{"skill":{"slug":"ocr-document","displayName":"Ocr Document","summary":"OCR document extraction - extract text from scanned documents, photos, and images using OCR. Use when reading scanned PDFs, photographed pages, handwritten n...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":351,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1774360386179,"updatedAt":1774364812529},"latestVersion":{"version":"1.0.0","createdAt":1774360386179,"changelog":"- Initial release of ocr_document skill for OCR text extraction from scanned documents, images, and handwritten notes.\n- Supports PDF, PNG, JPG, WebP, BMP, and TIFF formats from local files or URLs.\n- No API key, signup, or authentication required.\n- Language selection available for improved accuracy; replies always match the user's language.\n- Maximum file size is 10MB or 20 pages per document.\n- Powered by the MinerU Open API CLI; installation guides provided for npm, uv, go, and direct download.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"tanis90","userId":"s17c6n53ezjj2w372fjv34m7zx83gva1","displayName":"tanis90","image":"https://avatars.githubusercontent.com/u/22654397?v=4"},"moderation":null}