Aller au contenu
TakoAPI
Retour aux skills

mdnew

par thendcn

Web & Frontend Development
458Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Fetch clean, agent-optimized Markdown from any URL using the markdown.new service.

Description

Ce que fait ce skill

Fetches clean, token-efficient Markdown from any URL using the markdown.new three-tier conversion pipeline. Strips boilerplate, ads, and navigation menus, leaving only core content. Handles JS-heavy pages via Cloudflare Browser Rendering as a fallback.

Reduces page size by up to 80% compared to raw HTML, making it practical for agents with tight context windows that would otherwise struggle with full-page content.

Quand l'utiliser

  • Extracting article text for LLM analysis
  • Scraping docs pages when web_fetch returns noisy HTML
  • Reading JS-rendered pages without a full browser setup
  • Reducing token usage when ingesting long web pages
  • Feeding clean web content into agent context windows

Exemple de workflow

ENTRÉE

User asks: Summarize the content at https://docs.example.com/guide

AGENT
  1. 1

    Run python3 scripts/mdnew.py https://docs.example.com/guide

  2. 2

    Pipeline attempts Header Negotiation first, falls back to Workers AI, then Cloudflare Browser Rendering

  3. 3

    Receive clean Markdown with x-markdown-tokens count in the response

  4. 4

    Pass Markdown to LLM for summarization

SORTIE

Clean Markdown summary of the documentation page, using a fraction of the tokens raw HTML would require

Installation

clawhub install thendcn/mdnew

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens