.md
Redistributed unmodified from JimLiu/baoyu-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.