image-sorcery

Use when the user wants to process, analyze, or manipulate images using local tools — detect objects, find items by description, crop, resize, blur, overlay, draw annotations, run OCR, or inspect metadata. Trigger phrases include "detect objects", "find in image", "crop image", "resize photo", "blur area", "add text to image", "read text from image", "overlay images", "rotate image", "draw on image", "image metadata", "annotate screenshot".