Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and frozen Benchmark splits, mine real image pairs from Proxy gaps, generate AnomalyGen synthetic NG pairs, assemble a per-iteration Train JSON from both producers, train with Cosmos Framework LoRA SFT, and…
Install
npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a claude-code -gnpx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-run-deft-aoi-cosmos3gh skill install NVIDIA/skills tao-run-deft-aoi-cosmos3git clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-run-deft-aoi-cosmos3 ~/.claude/skills/tao-run-deft-aoi-cosmos3 # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-run-deft-aoi-cosmos3 ~/.agents/skills/tao-run-deft-aoi-cosmos3 # Codex, Cursor, Gemini CLI, Copilot, OpenCode