Agent skill · writing content · aradotso
markdown-proxy-url-fetcher
markdown-proxy-url-fetcher — an agent skill for coding agents.
Why this skill is useful
Includes executable scripts for fetching and converting URLs to Markdown that extend the AI's capabilities significantly.
What it needs
Requires beautifulsoup4, curl, lxml, playwright installed locally. Requires feishu account access. About 5k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash npx skills add joeseesun/markdown-proxy bash ls ~/.claude/skills/markdown-proxy/SKILL.md bash pip install playwright beautifulsoup4 lxml playwright install chromium bash export FEISHUAPPID=yourappid export FEISHUAPPSECRET=yourappsecret bash npx agent-fetch --help # npx auto-downloads, no pre-install needed Read this article: https://example.com/post Fetch this tweet: https://x.com/user/status/123456 Read this WeChat article: https://mp.weixin.qq.com/s/abc123 Convert this Feishu doc: https://company.feishu.cn/docx/AbCdEfGh Read this Feishu wiki page: https://company.feishu.cn/wiki/AbCdEfGh bash Step 1: Try r.jina.ai curl -s "https://r.jina.ai/https://example.com/article" Step 2: If empty/failed, try defuddle.md curl -s "https://defuddle.md/https://example.com/article" Step 3: If still failed, try agent-fetch locally npx agent-fetch https://example.com/article Step 4: Last resort — defuddle CLI npx defuddle https://example.com/article python The script is bundled — Claude Code invokes it automatically Manual usage: python ~/.claude/skills/markdown-proxy/fetchwechat.py \ "https://mp.weixin.qq.com/s/yourarticleid" python from playwright.syncapi import syncplaywright from bs4 import BeautifulSoup def fetchwechatarticle(url: str) -> str: with syncplaywright() as p: browser = p.chromium.launch(headless=True) page = browser.newpage() page.goto(url, waituntil="networkidle") html = page.content() browser.close() soup = BeautifulSoup(html, "lxml") # Extracts #jscontent div (WeChat article body) article = soup.find(id="jscontent") return converttomarkdown(article) bash Set credentials (required) export FEISHUAPPID=clixxxxxxxxxxxxxxxx export FEISHUAPPSECRET=yoursecrethere Manual invocation python ~/.claude/skills/markdown-proxy/fetchfeishu.py \ "https://company.feishu.cn/docx/AbCdEfGhIjKl" https://{tenant}.feishu.cn/docx/{docid} # New docs https://{tenant}.feishu.cn/docs/{docid} # Legacy docs https://{tenant}.feishu.cn/wiki/{wikiid} # Wiki pages https://{tenant}.larksuite.c …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/markdown-proxy-url-fetcher