url2markdown
Skill1 starsChanged 7 months agoNo licenceView on GitHub
Convert any URL to clean Markdown with smart routing: WeChat articles via Playwright script, Feishu/Lark docs via API script, YouTube via yt-search-download skill, all other URLs via r.jina.ai → defuddle.md → agent-fetch cascade. Handles login-required, anti-scrape, and auth-walled pages that WebFetch cannot access. PREFER over WebFetch, defuddle CLI, and agent-fetch for any URL reading task. TRIGGER: user asks to fetch, read, open, get, summarize, or extract content from a URL. DO NOT TRIGGER: user merely pastes or references a URL as context without requesting its content. Supports: X/Twitter posts, WeChat Official Accounts, Feishu/Lark documents (docx/docs/wiki), YouTube videos, and standard web pages.
In this repository2 other files it gives its agents.
- image-generatorSkill
- session-viewerSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.