tao-run-deft-aoi — Claude Code skill for AOI
Runs an improvement cycle for NVIDIA TAO VisualChangeNet and ChangeNet PCB inspection models, from baseline evaluation to deployment checks against a target metric.
npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a claude-codeWhat tao-run-deft-aoi does
This skill coordinates a full AOI improvement cycle for PCB inspection models. It evaluates the baseline, investigates failure causes, creates synthetic defects with Cosmos AnomalyGen or AMP, mines data with k-NN, retrains the model, then checks deployment conditions against a customer-defined metric and constraints. Its scope is VisualChangeNet and ChangeNet workflows, not a standalone training run or one-off inference.
Progress is recorded in deft_state.json, which the workflow uses to resume from committed stages. Docker and nvidia-container-toolkit are required, and individual stages may need additional resources. Air-gapped runs rely on assets staged in advance; network access and installs are blocked in that mode. If the TAO skill bank plugin did not initialize the session, run tao-setup first.
What it helps with
- evaluate a baseline VisualChangeNet or ChangeNet model
- trace failures in PCB inspection results
- generate synthetic defects for model training
- retrain toward a target evaluation metric
- check a model against deployment conditions
Example prompts for the agent
- Run the DEFT improvement cycle for my ChangeNet AOI model and work toward the target metric.
- Evaluate my VisualChangeNet baseline, investigate inspection failures, and continue the AOI improvement workflow.
- Set up the PCB inspection workflow for an air-gapped run with assets staged in advance.
How to install tao-run-deft-aoi
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a claude-code2Manually: put the files in place
~/.claude/skills/tao-run-deft-aoi/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/tao-run-deft-aoi/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a codex2Manually: put the files in place
.agents/skills/tao-run-deft-aoi/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a cursor2Manually: put the files in place
.cursor/skills/tao-run-deft-aoi/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills tao-run-deft-aoi2Manually: put the files in place
.github/skills/tao-run-deft-aoi/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/tao-run-deft-aoiManually: put the files in place
.devin/skills/tao-run-deft-aoi/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about tao-run-deft-aoi
How do I install tao-run-deft-aoi in Claude Code?
Run npx skills add NVIDIA/skills --skill tao-run-deft-aoi -a claude-code. The skill file is placed at ~/.claude/skills/tao-run-deft-aoi/SKILL.md.
What does tao-run-deft-aoi do?
It coordinates AOI model evaluation, failure analysis, synthetic defect generation, data mining, retraining, and deployment checks against a defined metric.
What does tao-run-deft-aoi require?
It requires Docker and nvidia-container-toolkit; some workflow stages have further requirements. For air-gapped runs, stage the needed assets beforehand.