Skip to main content
skill CX Codex

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

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add NVIDIA/skills --skill tao-run-deft-pas -a claude-code
Open on GitHub

What 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-code

2Manually: put the files in place

~/.claude/skills/tao-run-deft-pas/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tao-run-deft-pas/

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.

Similar skills

SKILL.md skills catalog →
minimal-run-and-audit lllllllama minimal-run-and-audit is a Claude Code skill that captures and standardizes evidence from deep learning reproduction runs, including inference, evaluation, and smoke tests. CX Codex +1 502,400installs run-train lllllllama run-train — a skill for Claude Code, Codex, Cursor and other platforms that executes a training command and saves logs, checkpoints and metrics to train_outputs/. Runs startup verification, short-run verification, full kickoff or resume. CX Codex +1 362,700installs evomath-tao EvoScientist evomath-tao is a Claude Code skill for verifying non-trivial mathematical claims, proofs, and research conjectures. It activates on olympiad problems, theoretical statements in ML and AI, and proof audits. CX Codex +1 162installs dart-run-static-analysis dart-lang dart-run-static-analysis runs dart analyze to catch errors and dart fix --apply to resolve mechanical linter issues. Helps verify Dart code quality during development and before commits. CX Codex +1 21,200installs cloud-run-basics official google The cloud-run-basics skill helps an agent manage Cloud Run services, jobs, and worker pools when a project needs HTTP deployment, scheduled work, or pull-based background processing. CX Codex +1 17,532installs platform-apex-test-run forcedotcom platform-apex-test-run runs Apex tests via the Salesforce CLI, analyzes code coverage, and guides test-fix loops. Useful when investigating unit test failures or low coverage. CX Codex +1 7,300installs

From the same set312

The whole set →
tao-generate-anomalies tao-generate-anomalies orchestrates NVIDIA's PAIDF AnomalyGen pipeline to fine-tune defect models, generate synthetic anomaly images, and evaluate output quality. CX Codex +1 ★ 4,106repo stars portfolio-optimization portfolio-optimization is a Claude Code skill for stock portfolio analysis with Mean-CVaR and Mean-Variance methods using NVIDIA cuOpt. Calculate allocations, assess risk, or backtest. CX Codex +1 ★ 4,106repo stars warp-eval warp-eval is a Claude Code skill that checks whether a specific hot code path is suitable for NVIDIA Warp, presenting measurements and evidence rather than an adoption verdict. CX Codex +1 ★ 4,106repo stars tao-run-deft-aoi-cosmos3 tao-run-deft-aoi-cosmos3 executes iterative training workflows for Cosmos3 visual inspection models. Designed strictly for binary OK or NG verification. CX Codex +1 ★ 4,106repo stars runai-get-utilization-overview runai-get-utilization-overview is a Claude Code skill that checks whether projects and departments on a Run:ai cluster are using allocated GPUs or leaving them idle, and ranks them by utilization. CX Codex +1 ★ 4,106repo stars tao-run-on-docker tao-run-on-docker runs single-node NVIDIA TAO container tasks on a local Docker daemon or a remote GPU box over SSH without the TAO SDK. CX Codex +1 ★ 4,106repo stars rtvi-vlm-customize-model rtvi-vlm-customize-model guides VLM replacement in the VSS Alerts Blueprint and checks the three services that call the model separately. CX Codex +1 ★ 4,106repo stars tao-run-deft-cr-its-mining tao-run-deft-cr-its-mining runs an improvement loop for Cosmos Reason video classifiers, designed for binary tasks like collision detection from traffic cameras. CX Codex +1 ★ 4,106repo stars

Project sponsors

Companies that keep this analytics open