leiming2333/Vision-Toolkit

A toolkit that supports multimodal capabilities and image generation, featuring MCP + Skill integration.

1Stars on the repository
3Mods indexed here, across every type
20d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

image-analysis

01

leiming2333/Vision-Toolkit

Skill Claude CodeCodex

Analyze an existing image: describe / answer questions, OCR (extract text), object detection, or compare two images for similarity. Invoke when the user asks to understand, describe, read text from, detect objects in, or compare images they already have (not generate new ones).

not rated 1 20d ago A 58 tokens original MIT

text-to-image

02

leiming2333/Vision-Toolkit

Skill Claude CodeCodex

A skill for creating images from written descriptions through several image-generation services.

not rated 1 20d ago A 49 tokens original MIT