Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance, crop_ratio) parameters. Three modes: full (Phase 0→7: finetune then generate), finetune_only (Phase 0→1: train only), inference_only (Phase 0, 2→7: generate from an existing checkpoint).
Install
npx skills add NVIDIA/skills --skill tao-generate-anomaliesnpx skills add NVIDIA/skills --skill tao-generate-anomalies -a claude-code -gnpx skills add NVIDIA/skills --skill tao-generate-anomalies -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-generate-anomaliesgh skill install NVIDIA/skills tao-generate-anomaliesgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-generate-anomalies ~/.claude/skills/tao-generate-anomalies # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-generate-anomalies ~/.agents/skills/tao-generate-anomalies # Codex, Cursor, Gemini CLI, Copilot, OpenCode