promptingcompany/nv-skills

1

tao-setup-nvidia-gpu-host Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.…

promptingcompany/nv-skills

39

2

tao-train-action-recognition Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classif…

promptingcompany/nv-skills

39

3

tao-train-bevfusion BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) s…

promptingcompany/nv-skills

39

4

tao-train-centerpose CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object p…

promptingcompany/nv-skills

39

5

tao-train-deformable-detr Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, ligh…

promptingcompany/nv-skills

39

6

tao-train-depth-anything-v2 Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixe…

promptingcompany/nv-skills

39

7

tao-train-dino DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising t…

promptingcompany/nv-skills

39

8

tao-train-fast-foundation-stereo Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of Foundatio…

promptingcompany/nv-skills

39

9

tao-train-foundation-stereo Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction…

promptingcompany/nv-skills

39

10

tao-train-grounding-dino Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-gui…

promptingcompany/nv-skills

39

11

tao-train-image-classification PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with dis…

promptingcompany/nv-skills

39

12

tao-train-mask-auto-encoder Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them…

promptingcompany/nv-skills

39

13

tao-train-mask-auto-label MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point…

promptingcompany/nv-skills

39

14

tao-train-mask-grounding-dino Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-s…

promptingcompany/nv-skills

39

15

tao-train-mask2former Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attent…

promptingcompany/nv-skills

39

16

tao-train-metric-learning-recognition Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based mat…

promptingcompany/nv-skills

39

17

tao-train-nvdinov2 NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teache…

promptingcompany/nv-skills

39

18

tao-train-nvpanoptix3d NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic,…

promptingcompany/nv-skills

39

19

tao-train-ocdnet OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable bin…

promptingcompany/nv-skills

39

20

tao-train-ocrnet OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and atten…

promptingcompany/nv-skills

39

21

tao-train-oneformer OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single archi…

promptingcompany/nv-skills

39

22

tao-train-optical-inspection Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects,…

promptingcompany/nv-skills

39

23

tao-train-pointpillars PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-b…

promptingcompany/nv-skills

39

24

tao-train-reid Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera vi…

promptingcompany/nv-skills

39

25

tao-train-rtdetr RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive …

promptingcompany/nv-skills

39

26

tao-train-segformer SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction,…

promptingcompany/nv-skills

39

27

tao-train-single-step Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without…

promptingcompany/nv-skills

39

28

tao-train-sparse4d Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention ac…

promptingcompany/nv-skills

39

29

tao-train-visual-changenet Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluat…

promptingcompany/nv-skills

39

30

tao-validate-dataset-format Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do not u…

promptingcompany/nv-skills

39

31

tilegym-adding-cutile-kernel Add a new cuTile GPU kernel operator to TileGym.

promptingcompany/nv-skills

39

32

tilegym-converting-cutile-to-julia Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-…

promptingcompany/nv-skills

39

33

tilegym-converting-cutile-to-triton Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cud…

promptingcompany/nv-skills

39

34

tilegym-cutile-autotuning Use when adding, modifying, optimizing, or debugging CuTile autotuning code.

promptingcompany/nv-skills

39

35

tilegym-cutile-python Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model w…

promptingcompany/nv-skills

39

36

tilegym-improve-cutile-kernel-perf Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and …

promptingcompany/nv-skills

39

37

tilegym-monkey-patch-kernels-to-transformers Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain…

promptingcompany/nv-skills

39

38

vss-ask-video Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for…

promptingcompany/nv-skills

39

39

vss-deploy-dense-captioning Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams,…

promptingcompany/nv-skills

39

40

vss-deploy-detection-tracking-2d Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection…

promptingcompany/nv-skills

39

41

vss-deploy-detection-tracking-3d Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fus…

promptingcompany/nv-skills

39

42

vss-deploy-profile Use to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not…

promptingcompany/nv-skills

39

43

vss-deploy-video-embedding Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers…

promptingcompany/nv-skills

39

44

vss-generate-video-calibration Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when…

promptingcompany/nv-skills

39

45

vss-generate-video-report Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics.…

promptingcompany/nv-skills

39

46

vss-manage-alerts Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries…

promptingcompany/nv-skills

39

47

vss-manage-video-io-storage Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). N…

promptingcompany/nv-skills

39

48

vss-query-analytics Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9…

promptingcompany/nv-skills

39

49

vss-search-archive Use to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT …

promptingcompany/nv-skills

39

50

vss-setup-behavior-analytics Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not fo…

promptingcompany/nv-skills

39