Skills from NVIDIA’s repositories that passed our trust, licence and security gates. Each keeps its author’s attribution.
| 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.
NVIDIAOfficial
A guide to configuring and swapping Vision Language Models (VLM) within the VSS Alerts Blueprint.
NVIDIAOfficial
A guide to diagnosing and resolving GPU out-of-memory errors in Megatron Bridge training jobs.
NVIDIAOfficial
A guide for packaging and registering reusable NeMo Relay runtime behaviors as embedded components or dynamic plugins.
NVIDIAOfficial
A troubleshooting guide for resolving runtime integration issues with NeMo Relay.
NVIDIAOfficial
Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) customization and cloud or local deployment. Not for offline/batch speech-to-text, text-only chat or RAG, or generic Docker or CUDA work unrelated to a voice agent.
NVIDIAOfficial
Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and frozen Benchmark splits, mine real image pairs from Proxy gaps, generate AnomalyGen synthetic NG pairs, assemble a per-iteration Train JSON from both producers, train with Cosmos Framework LoRA SFT, and repeat through the selected platform's submit/status/logs/cancel contract. This migration supports bare labels only: the assistant response must be exactly OK or NG. Use for "run Cosmos3 DEFT AOI", "CR3 AOI loop", or "improve Cosmos3 PCB inspection with bare OK/NG"; do not use for rich/reasoning annotation, one-off Cosmos training, or generic anomaly generation.
NVIDIAOfficial
Benchmark LLM serving performance on NVIDIA Jetson devices across vLLM, llama.cpp, and Ollama with structured JSON output.
NVIDIAOfficial
Configure Jetson USB2 and USB3 SS ports via kernel-DT overlays for custom carrier boards.
NVIDIAOfficial
Provides guidance for using cuEquivariance JAX for equivariant polynomial operations and Flax NNX layers.
NVIDIAOfficial
A diagnostic toolkit for identifying and resolving failed or unhealthy Dynamo deployments on Kubernetes.
NVIDIAOfficial
A disciplined framework for safely upgrading, downgrading, or recovering NVIDIA DOCA software environments.
NVIDIAOfficial
Validates NVIDIA TAO DAFT dataset structures, schemas, and cross-references using the tao-daft CLI.
NVIDIAOfficial
Reconciles Jetson video codec capabilities across APIs, official samples, and documentation.
NVIDIAOfficial
Manage, configure, and troubleshoot NVIDIA RAG Blueprint deployments across Docker, Kubernetes, and library environments.
NVIDIAOfficial
Provides foundational primitives and lifecycle management for NVIDIA DOCA applications on BlueField DPUs and ConnectX NICs.
NVIDIAOfficial
Automate the integration of MIPI and GMSL camera sensors on Jetson Thor and Orin platforms via kernel-DT overlays.
NVIDIAOfficial
A guide for configuring distributed training strategies and parallelism in NeMo AutoModel.
NVIDIAOfficial
A navigation assistant for the PhysicsNeMo repository, helping users identify models, datapipes, and examples for SciML and AI4Science tasks.
NVIDIAOfficial
Orchestrate iterative DINOv3 SSL DEFT data selection and retraining workflows using Data Services.
NVIDIAOfficial
Provides guidance for offloading SHA-1, SHA-256, and SHA-512 hashing to BlueField-2 DPU hardware using the NVIDIA DOCA SHA library.
NVIDIAOfficial
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, Isaac, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.
NVIDIAOfficial
An iterative workflow for binary industrial defect detection using TAO RT-DETR and automated data mining.
NVIDIAOfficial
A guide for launching distributed Megatron-LM training jobs on SLURM clusters.
NVIDIAOfficial
Configure Jetson Orin or Thor pinmux settings from a custom carrier XLSM file.