Fetch URL As Markdown

Local trafilatura-first URL-to-Markdown fetcher with a clean exit-code contract for when to fall back to Exa.

Tested · Works

Test report

Verdict
Tested · Works
Score
10.0/10
Tested
Jul 13, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 18, 2026 · 1564269

Ran the bundled script live on a real Wikipedia page: it returned clean 44KB markdown with a proper YAML metadata header and zero nav/menu chrome, versus a 30KB naive-strip baseline still full of "Jump to content Main menu... Donate Create account Log in" junk; separately confirmed the exit-code contract by hitting a real arXiv PDF and getting the documented exit 4 (no Exa fallback) instead of a false extraction failure.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 10/10
  • Docs & honesty 5/5

What Fetch URL As Markdown does

Fetches a URL and returns clean main-content Markdown using a local trafilatura script by default, falling back to Exa MCP only on download or extraction failure, and refusing outright on binary content. Use whenever the user asks to read, fetch, scrape, summarize, or quote a URL — it is meant to replace the built-in WebFetch tool for that case, not for PDFs, images, archives or JSON/API endpoints.

How to install Fetch URL As Markdown

git clone https://github.com/CodeAlive-AI/ai-driven-development
cd ai-driven-development
mkdir -p ~/.claude/skills
cp -r skills/fetch-url-as-markdown ~/.claude/skills/fetch-url-as-markdown

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Fetch URL As Markdown

  • /fetch-url-as-markdown Local trafilatura-first URL-to-Markdown fetcher with a clean exit-code contract for when to fall back to Exa.

It also activates on plain-language prompts like these:

  • Fetch this article and give me the clean main content as Markdown
  • Summarize what's on this webpage for me in plain text
  • Pull the text from this URL and quote the key points

Frequently asked questions

Is the Fetch URL As Markdown skill free?
Yes. The skill itself is free from CodeAlive-AI/ai-driven-development. SkillProof publishes the install command and an independent test verdict at no cost.
Does Fetch URL As Markdown work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Ran the bundled script live on a real Wikipedia page: it returned clean 44KB markdown with a proper YAML metadata header and zero nav/menu chrome, versus a 30KB naive-strip baseline still full of "Jump to content Main menu... Donate Create account Log in" junk; separately confirmed the exit-code contract by hitting a real arXiv PDF and getting the documented exit 4 (no Exa fallback) instead of a false extraction failure.
What is the Fetch URL As Markdown SkillProof Score?
10.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 10/10, docs & honesty 5/5.
How do I install Fetch URL As Markdown?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Fetch URL As Markdown with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.