skills.rest
rookie-ricardo
rookie-ricardoCOMMUNITY
Explore all skills by this author →
GitHub

web-to-markdown

Convert web URLs to Markdown using domain-aware routing.

930|86|Updated Jan 20, 2026
Search Tags:#automation#markdown#routing#readability#web-content#content-extraction
One-click install
npx skills add https://github.com/rookie-ricardo/erduo-skills --skill web-to-markdown-rookie-ricardo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-to-markdown
Source: https://github.com/rookie-ricardo/erduo-skills/tree/main/skills/web-to-markdown
Command: npx skills add https://github.com/rookie-ricardo/erduo-skills --skill web-to-markdown-rookie-ricardo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability, cuimp, jsdom, puppeteer, puppeteer-extra, puppeteer-extra-plugin-anonymize-ua, puppeteer-extra-plugin-stealth, turndown, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Web pages vary in structure and readability, making it hard to extract clean, usable text from links. This skill automates turning URLs into readable Markdown using deterministic, domain-aware routing rules.

Core Features & Use Cases

  • Domain-aware routing: default to r.jina.ai for general pages, use defuddle.md for YouTube transcripts, and employ browser-impersonation with Mozilla Readability for WeChat/Zhihu/Feishu pages.
  • Readability-first extraction: Moz Readability with fallbacks to HTML-to-Markdown conversion via Turndown.
  • Use Case: Convert a news article URL into Markdown for a knowledge base entry, preserving headings, titles, and key passages.

Quick Start

Run the URL-to-Markdown workflow by providing a single URL.

Frequently Asked Questions about web-to-markdown

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert web pages to Markdown from URLs that block scraping?▼

You can convert web pages to Markdown using domain-aware routing that applies browser-impersonation with Mozilla Readability for platforms like WeChat, Zhihu, and Feishu that block scraping.

What is the best way to extract readable text from a YouTube URL into Markdown?▼

The best way to extract YouTube content into Markdown is using defuddle.md routing, which specifically targets and retrieves transcripts from YouTube URLs.

How do I automate web content extraction for knowledge base entries?▼

Automate web content extraction by providing a single URL to route through r.jina.ai or Mozilla Readability, returning clean Markdown with preserved headings and key passages for knowledge base entries.

Can I get metadata alongside the Markdown output when converting URLs?▼

Yes, you can request a JSON metadata object alongside the Markdown output that includes the source, strategy used, and resolved URL for the converted web page.

Does the URL to Markdown conversion fall back if the primary routing fails?▼

Yes, the URL to Markdown conversion gracefully falls back across alternative routing paths, such as switching from r.jina.ai to HTML-to-Markdown Turndown, if the primary route fails.

Why does my web content extraction return unreadable Markdown for X or Twitter links?▼

Web content extraction for X or Twitter links requires specific routing; the default r.jina.ai route handles general pages including X/Twitter to ensure the returned Markdown remains readable.

Related Skills

Explore More Content & Communication Skills→
llm011llm011
9

url-process

Route links to platform-specific extraction workflows for Markdown or summaries.

Official
Advanced
christian-bromannchristian-bromann
3

langchain-embeddings-vectorstores

Convert text into embeddings and index them into vector stores for semantic search.

Community
Advanced
badlogicbadlogic
2.3k

browser-tools

Automate Chrome browser control and content extraction via the Chrome DevTools Protocol.

Community
Advanced
OpenAEC-FoundationOpenAEC-Foundation
163

frappe-website-deploy

Deploy ERPNext/Frappe websites via REST API with Page Builder.

Official
Advanced