{"skill":{"slug":"vision-helper","displayName":"Vision Helper — AI Image Analysis","summary":"Analyze images using local or cloud vision models via Ollama to identify content, UI elements, screenshots, or extract text with OCR support.","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":38,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1777372807276,"updatedAt":1777373806538},"latestVersion":{"version":"1.0.0","createdAt":1777372807276,"changelog":"- Initial release of Vision Helper, an image analysis skill using local or cloud vision models via Ollama.\n- Supports analyzing images, UI elements, screenshots, and performing OCR with extended timeout for cloud models (up to 180 seconds).\n- Bypasses built-in image tool limitations, including path restrictions and short timeouts.\n- Provides CLI and conversational usage examples, including workflows for browser, desktop, and game UI screenshots.\n- Allows easy switching between multiple supported local and cloud vision models via environment variables.\n- Supports various image formats and directory paths for flexible screenshot handling.","license":"MIT-0"},"metadata":null,"owner":{"handle":"ravenquasar","userId":"s17drtcv3zq9axeqrjg3fh8e6d85pc2h","displayName":"U3UT7","image":"https://avatars.githubusercontent.com/u/28983534?v=4"},"moderation":null}