Agent skill · nvidia
tao-run-deft-pas
Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. Use when a request combines retrieval evaluation, weak-attribute or caption-pair mining, repeated retraining, and a stopping condition based on a retrieval KPI, validation plateau, or iteration budget; the customer need not know the DEFT or People Attribute Search (PAS) names. The self-contained workflow performs dataset preparation, zero-shot evaluation, attribute gap analysis, caption-space k-NN mining, history-aware selection, retraining, and re-evaluation. Treat `tao-deft-pas` as shorthand for this canonical `tao-run-deft-pas` workflow. Do not use for standalone CLIP training, one-off evaluation or embedding, generic k-NN mining, or AOI/ChangeNet DEFT workflows.
What it needs
About 11k tokens when loaded.
What this skill does
PAS DEFT Workflow Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first for host preflight, credential checks, and cross-skill discovery. Run the canonical PAS flow as one resumable, disk-backed workflow. All PAS workflow logic, templates, and host adapters ship with this skill; customers do not need a separate source checkout. The bundled scripts make stage calls deterministic without adding another orchestration layer. This skill supports every packaged TAO execution platform: Docker, SLURM, Kubernetes, Brev, and virtualenv. The workflow produces a platform-neutral, schema-validated action bundle; the selected platform skill owns native submit/status/logs/cancel and the job-record. Virtualenv execution uses separate immutable pyt and ds runtime profiles; the workspace control .venv is not an execution runtime. Entry Contract The archive-location boundary is active as soon as the user supplies a data root, archive root, or archive file path. The first and only operation allowed to enumerate or inspect that location's contents is the packaged scripts/discoverpasinputs.py invocation. Before it runs, do not use Bash, Read, Glob, list-directory tools, or agent-authored Python to inspect the location. After it runs, do not perform a second search. This is a capability boundary for the entire intake, not an ordering suggestion inside preflight. tao-deft-pas and tao-run-deft-pas select this same workflow. If the user did not choose a platform, ask once in plain text: Execution platform: Docker, SLURM, Kubernetes, Brev, and virtualenv? Never default or use an option-limited control. On resume, the immutable platform in deftstate.json is already the selection and must not be changed. Use two intake phases: 1. Perform only bounded, lightweight path discovery. Two explicit archive file paths win and suppress all archive searching. An explicit archive directory is treated as one approved search root. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/tao-run-deft-pas