Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
706 skills
NVIDIAOfficial
Train and deploy ST-GCN models for skeleton-based action recognition using NVIDIA TAO Toolkit.
NVIDIAOfficial
Serve and visually inspect converted LeRobot datasets in a browser for verification.
NVIDIAOfficial
Pretrain a new KERMT chemistry model from scratch using a custom corpus.
NVIDIAOfficial
A CLI tool for ingesting, indexing, and querying document collections using NeMo Retriever.
NVIDIAOfficial
A comprehensive workflow for training, optimizing, and deploying RT-DETR real-time object detection models.
NVIDIAOfficial
Train, evaluate, and deploy OneFormer models for universal image segmentation using NVIDIA TAO.
NVIDIAOfficial
Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.
NVIDIAOfficial
Train and evaluate BEVFusion models for multi-sensor 3D object detection in autonomous driving.
NVIDIAOfficial
A workflow for finetuning NV-Generate-CTMR MR-Brain diffusion models using NIfTI training volumes.
NVIDIAOfficial
Unified frontend for training and evaluating Cosmos3 multimodal models using Cosmos Framework or Cosmos-RL backends.
NVIDIAOfficial
Manage the lifecycle of CenterPose models for 6-DoF object pose estimation using NVIDIA TAO.
NVIDIAOfficial
Guide for using NVIDIA DALI's imperative dynamic-mode API (ndd) for flexible data processing.
NVIDIAOfficial
Manage the lifecycle of Deformable DETR object detection models within the NVIDIA TAO ecosystem.
NVIDIAOfficial
Perform unique-neighbor matching for object detection datasets using NVIDIA TAO Data Services.
NVIDIAOfficial
Manage the lifecycle of Mask Grounding DINO models for open-set instance segmentation using TAO.
NVIDIAOfficial
Continual self-supervised pre-training for DINOv3 vision transformer backbones.
NVIDIAOfficial
A unified routing skill for deploying, running, and testing NVIDIA Nemotron Speech (Riva) NIMs for ASR, TTS, and NMT tasks.
NVIDIAOfficial
A workflow for designing and generating synthetic datasets using the Data Designer library.
NVIDIAOfficial
Masked Auto-Encoder (MAE) tool for self-supervised visual representation learning, pretraining, and fine-tuning within the TAO ecosystem.
NVIDIAOfficial
Define equivariant groups, irreps, and tensor products for NumPy-based mathematical modeling.
NVIDIAOfficial
Manage Cosmos-Embed1 video-text embedding workflows for retrieval, search, and fine-tuning.
NVIDIAOfficial
Manage the lifecycle and inference requests for TAO model microservices across multiple compute platforms.
NVIDIAOfficial
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).
NVIDIAOfficial
A discovery skill for querying available TAO models, application workflows, and AutoML capabilities within the TAO Skill Bank.