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.
5813 skills
NVIDIAOfficial
Automated migration of projects and codebases from NeMo Flow to NeMo Relay.
NVIDIAOfficial
Evaluate RAG pipeline quality using filesystem-based benchmarks and RAGAS metrics.
NVIDIAOfficial
Continual self-supervised pre-training for DINOv3 vision transformer backbones.
NVIDIAOfficial
Integrate DOCA capabilities into existing DPDK applications without rewriting the data-plane.
NVIDIAOfficial
A guide for converting single-node scripts to multi-node Slurm jobs and troubleshooting distributed training failures.
NVIDIAOfficial
A unified routing skill for deploying, running, and testing NVIDIA Nemotron Speech (Riva) NIMs for ASR, TTS, and NMT tasks.
NVIDIAOfficial
Develop, test, and package external Holoscan Modules using the Holoscan CLI.
NVIDIAOfficial
Record human-led teleoperation demonstrations into HDF5 datasets for healthcare robotics workflows.
NVIDIAOfficial
Execute TAO container jobs on Kubernetes clusters using native Jobs and GPU scheduling.
NVIDIAOfficial
Set up the standalone IsaacLabTraining package from NVIDIA-ISAAC-ROS/isaac_ros_manipulation, then launch, monitor, resume, evaluate, and tune DisplayPort insertion policies without a separate Isaac Lab source installation. Use for setup and campaign planning, dependency repair, curriculum or PhysX troubleshooting, video evidence, and long GPU runs.
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
Operational guide for configuring and verifying hierarchical context parallelism in Megatron-Bridge.
NVIDIAOfficial
Deploy and interact with the NVIDIA cuOpt REST server for routing and optimization tasks.
NVIDIAOfficial
Integrates NeMo Retriever MCP tools for document searching and ingestion within agent workflows.
NVIDIAOfficial
Registers local Jetson reference documentation paths into an active target-platform profile.
NVIDIAOfficial
Guides first-time NeMo Relay users through selecting and executing the appropriate quick-start integration path.
NVIDIAOfficial
A comprehensive guide for onboarding new model architectures into the NeMo AutoModel framework.
NVIDIAOfficial
Define equivariant groups, irreps, and tensor products for NumPy-based mathematical modeling.
NVIDIAOfficial
Executes the complete Isaac for Healthcare data-to-policy pipeline from recording through checkpoint validation.
NVIDIAOfficial
Automated hyperparameter optimization for NVIDIA TAO networks using AutoMLRunner.
NVIDIAOfficial
Setup and repair the FoundationPose perception pipeline and its associated TensorRT depth engines.
NVIDIAOfficial
Generate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration. The DAG renders components in simulation, turns the renders into realistic golden images (sim2real), and uses AnomalyGen to add texture defects such as solder bridges, excess solder or missing components. Simulation can also render shift, tombstone and sideflip pose defects. Use it to build DIG payloads, pick a pipeline mode (full, simulation, sim2real or defect-only), check GPU readiness, follow a run, and match each defect image to its golden and simulated source. Not for running Simulation, Augmentation or AnomalyGen on their own.
NVIDIAOfficial
Provides guidance for implementing and debugging DOCA Ethernet packet-queue operations on NVIDIA BlueField DPUs and ConnectX NICs.