Extract text from scanned PDFs and images using OCR engines.
npx skills add https://github.com/yejinlei/pdf-ocr-skill --skill pdf-ocr-skill
Please help me install this Agent Skill. Skill: pdf-ocr-skill Source: https://github.com/yejinlei/pdf-ocr-skill/tree/main Command: npx skills add https://github.com/yejinlei/pdf-ocr-skill --skill pdf-ocr-skill
This Skill removes the manual effort of reading scanned PDFs and images by converting them into searchable, editable text. It is built for documents that cannot be copied directly, such as photocopies, scans, screenshots, and image-based reports.
Ask the Skill to extract text from your scanned PDF or image using the OCR engine you prefer, and it will return the recognized text with page-by-page results.
High-intent search queries and answers about installing and using this skill.
To extract text from scanned PDFs and image files, this Skill applies page-by-page OCR using engines like RapidOCR or PaddleOCR to convert image-based content into searchable, editable text.
Yes, OCR supports both Chinese and English text recognition. It processes scanned reports, books, and forms while preserving reading order and recovering layout structure where possible.
The best way to convert scanned PDFs to Markdown is by using the enhanced RapidDoc engine, which provides structured extraction and returns layout-aware output for your documents.
Yes, you can use the SiliconFlow API for OCR instead of local engines. The Skill supports engine fallback and selection between RapidOCR, PaddleOCR, RapidDoc, and the SiliconFlow API.
Yes, the Skill processes batch document sets and supports common image formats including JPG, PNG, BMP, GIF, TIFF, and WEBP, alongside standard scanned PDF files.
Local OCR engines like RapidOCR may have limitations with complex layout documents, but the Skill offers engine fallback to RapidDoc or SiliconFlow API to improve structure recovery and accuracy.
ekkus93Extract text from image files using Tesseract OCR.
srivtxExtract text from PDFs, scanned documents, and images using OCR.
jdrodriguezExtract text from scanned PDFs and images using OCR.
rickyanandaExtract text from PDFs, scans, and office documents into markdown.
