NVIDIAOfficial

@NVIDIA on GitHub

Skills from NVIDIA’s repositories that passed our trust, licence and security gates. Each keeps its author’s attribution.

Sources and trust

Repository	Tier	Verdict	Authorship	Checked	Skills
NVIDIA/skills	Vendor	Approved · created 2026-02-25, pushed 2026-11-06, 3888 stars	Written in-house	2026-11-07	431

Files are mirrored only where the licence allows redistribution; otherwise we link to the source.

431 published skills

Tao Train Dinov3
NVIDIAOfficial
Continual self-supervised pre-training for DINOv3 vision transformer backbones.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Doca Dpdk Bridge
NVIDIAOfficial
Integrate DOCA capabilities into existing DPDK applications without rewriting the data-plane.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Mbridge Multi Node Slurm
NVIDIAOfficial
A guide for converting single-node scripts to multi-node Slurm jobs and troubleshooting distributed training failures.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemotron Speech
NVIDIAOfficial
A unified routing skill for deploying, running, and testing NVIDIA Nemotron Speech (Riva) NIMs for ASR, TTS, and NMT tasks.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Holoscan Module Lifecycle
NVIDIAOfficial
Develop, test, and package external Holoscan Modules using the Holoscan CLI.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
I4h Workflow Dataset Teleop
NVIDIAOfficial
Record human-led teleoperation demonstrations into HDF5 datasets for healthcare robotics workflows.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Run On Kubernetes
NVIDIAOfficial
Execute TAO container jobs on Kubernetes clusters using native Jobs and GPU scheduling.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Isaac Cable Insertion Policy Training
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.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
Data Designer
NVIDIAOfficial
A workflow for designing and generating synthetic datasets using the Data Designer library.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Tao Train Mask Auto Encoder
NVIDIAOfficial
Masked Auto-Encoder (MAE) tool for self-supervised visual representation learning, pretraining, and fine-tuning within the TAO ecosystem.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Mbridge Perf Hierarchical Context Parallel
NVIDIAOfficial
Operational guide for configuring and verifying hierarchical context parallelism in Megatron-Bridge.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Cuopt Server API Python
NVIDIAOfficial
Deploy and interact with the NVIDIA cuOpt REST server for routing and optimization tasks.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Nemo Retriever MCP
NVIDIAOfficial
Integrates NeMo Retriever MCP tools for document searching and ingestion within agent workflows.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Jetson Link Docs
NVIDIAOfficial
Registers local Jetson reference documentation paths into an active target-platform profile.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Relay Get Started
NVIDIAOfficial
Guides first-time NeMo Relay users through selecting and executing the appropriate quick-start integration path.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Automodel Model Onboarding
NVIDIAOfficial
A comprehensive guide for onboarding new model architectures into the NeMo AutoModel framework.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Cuequivariance
NVIDIAOfficial
Define equivariant groups, irreps, and tensor products for NumPy-based mathematical modeling.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
I4h Workflow E2e
NVIDIAOfficial
Executes the complete Isaac for Healthcare data-to-policy pipeline from recording through checkpoint validation.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Run Automl
NVIDIAOfficial
Automated hyperparameter optimization for NVIDIA TAO networks using AutoMLRunner.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Foundationpose Setup
NVIDIAOfficial
Setup and repair the FoundationPose perception pipeline and its associated TensorRT depth engines.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Cdf Defect Image Generation
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.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
Doca Eth
NVIDIAOfficial
Provides guidance for implementing and debugging DOCA Ethernet packet-queue operations on NVIDIA BlueField DPUs and ConnectX NICs.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Relay Plugin Observability
NVIDIAOfficial
Configure observability, telemetry, and event export for NeMo Relay applications.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Mcore Create Issue
NVIDIAOfficial
Automates the triage of failing GitHub Actions jobs into structured bug reports.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k