Vision Tools
Anionex/agent-vision-toolkitLocal vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.
At a glance
Manual install
Advanced Python
Auth required
Actively maintained
Install
git clone --depth 1 https://github.com/Anionex/agent-vision-toolkit
cp -r agent-vision-toolkit/skills/vision-tools ~/.claude/skills/vision-tools
Can use
Not declared by the author
Requirements
Python
Works with
Claude CodeAPIIDE
Setup, runtime and requirements describe Anionex/agent-vision-toolkit, the repo this skill ships in.