baoyu-url-to-markdown

Fetch webpages and convert HTML to Markdown via Chrome DevTools Protocol.

1|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/lisposter/creator --skill baoyu-url-to-markdown
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-url-to-markdown
Source: https://github.com/lisposter/creator/tree/main/.agents/skills/baoyu-url-to-markdown
Command: npx skills add https://github.com/lisposter/creator --skill baoyu-url-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill enables saving online content as Markdown by fetching a webpage and converting its HTML into clean, readable Markdown. It eliminates manual copy-paste and messy HTML editing, streamlining content capture for offline use and documentation.

Core Features & Use Cases

  • Chrome CDP-driven rendering for JavaScript-rendered pages.
  • Two capture modes: auto on page load or wait-for-user signal for login-protected or lazy-loaded content.
  • Outputs YAML front matter with metadata and a clean Markdown body, organized per domain and slug for easy archival.
  • Use Case: Save a long article from a blog as a ready-to-edit Markdown file for notes or knowledge bases.

Quick Start

Auto mode: npx -y bun ${SKILL_DIR}/scripts/main.ts <url> Wait mode: npx -y bun ${SKILL_DIR}/scripts/main.ts <url> --wait Save to file: npx -y bun ${SKILL_DIR}/scripts/main.ts <url> -o output.md

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 save a webpage as Markdown without messy HTML formatting?

To save a webpage as Markdown, this skill fetches the HTML via Chrome DevTools Protocol and converts it into clean, readable Markdown with YAML frontmatter, eliminating manual copy-paste and HTML editing.

Can I capture content from login-restricted or dynamically loaded webpages?

Yes, you can capture login-restricted or dynamic webpages by using the wait-for-user signal mode, which pauses the script to allow manual login or lazy-loaded content rendering before conversion.

How do I convert JavaScript-rendered pages to Markdown?

You can convert JavaScript-rendered pages to Markdown by running the provided script with the target URL; it uses a local Chrome binary via Chrome DevTools Protocol to fully render the page before extraction.

Do I need a local Chrome binary installed to use Chrome CDP for web scraping?

Yes, you need a local Chrome binary installed because the skill relies on Chrome DevTools Protocol to launch a browser instance, render the target webpage, and extract the HTML content for Markdown conversion.

What's the best way to archive web content with metadata for a knowledge base?

The best way to archive web content is using this skill to output a Markdown file with YAML frontmatter metadata, organizing the saved files per domain and slug for easy documentation and offline retrieval.

Why does webpage to Markdown conversion fail on lazy-loaded content?

Webpage to Markdown conversion fails on lazy-loaded content when using auto mode because the page hasn't fully rendered; switching to the wait mode allows dynamic content to load before capture.