vision-tools
Too-long screenshots? Ask, box, split, trace to SVG. Local CLIs, no cloud. Six sharp tools for every image.
What does this skill do?
Local 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/S
Why is it worth installing?
Others describe; it locates, traces, and slices. Treats images as queryable data, not just pictures.
How do you install it?
git clone --depth 1 https://github.com/Anionex/agent-vision-toolkit.git Then point your agent at the skill directory.
Where does it come from?
Repository: Anionex/agent-vision-toolkit 653 stars on GitHub at the time of listing. The repository ships 1 skills in total. Homepage: https://agent-vision.anionex.me