Skip to content

Category

AI Skills

Skills for AI agents — Claude skills, agent skills, cursor rules and MCP servers that teach Claude Code, Codex, Cursor and other agents new tricks.

12841 apps.

AI Skills, page 100

Ranked by popularity.

4951
T

tao-run-on-kubernetes

Kubernetes execution platform

Get
4952
T

tao-run-on-slurm

Remote SLURM GPU cluster execution over SSH

Get
4953
T

tao-run-platform

TAO Execution SDK

Get
4954
T

tao-setup-nvidia-gpu-host

Host setup for TAO GPU backends

Get
4955
T

tao-train-action-recognition

Action recognition from video sequences

Get
4956
T

tao-train-bevfusion

BEVFusion for multi-sensor 3D object detection

Get
4957
T

tao-train-centerpose

CenterPose for keypoint / pose estimation

Get
4958
T

tao-train-deformable-detr

Deformable DETR for 2D object detection

Get
4959
T

tao-train-fast-foundation-stereo

Real-time stereo depth estimation using FastFoundationStereo

Get
4960
T

tao-train-foundation-stereo

Stereo depth estimation using FoundationStereo

Get
4961
T

tao-train-grounding-dino

Grounding DINO for open-set object detection

Get
4962
T

tao-train-image-classification

PyTorch-based TAO image classification

Get
4963
T

tao-train-mask-auto-encoder

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning

Get
4964
T

tao-train-mask-auto-label

MAL (Mask Auto-Label) for weakly-supervised segmentation

Get
4965
T

tao-train-mask-grounding-dino

Mask Grounding DINO for grounded instance segmentation

Get
4966
T

tao-train-metric-learning-recognition

Metric-learning recognition (ml-recog) for fine-grained visual recognition

Get
4967
T

tao-train-nvdinov2

NVDINOv2 for self-supervised visual representation learning

Get
4968
T

tao-train-ocdnet

OCDNet for scene text detection

Get
4969
T

tao-train-ocrnet

OCRNet for scene text recognition

Get
4970
T

tao-train-oneformer

OneFormer for universal image segmentation

Get
4971
T

tao-train-optical-inspection

Optical Inspection for defect detection using Siamese networks

Get
4972
T

tao-train-pointpillars

PointPillars for 3D object detection from LiDAR point clouds

Get
4973
T

tao-train-rtdetr

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection

Get
4974
T

tao-train-segformer

SegFormer for semantic segmentation

Get
4975
T

tao-train-single-step

Standard single-step train/eval/export workflow for any TAO model

Get
4976
T

tao-train-sparse4d

Sparse4D for multi-camera temporal 3D object detection and tracking

Get
4977
T

tao-train-visual-changenet

Visual ChangeNet for binary image classification

Get
4978
T

tao-validate-dataset-format

Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema

Get
4979
T

tilegym-adding-cutile-kernel

Add a new cuTile GPU kernel operator to TileGym

Get
4980
T

tilegym-converting-cutile-to-julia

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents

Get
4981
T

tilegym-converting-cutile-to-triton

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit)

Get
4982
T

tilegym-cutile-autotuning

Adding, modifying, optimizing, or debugging CuTile autotuning code

Get
4983
T

tilegym-cutile-python

Expert cuTile programming assistant

Get
4984
T

tilegym-improve-cutile-kernel-perf

Iteratively optimize cuTile kernel performance through systematic profiling

Get
4985
T

tilegym-monkey-patch-kernels-to-transformers

Integrate TileGym kernels into Hugging Face `transformers` models

Get
4986
V

vss-ask-video

Ask the VSS agent's video_understanding tool a fresh visual question about a

Get
4987
V

vss-deploy-dense-captioning

Deploying standalone RT-VLM dense captioning or calling its REST API

Get
4988
V

vss-deploy-detection-tracking-2d

Deploy, run, debug, tear down

Get
4989
V

vss-deploy-detection-tracking-3d

Deploy and operate the RTVI-CV-3D microservice as MV3DT

Get
4990
V

vss-deploy-profile

Select, configure, deploy, verify, debug, or tear down a VSS profile

Get
4991
V

vss-deploy-video-embedding

Deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding

Get
4992
V

vss-generate-video-calibration

Run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset

Get
4993
V

vss-generate-video-report

Producing a VSS analysis report

Get
4994
V

vss-manage-alerts

VSS alert workflows

Get
4995
V

vss-manage-video-io-storage

Call the VIOS REST API (sensor list, timelines, clip extraction, snapshots

Get
4996
V

vss-query-analytics

Reading video-analytics metrics, incidents, alerts, and sensor data

Get
4997
V

vss-search-archive

Run top-level VSS fusion search on archived video

Get
4998
V

vss-setup-behavior-analytics

Deploy the vss-behavior-analytics service standalone

Get
4999
V

vss-setup-video-analytics-api

Deploy the vss-video-analytics-api REST service standalone

Get
5000
V

vss-summarize-video

Summarize a recorded video via the LVS summarization microservice

Get

Other categories