Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.
Install
npx skills add einverne/dotfiles --skill gemini-visionnpx skills add einverne/dotfiles --skill gemini-vision -a claude-code -gnpx skills add einverne/dotfiles --skill gemini-vision -a codex -ggemini skills install https://github.com/einverne/dotfiles.git --path claude/skills/gemini-visiongh skill install einverne/dotfiles gemini-visiongit clone --depth 1 https://github.com/einverne/dotfiles /tmp/einverne__dotfiles
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/einverne__dotfiles/claude/skills/gemini-vision ~/.claude/skills/gemini-vision # Claude Code
cp -R /tmp/einverne__dotfiles/claude/skills/gemini-vision ~/.agents/skills/gemini-vision # Codex, Cursor, Gemini CLI, Copilot, OpenCode