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

Hsb Ip Packetizer
NVIDIAOfficial
Configure HSB Sensor RX packetizer fields for HOLOLINK_def.svh.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Holoscan Install Container
NVIDIAOfficial
A workflow for installing and verifying the Holoscan SDK 5.x development container.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Tilegym Improve Cutile Kernel Perf
NVIDIAOfficial
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyMedium riskGitHub stars of the source repository3.9k
Tao Launch Workflow
NVIDIAOfficial
The mandatory pre-launch gate and execution contract for all TAO model workflows and actions.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Jetson Speculative Decoding
NVIDIAOfficial
Optimize Jetson vLLM inference speed using EAGLE-3 or draft-model speculative decoding.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Medtech Model Evidence Export
NVIDIAOfficial
Export medical AI inference results and evidence packs to MLflow for post-hoc tracking.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Doca Verbs
NVIDIAOfficial
Provides raw-verbs access within DOCA Core for low-level QP, CQ, and SRQ control when high-level DOCA libraries are insufficient.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Analyze Gaps Od Map
NVIDIAOfficial
Perform gap analysis on object detection models by comparing ground truth against inference annotations.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Rtvi Cv Customize Model
NVIDIAOfficial
A guide to replacing the default DeepStream CV detection model in the VSS Alerts Blueprint verification mode.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Fabric Integrate
NVIDIAOfficial
Integrate NVIDIA NeMo Fabric into applications using the typed Python SDK.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Doca Programming Guide
NVIDIAOfficial
A guide for developers building applications that consume NVIDIA DOCA libraries.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Omniverse Content Services
NVIDIAOfficial
Orchestrates USD content collaboration, data access, and 3D creation pipelines across distributed infrastructure.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Holoscan Install Wheel
NVIDIAOfficial
A workflow for installing and verifying NVIDIA Holoscan SDK 5.x Python wheels in isolated environments.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Drug Discovery Pipeline
NVIDIAOfficial
NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline using NVIDIA BioNeMo NIMs: generate drug-like molecules with GenMol, dock them to a protein target with DiffDock, then predict binding affinity with Boltz2. Use this skill whenever the user wants to generate and screen small molecule drug candidates, perform hit discovery, optimize leads against a protein target, or do virtual screening combining molecule generation, docking, and affinity prediction. Triggers on: drug discovery pipeline, hit discovery, lead optimization, virtual screening, molecule generation, molecular docking, binding affinity, GenMol, DiffDock, Boltz2, SMILES, SAFE notation, NIM microservice. This is a multi-step pipeline composing three BioNeMo NIMs.
Science and researchClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyMedium riskGitHub stars of the source repository3.9k
Mcore Testing
NVIDIAOfficial
Comprehensive guide for managing, running, and adding unit and functional tests within the Megatron-LM framework.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Pva Doctor
NVIDIAOfficial
Validates NVIDIA PVA development environment readiness for specification, generation, build, and debug tasks.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Jetson Download Bsp
NVIDIAOfficial
Automates the secure download and staging of NVIDIA Jetson Linux BSP artifacts for Auto Setup workflows.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Rtx Remix Modding
NVIDIAOfficial
Manage and modify game assets in NVIDIA RTX Remix projects using MCP-based tool integration.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nvidia Ontology Setup
NVIDIAOfficial
Set up, troubleshoot, and connect to the Auto Ontology runtime using Helm, Docker Compose, or developer environments.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Paidf Cosmos Predict
NVIDIAOfficial
Automates video generation using PAIDF Cosmos Predict for media samples.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Doca Urom Svc
NVIDIAOfficial
Operate the DOCA UROM Service container on BlueField Arm to execute remote memory operations offloaded from a paired host.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Generate Video Reasoning Annotations
NVIDIAOfficial
A multi-step pipeline for generating Chain-of-Thought training data from raw video using VLM and LLM distillation.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Nemo Mbridge Perf Activation Recompute
NVIDIAOfficial
Optimize GPU memory usage in Megatron Bridge by configuring selective or full activation recomputation.
Software developmentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Nemotron Customize
NVIDIAOfficial
Plan and execute Nemotron model customization pipelines using repo-native steps.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k