Analyze images using OpenAI's Vision API. Use bash command to execute the vision script like 'bash <base_dir>/scripts/vision.sh <image> <question>'. Can understand image content, objects, text, colors, and answer questions about images.
安装
npx skills add zhayujie/CowAgent --skill openai-image-visionnpx skills add zhayujie/CowAgent --skill openai-image-vision -a claude-code -gnpx skills add zhayujie/CowAgent --skill openai-image-vision -a codex -ggemini skills install https://github.com/zhayujie/CowAgent.git --path skills/openai-image-visiongh skill install zhayujie/CowAgent openai-image-visiongit clone --depth 1 https://github.com/zhayujie/CowAgent /tmp/zhayujie__CowAgent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/zhayujie__CowAgent/skills/openai-image-vision ~/.claude/skills/openai-image-vision # Claude Code
cp -R /tmp/zhayujie__CowAgent/skills/openai-image-vision ~/.agents/skills/openai-image-vision # Codex, Cursor, Gemini CLI, Copilot, OpenCode