Analyze images using LLM vision APIs (Anthropic Claude, OpenAI GPT-4, Google Gemini, Azure OpenAI). Use when a task requires understanding image content, describing visual elements, answering questions about images, comparing images, or extracting text from images (OCR). Provides ready-to-use scripts.
Install
npx skills add microsoft/amplifier-bundle-skills --skill image-visionnpx skills add microsoft/amplifier-bundle-skills --skill image-vision -a claude-code -gnpx skills add microsoft/amplifier-bundle-skills --skill image-vision -a codex -ggemini skills install https://github.com/microsoft/amplifier-bundle-skills.git --path skills/image-visiongh skill install microsoft/amplifier-bundle-skills image-visiongit clone --depth 1 https://github.com/microsoft/amplifier-bundle-skills /tmp/microsoft__amplifier-bundle-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__amplifier-bundle-skills/skills/image-vision ~/.claude/skills/image-vision # Claude Code
cp -R /tmp/microsoft__amplifier-bundle-skills/skills/image-vision ~/.agents/skills/image-vision # Codex, Cursor, Gemini CLI, Copilot, OpenCode