Vision and multimodal capabilities for Claude including image analysis, PDF processing, and document understanding. Activate for image input, base64 encoding, multiple images, and visual analysis.
Install
npx skills add TheLobbi/claude --skill vision-multimodalnpx skills add TheLobbi/claude --skill vision-multimodal -a claude-code -gnpx skills add TheLobbi/claude --skill vision-multimodal -a codex -ggemini skills install https://github.com/TheLobbi/claude.git --path .claude/skills/vision-multimodalgh skill install TheLobbi/claude vision-multimodalgit clone --depth 1 https://github.com/TheLobbi/claude /tmp/TheLobbi__claude
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/TheLobbi__claude/.claude/skills/vision-multimodal ~/.claude/skills/vision-multimodal # Claude Code
cp -R /tmp/TheLobbi__claude/.claude/skills/vision-multimodal ~/.agents/skills/vision-multimodal # Codex, Cursor, Gemini CLI, Copilot, OpenCode