markgrab
QuartzUnit v0.1.1
Universal web content extraction — convert any URL to clean, LLM-ready markdown. Supports HTML pages (with content density filtering and auto-fallback to Playwright for JS-heavy sites), YouTube tra...
From the developer
License
MIT
Works with
Claude Code
Description
From the marketplace listing
Universal web content extraction — convert any URL to clean, LLM-ready markdown. Supports HTML pages (with content density filtering and auto-fallback to Playwright for JS-heavy sites), YouTube transcripts, PDF, and DOCX. Provides both MCP tools (extract_url, extract_multiple) for automatic invocation and skills for manual use. Built on httpx and BeautifulSoup, with optional Playwright browser rendering. Available on PyPI: pip install markgrab
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Fetch web pages and convert HTML to clean, LLM-optimized Markdown. Extracts article content, strips boilerplate, estimates token count. N...
Shared terms: clean, content, convert, html
-
The complete web toolkit for your agent. Search the web and get answers in milliseconds. Fetch any URL and get clean markdown content bac...
Shared terms: clean, content, markdown, url
-
Turn any website into clean, LLM-ready markdown or structured data. Olostep integrates powerful web scraping, crawling, search, and AI-po...
Shared terms: clean, llm, markdown, web
-
MinerU document extraction — convert PDFs, scanned documents, images, Word (DOC/DOCX), PowerPoint (PPT/PPTX), and web pages into clean Ma...
Shared terms: clean, convert, extraction, page
-
Anakin turns any website into clean, LLM-ready data directly from Claude Code. Scrape single pages or batch up to 10 URLs at once, return...
Shared terms: clean, llm, markdown, page
Keywords
Files & skills
markgrab · catalog manifest
Saved declaration
{}
markgrab · catalog manifest
Saved declaration
{
"name": "markgrab",
"source": {
"sha": "bae2938becf56db3c80da5f81b82d48813a0dc03",
"url": "https://github.com/QuartzUnit/markgrab-plugin.git",
"source": "url"
},
"homepage": "https://github.com/QuartzUnit/markgrab",
"description": "Universal web content extraction — convert any URL to clean, LLM-ready markdown. Supports HTML pages (with content\ndensity filtering and auto-fallback to Playwright for JS-heavy sites), YouTube transcripts, PDF, and DOCX. Provides\nboth MCP tools (extract_url, extract_multiple) for automatic invocation and skills for manual use. Built on httpx and\nBeautifulSoup, with optional Playwright browser rendering. Available on PyPI: pip install markgrab"
}
markgrab · catalog manifest
Saved declaration
{
"name": "markgrab",
"author": {
"url": "https://github.com/QuartzUnit",
"name": "QuartzUnit"
},
"license": "MIT",
"version": "0.1.1",
"homepage": "https://github.com/QuartzUnit/markgrab",
"keywords": [
"content-extraction",
"markdown",
"web-scraping",
"llm",
"rag",
"pdf",
"youtube"
],
"repository": "https://github.com/QuartzUnit/markgrab",
"description": "Universal web content extraction — convert any URL or document to LLM-ready markdown. Supports HTML, YouTube transcripts, PDF, and DOCX with auto-fallback and content density filtering."
}
plugin.json observed Nov 6, 2026 · 10:46 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install markgrab@claude-communityTechnical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 06:00 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: served from cache. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.