baoyu-url-to-markdown

Fetch web pages via Chrome CDP and convert them to Markdown with YAML front matter.

10|2|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/wx-chevalier/Awesome-Agent-Skills --skill baoyu-url-to-markdown-wx-chevalier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-url-to-markdown
Source: https://github.com/wx-chevalier/Awesome-Agent-Skills/tree/main/baoyu/baoyu-url-to-markdown
Command: npx skills add https://github.com/wx-chevalier/Awesome-Agent-Skills --skill baoyu-url-to-markdown-wx-chevalier

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability, linkedom, turndown, turndown-plugin-gfm, bun, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of converting web pages into clean Markdown files, preserving content and structure for easier use and archiving.

Core Features & Use Cases

  • Web Scraping: Fetches content from any URL using Chrome CDP for full JavaScript rendering.
  • Content Conversion: Converts HTML to clean Markdown, including YAML front matter with metadata.
  • Flexible Capture: Supports automatic capture on page load or manual user signal for dynamic pages.
  • Use Case: Save an online article or a complex web application's content as a Markdown file for offline reading, note-taking, or integration into a knowledge base.

Quick Start

Use the baoyu-url-to-markdown skill to convert the webpage at https://example.com into a markdown file.

Frequently Asked Questions about baoyu-url-to-markdown

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

FAQPage Schema
How do I convert a dynamic web page to Markdown?

To convert a dynamic web page to Markdown, the Skill fetches the URL using Chrome CDP for full JavaScript rendering, then transforms the HTML content into clean Markdown. This handles dynamic content automatically, ensuring complete capture of JavaScript-rendered pages.

Can I capture web pages that require login or user interaction?

Yes, you can capture web pages requiring login or interaction by using manual user signaling. The Skill supports flexible capture modes, allowing you to trigger the content extraction manually after completing necessary actions on the page.

How does Chrome CDP help with web scraping JavaScript-rendered content?

Chrome CDP facilitates web scraping JavaScript-rendered content by executing the page's scripts in a real browser environment. This ensures all dynamic elements are fully loaded before the HTML is extracted and converted to Markdown.

Does the converted Markdown include any metadata from the original web page?

Yes, the converted Markdown includes metadata from the original web page formatted as YAML front matter. It automatically captures and embeds details like the source URL, page title, and capture time alongside the content.

What is the best way to archive web content for offline reading?

The best way to archive web content for offline reading is converting it to a clean Markdown file with YAML front matter. This Skill fetches the page via Chrome CDP and outputs a structured document for note-taking or knowledge bases.

How do I convert HTML to Markdown for my knowledge base?

You can convert HTML to Markdown for your knowledge base by supplying the target URL to this Skill. It processes the web page using Readability and Turndown to output clean, structured Markdown suitable for integration.