“无善无恶心之体，有善有恶意之动，知善知恶是良知，为善去恶是格物” -- 王阳明
yejinlei publishes skills that help an AI agent extract text from scanned PDFs and image files such as JPG, PNG, TIFF and WEBP, using Python tooling including PyMuPDF for page rendering and OCR engines like RapidOCR and PaddleOCR. The skills focus on bilingual Chinese and English recognition, and the most popular one is designed to produce output that works with the same scanned documents in Adobe Acrobat and PdfCraft.
Pdf Ocr Skill
1 skills · 13 stars · MIT
OCR scanned .pdf files to extract text, Adobe Acrobat and PdfCraft Pull Chinese and English text from scanned PDFs and images with local OCR