{"skill":{"slug":"opendataloader-pdf","displayName":"opendataloader-pdf","summary":"Use when parsing PDFs for RAG pipelines, extracting structured data from PDFs, or converting PDFs to Markdown/JSON with bounding boxes for AI processing","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":233,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1773971795448,"updatedAt":1773972108758},"latestVersion":{"version":"1.0.0","createdAt":1773971795448,"changelog":"- Initial release of opendataloader-pdf skill.\n- Enables PDF parsing for RAG pipelines, extracting structured data, and converting PDFs to Markdown/JSON/HTML with bounding boxes.\n- Supports Python and Node.js, with both fast local and hybrid AI (OCR, advanced extraction) modes.\n- Provides element-level data (types, content, bounding boxes, page numbers) and robust table/extraction features.\n- Includes LangChain integration and offers detailed troubleshooting guidance.","license":"MIT-0"},"metadata":null,"owner":{"handle":"emptyguo","userId":"s1795gwcdfda38hh4vrztwfc2s83hfy6","displayName":"empty_4399","image":"https://avatars.githubusercontent.com/u/33861431?v=4"},"moderation":null}