Agent skill · nvidia
tao-run-deft-object-detection
Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images, unique-neighbor mining against a source pool, ODVG dataset staging, and retraining — repeated for a fixed number of iterations. Also prepares the source pool the loop mines from, as a separate run: Co-DETR pseudo-labeling, folding to the target classes, KITTI→COCO→ODVG conversion, and embedding. Use for prompts like "run the DEFT OD loop", "run smart data augmentation for grounding dino", "mine and retrain my detection model", "improve OD mAP with gap analysis and mining", "prep the source pool", or "pseudo-label my unlabeled images for mining"; do not use for standalone TAO training, one-off inference, or gap analysis alone.
What it needs
About 8k tokens when loaded.
What this skill does
Skill: tao-run-deft-object-detection Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery). Execution Contract Treat this as a disk-backed state machine, not as a prose recipe. 1. Preserve every explicit user value. epoch 1 means train.numepochs=1; a spec value or documented default applies only when the user did not supply that parameter. Show the source of every run parameter (user, spec, or default) in the Pre-Flight Summary. 2. After the user approves the Summary, initialize deftstate.json once with scripts/initdeftstate.py. Never hand-author or reinitialize it on resume. 3. Run every bundled or inline host-Python command through scripts/deftpython.sh. On startup, after context compaction, before every stage, and before any completion claim, run: If it prints DEFTRUNSTATUS=INVALID, stop and repair the listed disk inconsistency; do not launch another stage. Read the path printed as readbeforeaction before continuing. 4. Invoke the mapped underlying skill after reading the DEFT overlay. Do not replace a missing or unread stage reference, or a failed skill call, with guessed shell commands, inline Python, a different output tree, or fabricated data. 5. Commit every stage with scripts/commitstage.py; it verifies artifacts, updates deftstate.json, appends exactly one ordered looplog.jsonl event, and rolls back if its audit fails. 6. Claim the loop complete only when this exits zero: Context Discipline Load references just in time. Run the audit, read only its readbeforeaction file and the current stage's named section, then act. Never preload all references. Redirect verbose train, inference, and Docker output to files. Inspect at most the final 40 lines or a one-line artifact check; never print a full spec, state file, or loop log into the conversation. A Skill-tool call loads stage instructions; it does not start a background orchestrator. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/tao-run-deft-object-detection