baoyu-url-to-markdown

Fetch web content via Chrome CDP and convert HTML to Markdown with YAML frontmatter.

Updated Feb 15, 2026

Search Tags:#markdown #web scraping #content conversion #url to markdown #chrome cdp #web archiving

Ready to run

npx skills add https://github.com/sksdwl/shudan --skill baoyu-url-to-markdown-sksdwl

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: baoyu-url-to-markdown
Source: https://github.com/sksdwl/shudan/tree/main/workspace/skills/baoyu-url-to-markdown
Command: npx skills add https://github.com/sksdwl/shudan --skill baoyu-url-to-markdown-sksdwl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of fetching web content from a given URL and converting it into a clean Markdown format, preserving essential information while removing web page clutter.

Core Features & Use Cases

URL to Markdown Conversion: Fetches and transforms HTML content into Markdown.
Chrome CDP Integration: Utilizes Chrome DevTools Protocol for accurate rendering, including JavaScript-heavy pages.
Flexible Capture Modes: Supports automatic capture on page load or manual triggering for pages requiring login or user interaction.
Use Case: When you find an interesting article online and want to save it for offline reading or easy referencing in a structured format, use this Skill to convert the entire page into a Markdown file.

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 web page URL to Markdown format?▼

This URL to Markdown converter fetches web content from a specified address and transforms the HTML into a clean Markdown file. It preserves essential information while removing web page clutter, outputting a file with YAML frontmatter containing page metadata.

Does web scraping with Chrome CDP work on JavaScript-heavy pages?▼

Yes, web scraping with Chrome CDP works on JavaScript-heavy pages. The Chrome DevTools Protocol accurately renders dynamic content, ensuring that JavaScript-loaded elements are fully captured before converting the HTML to Markdown format.

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

Yes, you can capture web content from pages requiring login or user interaction. The converter supports flexible capture modes, allowing manual triggering for pages where you need to perform actions before the HTML is fetched and converted to Markdown.

What is the best way to save web articles for offline reading in a structured format?▼

The best way to save web articles for offline reading in a structured format is converting the HTML to Markdown. This approach stores the page content in a clean, portable text file with YAML frontmatter metadata for easy referencing and archiving.

Does the Markdown conversion output include any page metadata?▼

Yes, the Markdown conversion output includes page metadata. The resulting Markdown file contains YAML frontmatter at the top, which holds essential metadata extracted from the original web page alongside the converted text content.