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