tao-run-deft-pas — Claude Code skill for retrieval improvement
The tao-run-deft-pas skill runs repeated TAO CLIP or SigLIP training for image retrieval from labelled attributes. Use it when each training round should be evaluated against a stopping condition.
no license ★ 4,106 updated 2026-10-23
npx skills add NVIDIA/skills --skill tao-run-deft-pas -a claude-codeWhat tao-run-deft-pas does
The workflow prepares the dataset, measures retrieval before fine-tuning, identifies attribute gaps and selects caption pairs through k-NN mining. It then fine-tunes the model and measures retrieval again, with selection informed by prior rounds. Set a limit on iterations or stop against a retrieval target or a validation plateau.
Runs keep state on disk and can resume. The skill bundles scripts, templates and host adapters for Docker, SLURM, Kubernetes, Brev and virtualenv. Its control setup needs Python 3.9+ with venv, ensurepip and pip; the workflow also needs accessible NVIDIA GPUs and the PAS export archives images_raw.tar and meta.tar.gz.
Choose a supported TAO execution platform and meet its prerequisites before starting. Virtualenv has an extra requirement: CPython 3.12 profiles named pyt and ds. Without those profiles, virtualenv execution will not work. A separate source checkout is not required.
What it helps with
- measure baseline image-to-text retrieval
- locate weak attributes in a dataset
- mine caption pairs for additional training data
- repeat fine-tuning until a metric or stopping rule is met
- resume a saved PAS run
Example prompts for the agent
- Run iterative TAO CLIP retrieval improvement on my PAS data and stop at the target metric.
- Find weak attributes and caption pairs for SigLIP, then retrain within the iteration limit.
- Resume the saved PAS run and stop when validation plateaus.
How to install tao-run-deft-pas
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-pas -a claude-code2Manually: put the files in place
~/.claude/skills/tao-run-deft-pas/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/tao-run-deft-pas/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-pas -a codex2Manually: put the files in place
.agents/skills/tao-run-deft-pas/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-pas -a cursor2Manually: put the files in place
.cursor/skills/tao-run-deft-pas/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills skills/tao-run-deft-pas2Manually: put the files in place
.github/skills/tao-run-deft-pas/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill tao-run-deft-pas -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/tao-run-deft-pasManually: put the files in place
.devin/skills/tao-run-deft-pas/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-pas
How do I install tao-run-deft-pas in Claude Code?
Run npx skills add NVIDIA/skills --skill tao-run-deft-pas -a claude-code. The skill file is installed at ~/.claude/skills/tao-run-deft-pas/SKILL.md.
What does tao-run-deft-pas do?
It evaluates attribute-based image retrieval, finds weak attributes, mines caption pairs and repeats fine-tuning with a fresh evaluation. A run can stop at an iteration limit, a retrieval target or a validation plateau.
What does tao-run-deft-pas need to run?
It needs accessible NVIDIA GPUs, the images_raw.tar and meta.tar.gz PAS archives, and a supported TAO platform: Docker, SLURM, Kubernetes, Brev or virtualenv. Virtualenv also needs the pyt and ds profiles on CPython 3.12.