Agent 工作流
可复用的 Agent 工作流和编排模式
Skills 列表
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nvidiacuopt-skill-evolution
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
nvidiacuopt-numerical-optimization-api-cli
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS/LP/QPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from an MPS or LP file via command line.
nvidiatilegym-improve-cutile-kernel-perf
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
nvidiatao-train-nvpanoptix3d
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation
nvidiatao-train-action-recognition
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for
nvidiatao-train-reid
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different
nvidiatao-train-pose-classification
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
nvidiatao-analyze-gaps-vlm-bcq
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.
nvidiatao-train-visual-changenet
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,
nvidiatao-run-automl-deft-pipeline
Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. Use when the user asks to "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model".
nvidiatao-train-dino
DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with
nvidiatao-run-platform
TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM,
nvidiatao-run-deft-aoi
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.
nvidiatao-generate-referring-expressions
"Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
nvidiatao-train-mask-auto-label
MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations
nvidiatao-train-single-step
Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset
nvidiatao-train-rtdetr
RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with
nvidiatao-validate-dataset-format
Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do
nvidiatao-train-mask-grounding-dino
Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for
nvidiatao-mine-aoi-images
Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after `tao-route-visual-changenet-samples` when expanding a real-image augmentation queue from the mining subset.
nvidiatilegym-monkey-patch-kernels-to-transformers
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
nvidiatao-train-sparse4d
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable
nvidiatao-route-visual-changenet-samples
Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module
nvidia