Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images.
Install
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generationnpx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a claude-code -gnpx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/physical-ai-defect-image-generationgh skill install NVIDIA/skills physical-ai-defect-image-generationgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/physical-ai-defect-image-generation ~/.claude/skills/physical-ai-defect-image-generation # Claude Code
cp -R /tmp/NVIDIA__skills/skills/physical-ai-defect-image-generation ~/.agents/skills/physical-ai-defect-image-generation # Codex, Cursor, Gemini CLI, Copilot, OpenCode