Analyzes and describes visual content from images and PDF files using the Gemini 1.5 Flash vision model.
The AI Image & PDF Analyzer is a specialized Claude Code skill that integrates Gemini 1.5 Flash to provide rapid visual understanding of local files. It enables developers to perform high-accuracy OCR, identify UI components in design mockups, and interpret complex diagrams or icons directly from the terminal. By bridging the gap between visual assets and text-based coding workflows, it streamlines tasks like frontend implementation from screenshots and data extraction from scanned documents within the Kakutey bookkeeping ecosystem.
Key Features
01Seamless integration with Claude Code via localized Python CLI scripts
02Advanced OCR capabilities for text extraction from images and PDFs
03High-speed vision analysis powered by Gemini 1.5 Flash
04Support for multiple file formats including PNG, JPG, SVG, and PDF
05Intelligent UI and layout component identification for design-to-code tasks
060 GitHub stars
Use Cases
01Converting UI design screenshots into functional frontend code structures
02Automating data entry by extracting text from scanned bookkeeping documents
03Identifying and explaining complex technical icons or architectural diagrams
