How this skill is triggered — by the user, by Claude, or both
Slash command
/computer-vision:cv-setupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify and install ALL Computer Vision plugin dependencies.
Verify and install ALL Computer Vision plugin dependencies.
uv is installed: uv --versionuv sync --directory "${CLAUDE_PLUGIN_ROOT}" to install all Python dependenciesuv run --directory "${CLAUDE_PLUGIN_ROOT}" python -c "from src.server import mcp; print('Server OK:', len(mcp._tool_manager._tools), 'tools registered')"powershell -Command "[Windows.Media.Ocr.OcrEngine,Windows.Foundation,ContentType=WindowsRuntime] | Out-Null; [Windows.Media.Ocr.OcrEngine]::AvailableRecognizerLanguages | Select-Object LanguageTag"Add-WindowsCapability -Online -Name "Language.OCR~~~en-US~0.0.1.0"npx claudepluginhub southlab-ai/claude-plugin-marketplace --plugin computer-visionInstalls, verifies, or refreshes the claude-evolve plugin: sets up Python venv, installs dependencies, and confirms MCP server registration.
Checks and configures motiscope — verifies ffmpeg/ffprobe installation and scaffolds optional API-key config for asset generation. Use for first-time setup or dependency troubleshooting.
Analyzes images using MiniMax vision MCP tool to describe content, extract text (OCR), and review UI mockups, charts, and photos.