tao-run-deft-aoi-cosmos3 — Claude Code skill: setup and usage
tao-run-deft-aoi-cosmos3 executes iterative training workflows for Cosmos3 visual inspection models. Designed strictly for binary OK or NG verification.
no license ★ 4,106 updated 2026-10-23
npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a claude-codeWhat tao-run-deft-aoi-cosmos3 does
This workflow manages recurring training passes for NVIDIA Cosmos Reason 3 checkpoints. It uses Nano unless you specifically pick Edge or Super. The engine measures baseline accuracy against Benchmark and Proxy splits, gathers challenging real image pairs, creates synthetic faults using AnomalyGen, and formats JSON batches for Cosmos Framework LoRA SFT.
State transitions persist on disk inside deft_state.json. Workload orchestration relies on standard execution verbs: job submission, status polling, reading logs, and job cancellation. The agent reads durable stage records instead of guessing progress from terminal prose.
Responses must remain binary: the model produces only OK or NG labels. Running the tool requires the full TAO skill-bank tree mapped to TAO_SKILL_BANK_PATH, alongside host Python containing pyarrow, yaml, and TOML parsing support.
What it helps with
- orchestrate Cosmos3 LoRA SFT training passes for PCB inspection
- synthesize defect pairs through AnomalyGen tooling
- mine failure cases from evaluation splits
- manage multi-step state persistence via deft_state.json
Example prompts for the agent
- Run Cosmos3 DEFT AOI on the current board dataset using Nano
- Start CR3 AOI loop with the Edge checkpoint
- Improve Cosmos3 PCB inspection with bare OK/NG outputs
How to install tao-run-deft-aoi-cosmos3
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a claude-code2Manually: put the files in place
~/.claude/skills/tao-run-deft-aoi-cosmos3/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/tao-run-deft-aoi-cosmos3/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a codex2Manually: put the files in place
.agents/skills/tao-run-deft-aoi-cosmos3/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a cursor2Manually: put the files in place
.cursor/skills/tao-run-deft-aoi-cosmos3/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills skills/tao-run-deft-aoi-cosmos32Manually: put the files in place
.github/skills/tao-run-deft-aoi-cosmos3/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/tao-run-deft-aoi-cosmos3Manually: put the files in place
.devin/skills/tao-run-deft-aoi-cosmos3/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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-cosmos3
How to install tao-run-deft-aoi-cosmos3 in Claude Code?
Run npx skills add NVIDIA/skills --skill tao-run-deft-aoi-cosmos3 -a claude-code in your terminal.
Which model variants does this skill support?
It targets nvidia/Cosmos3-Nano by default, alongside explicit options for nvidia/Cosmos3-Edge and nvidia/Cosmos3-Super.
Does this workflow support detailed anomaly explanations?
No. The pipeline strictly requires bare labels where the assistant outputs either OK or NG.