leiming2333

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).

leiming2333/Vision-Toolkit

Skill Claude CodeCodex

Generate images from text prompts via OpenAI DALL-E / 通义万相 / Google Imagen. Invoke when the user asks to create, draw, generate, or make an image, illustration, or picture from a description.

leiming2333/Vision-Toolkit

MCP server Claude CodeCodexCursor

多模态视觉 MCP + 文生图 Skill 工具包 (OpenAI GPT-4o · 通义千问 Qwen-VL · Google Gemini · Anthropic Claude). Runs locally from the vision-toolkit npm package.