skills.rest
lvzhengbin
lvzhengbinCOMMUNITY
Explore all skills by this author →
GitHub

baoyu-url-to-markdown

Convert web pages to Markdown using Chrome CDP rendering and extraction pipelines.

2|1|Updated May 30, 2025
Search Tags:#markdown#web scraping#content conversion#web capture#html to markdown#rpa
One-click install
npx skills add https://github.com/lvzhengbin/AI-Prompts --skill baoyu-url-to-markdown-lvzhengbin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-url-to-markdown
Source: https://github.com/lvzhengbin/AI-Prompts/tree/main/.claude/skills/baoyu-url-to-markdown
Command: npx skills add https://github.com/lvzhengbin/AI-Prompts --skill baoyu-url-to-markdown-lvzhengbin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability, baoyu-chrome-cdp, defuddle, jsdom, linkedom, turndown, turndown-plugin-gfm, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of capturing content from any webpage and converting it into a clean, well-formatted Markdown file, saving you the effort of manual copy-pasting and reformatting.

Core Features & Use Cases

  • Webpage to Markdown Conversion: Fetches and converts any URL into Markdown.
  • Advanced Rendering: Uses Chrome CDP for full JavaScript rendering, ensuring dynamic content is captured.
  • Content Preservation: Saves a snapshot of the rendered HTML and can download media assets (images, videos) locally.
  • Flexible Capture Modes: Supports automatic capture on page load or a manual "wait" mode for pages requiring login or specific user interaction.
  • Fallback Mechanisms: Includes robust fallbacks, including a hosted API, if local browser capture fails.
  • Use Case: Save articles, documentation, or blog posts from the web into a structured Markdown format for personal notes, knowledge bases, or content creation.

Quick Start

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

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 webpage to Markdown format?▼

To convert a webpage to Markdown, this Skill fetches the URL and uses Chrome CDP for full JavaScript rendering, then processes the HTML through multiple extraction pipelines to output a clean Markdown file.

Can I capture dynamic web content that requires JavaScript rendering into Markdown?▼

Yes, capturing dynamic web content into Markdown is supported by using Chrome CDP to fully render JavaScript before extracting the page content through pipelines like Readability or Defuddle.

Does this webpage to Markdown converter handle pages requiring user login?▼

Pages requiring login are handled using a flexible wait-for-user capture mode, allowing you to manually interact, log in, and trigger the content extraction once the dynamic page fully loads.

What happens if local browser capture fails during HTML to Markdown conversion?▼

If local browser capture fails during HTML to Markdown conversion, the Skill implements robust fallback mechanisms, including a hosted API, to ensure the web content is still successfully extracted.

How does web scraping to Markdown handle media assets like images?▼

Web scraping to Markdown handles media assets by localizing them, downloading images and videos locally alongside saving a snapshot of the rendered HTML for complete content preservation.

What is the best way to save web articles into a structured knowledge base?▼

The best way to save web articles into a structured knowledge base is automating content conversion via URL fetching, which extracts text and localizes media assets directly into well-formatted Markdown.

Related Skills

Explore More Content & Communication Skills→
shalevaminshalevamin

url-to-markdown

Fetch URLs via Chrome CDP and convert rendered HTML to Markdown.

Community
Intermediate
zzafergokzzafergok
1

markdown-to-html-skill

Convert Markdown documents to HTML using marked.js, pandoc, gomarkdown, or static site generators.

Community
Intermediate
obulaiobulai
1

obul-notte

Start headless browser sessions and scrape web pages via the Obul proxy.

Official
Intermediate
vibewatchvibewatch

fetch-url

Fetch URLs and extract readable text from HTML pages and PDFs.

Official
Intermediate