Can I capture pages that require a login?

Yes. By using the --wait mode, you can manually log in or navigate the page before signaling the skill to capture the content.

Does this skill work with JavaScript-rendered websites?

Yes, it uses Chrome CDP (Chrome DevTools Protocol) to ensure full rendering of SPAs and dynamic content before converting to Markdown.

Does it preserve page metadata?

Yes, every output file includes YAML front matter containing the source URL, page title, description, author, and capture timestamp.

What are the system requirements for this skill?

The skill requires Bun for execution and a local installation of Chrome or Chromium. You can customize the Chrome path using environment variables if needed.

Where are the converted Markdown files stored?

Files are automatically organized in a 'url-to-markdown' directory, categorized by domain name with slug-based filenames.

URL to Markdown Converter

Name: URL to Markdown Converter
Author: JimLiu

byJimLiu

•

3,229

웹 스크래핑 및 데이터 수집

Converts any live webpage into clean, structured Markdown format using Chrome CDP for full JavaScript rendering.

소개

The baoyu-url-to-markdown skill enables Claude to browse the web with high fidelity, capturing complex pages and converting them into production-ready Markdown. By utilizing the Chrome DevTools Protocol (CDP), it ensures that JavaScript-heavy sites, single-page applications (SPAs), and dynamic content are fully rendered before conversion. It features a unique 'wait mode' for handling pages behind logins or paywalls, allowing users to manually signal when a page is ready for capture. This tool is ideal for developers, researchers, and writers who need to archive web content, documentation, or articles with preserved metadata and clean formatting.

주요 기능

Comprehensive YAML front matter including URL, title, and author metadata
Customizable Chrome profiles and environment variable support
Intelligent conflict resolution with timestamped file naming
Two capture modes: automated on network idle or manual user signal
3,229 GitHub stars
Full JavaScript rendering via Chrome CDP for dynamic web content

사용 사례

Automating the collection of web data into a structured local knowledge base
Saving technical documentation or blog posts for offline reading or AI processing
Extracting content from password-protected or paywalled sites via interactive wait mode

소개

주요 기능

Comprehensive YAML front matter including URL, title, and author metadata
Customizable Chrome profiles and environment variable support
Intelligent conflict resolution with timestamped file naming
Two capture modes: automated on network idle or manual user signal
3,229 GitHub stars
Full JavaScript rendering via Chrome CDP for dynamic web content

사용 사례

Automating the collection of web data into a structured local knowledge base
Saving technical documentation or blog posts for offline reading or AI processing
Extracting content from password-protected or paywalled sites via interactive wait mode