Vision Reader

Read and understand image content using vision-capable AI models or OCR. Use when the user asks to read/analyze an image, extract text from a screenshot, understand what's in a photo, do OCR on a document, or needs visual content interpreted. Supports local images and URLs.

xyva-yuangui Updated 21 repo stars
Step 1: 命名 AI 助手

File contents

xyva-yuangui/XyvaClaw commit acb0046090

Frequently asked questions

npx get-skill add xyva-yuangui/vision-reader