This skill provides a specialized workflow for digitizing scanned documents and ebooks into AI-ready Markdown. It leverages Baidu OCR for high-accuracy text recognition in scanned PDFs and image files (PNG/JPEG), while integrating with Calibre to handle MOBI and EPUB formats. Beyond simple text extraction, the skill intelligently formats the output by converting short titles into headers and optimizing paragraph spacing, making it an essential tool for researchers and developers who need to transform legacy file formats into clean, searchable documentation.
主要功能
01Support for base64 inline images and custom output paths
02High-accuracy character recognition via Baidu OCR backend
03Automatic Markdown formatting for headers and dialogue segments
04Seamless integration with Calibre for ebook-to-PDF pre-processing
05Supports PDF, PNG, JPEG, MOBI, and EPUB file formats
0616 GitHub stars
使用场景
01Digitizing personal EPUB or MOBI libraries for documentation and study
02Extracting structured text from screenshots of technical manuals or code
03Converting scanned research papers or textbooks into searchable Markdown notes