The ocr-document-processor skill extracts text and structured data from scanned images, PDFs, and handwritten documents using optical character recognition (OCR), supporting specialized parsing for receipts and business cards. It serves developers and data processors who need to convert unstructured visual documents into searchable, machine-readable formats like JSON, markdown, or HTML. The skill solves the problem of recovering legible text from low-quality or skewed scans while providing confidence assessments and specialized extraction modes for common document types.
npx skills add https://github.com/dkyazzentwatwa/chatgpt-skills --skill ocr-document-processor