{
  "markdown": "# MarkGrab Plugin for Claude Code\n\n> [llms.txt](llms.txt)\n\nUniversal web content extraction — any URL to LLM-ready markdown.\n\n## Skills\n\n| Skill | Description |\n|-------|-------------|\n| `extract-url` | Extract content from a web URL (HTML, YouTube, PDF) |\n| `extract-file` | Convert local PDF/DOCX to markdown |\n| `batch-extract` | Bulk extract from multiple URLs |\n\n## Requirements\n\n```bash\npip install markgrab          # core\npip install \"markgrab[all]\"   # all content types\n```\n\n## Supported Content Types\n\n- **HTML** — content density filtering, auto-fallback to Playwright for JS-heavy sites\n- **YouTube** — transcript extraction with timestamps and multi-language support\n- **PDF** — text extraction with page structure\n- **DOCX** — paragraph and heading extraction\n\n## Links\n\n- [PyPI](https://pypi.org/project/markgrab/)\n- [GitHub](https://github.com/QuartzUnit/markgrab)\n- [Documentation](https://github.com/QuartzUnit/markgrab#readme)\n\n\n---\n\n<sub>Part of the [QuartzUnit](https://github.com/QuartzUnit) ecosystem — composable Python libraries for data collection, extraction, search, and AI agent safety.</sub>\n",
  "bytes": 1123,
  "sha": "95ce0360dd091b76938511cb5cef7a1a451cdcc140f19b71e8737c5f348af190",
  "repo_slug": "quartzunit/markgrab-plugin",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_quartzunit_markgrab_plugin_markgrab_115bf2bf/readme"
}