Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing).
安装
npx skills add samhvw8/dot-claude --skill ai-multimodalnpx skills add samhvw8/dot-claude --skill ai-multimodal -a claude-code -gnpx skills add samhvw8/dot-claude --skill ai-multimodal -a codex -ggemini skills install https://github.com/samhvw8/dot-claude.git --path skills/ai-multimodalgh skill install samhvw8/dot-claude ai-multimodalgit clone --depth 1 https://github.com/samhvw8/dot-claude /tmp/samhvw8__dot-claude
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/samhvw8__dot-claude/skills/ai-multimodal ~/.claude/skills/ai-multimodal # Claude Code
cp -R /tmp/samhvw8__dot-claude/skills/ai-multimodal ~/.agents/skills/ai-multimodal # Codex, Cursor, Gemini CLI, Copilot, OpenCode