URL to Markdown Fetcher

What it does

When your agent uses it

• Reading a WeChat public-account article or a Feishu document from its link
• Converting a webpage or PDF into Markdown before summarizing or translating it
• Pulling the structured content of an arXiv paper from its LaTeX source
• Fetching a post from a site that requires login, such as X

Example prompts

• “Read https://mp.weixin.qq.com/s/abc123 and summarize the main argument.”
• “Convert this arXiv paper into Markdown and keep the equations.”
• “Fetch the article at example.com/blog/launch and save it as Markdown in my Downloads folder.”

Requirements

• Bash, to run the fetch scripts
• Feishu API credentials, for Feishu and Lark documents
• Playwright, for the WeChat fallback

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Route by URL Type
2. 2Display Content
3. 3Continue or Save

What it can do on your machine

Read from SKILL.md and the folder at commit ab56e0a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • bash
  • python3
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • r.jina.ai
  • x.com
  • mp.weixin.qq.com
  • xxx.feishu.cn
  • arxiv.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • FEISHU_APP_SECRET

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

URL to Markdown Fetcher loads about 1.4k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 131 tokens; SKILL.md has 280 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~131

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from joeseesun/qiaomu-markdown-proxy at commit ab56e0a, republished under its MIT licence (© joeseesun). 280 words, ~1,363 tokens.

name

qiaomu-markdown-proxy

description

Read, fetch, extract, parse, or convert a URL or link into clean Markdown. Use FIRST whenever a user asks to read source content from a webpage, especially WeChat/微信公众号 mp.weixin.qq.com, Feishu/Lark docs, X/Twitter, PDFs, arXiv papers, or a URL that will feed a later summary, rewrite, article, podcast, or analysis. For WeChat and Feishu, prefer this specialist extractor over generic web open or generic content parsers. Exclude YouTube, pure web search, already-pasted text, and local non-PDF files.

version

2.1.0

if URL contains "mp.weixin.qq.com":
    → bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch_weixin.sh "URL"
    → Done

if URL contains "feishu.cn/docx/" or "feishu.cn/wiki/" or "larksuite.com/docx/":
    → python3 ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch_feishu.py "URL"
    → Done

if URL contains "huggingface.co/papers/":
    → First fetch the page (WebFetch) to find the arXiv URL
    → Then python3 ~/.agents/skills/qiaomu-markdown-proxy/scripts/extract_tex.py "{arxiv_url}"
    → Done

if URL contains "arxiv.org/abs/" or "arxiv.org/pdf/":
    → python3 ~/.agents/skills/qiaomu-markdown-proxy/scripts/extract_tex.py "URL"
    → Done

if URL contains "youtube.com" or "youtu.be":
    → Call qiaomu-youtube-download skill
    → Done

if URL ends with ".pdf" or is local PDF path:
    if remote URL:
        → Try: curl -sL "https://r.jina.ai/{url}"
        → If fails: download + extract_pdf.sh
    if local path:
        → bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/extract_pdf.sh "PATH"
    → Done

else:
    → bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch.sh "URL"
    → Done

Title:  {title}
Author: {author} (if available)
Source: {platform} (公众号 / 飞书文档 / 网页 / PDF)
URL:    {original_url}

Summary
{3-5 sentence summary}

Content
{full Markdown, truncated at 200 lines if long}

bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch.sh "https://example.com/article"

bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch.sh "https://x.com/username/status/1234567890"

bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch_weixin.sh "https://mp.weixin.qq.com/s/abc123"

python3 ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch_feishu.py "https://xxx.feishu.cn/docx/xxxxxxxx"

python3 ~/.agents/skills/qiaomu-markdown-proxy/scripts/extract_tex.py "https://arxiv.org/abs/1706.03762"

curl -sL "https://r.jina.ai/https://example.com/paper.pdf"

bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/extract_pdf.sh "/path/to/paper.pdf"

bash ~/.agents/skills/qiaomu-markdown-proxy/scripts/fetch.sh "https://example.com" "http://127.0.0.1:7890"

© joeseesun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references, assets) in the repository root of joeseesun/qiaomu-markdown-proxy.

• SKILL.md
• .gitignore
• LICENSE
• README.md
• agents/interface.yaml
• assets/qiaomu-profile/qiaomu_avatar.jpeg
• assets/qiaomu-profile/qiaomu_reward_qr.png
• assets/qiaomu-profile/qiaomu_wechat_public_account_qr.jpg
• evals/trigger_cases.json
• manifest.json
• references/methods.md
• reports/creation-handoff.md
• reports/output-evidence.json
• reports/prior-art-research.md
• reports/release-local.json
• … and 11 more

Open the folder on GitHubat commit ab56e0a