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

RepositoryTierVerdictAuthorshipCheckedSkills
NVIDIA/skillsVendorApproved · created 2026-02-25, pushed 2026-11-06, 3888 starsWritten in-house2026-11-07431

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

431 published skills

  • Nvshmem Enable Tma

    NVIDIAOfficial

    Prepare and review NVSHMEM CUDA kernels to enable TMA-backed device-side transfers.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Nemoclaw User Guide

    NVIDIAOfficial

    Provides instructions for AI agents to access and utilize canonical NemoClaw documentation and MCP server resources.

    Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Technical guidance for configuring and optimizing Mixture-of-Experts (MoE) models for long-context training.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Nvflare Fed Stats

    NVIDIAOfficial

    Automated federated statistics computation for tabular and image datasets across NVFLARE sites.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
  • Doca Setup

    NVIDIAOfficial

    Use this skill when the user is dealing with the DOCA environment around their workload — verifying an install is healthy, preparing the build env (pkg-config, headers, LD_LIBRARY_PATH, hugepages, devlink, representors), debugging env-class failures, deciding container-vs-bare-metal deployment shape, or reaching a DOCA install from a host that doesn't have one yet via the NGC DOCA container Stage-1 fallback. Trigger even when the user does not explicitly mention "DOCA setup" — typical implicit phrasings include "just got a BlueField, what now", "code is built, how to run it", "pkg-config can't find doca-flow", "no free 2048 kB hugepages", "representor X not found", "on a Mac and want to learn DOCA". Refuse and route elsewhere for library API specifics (Flow pipes, RDMA queues), the modify-a-sample first-app workflow or DOCA_ERROR_* program-side debugging, and "where is X documented" knowledge-map questions — those belong to other skills.

    Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
    Link-onlyMedium riskGitHub stars of the source repository3.9k
  • Doca Pcc Counters

    NVIDIAOfficial

    Guide for using the pcc_counters.sh script to read firmware-level PCC diagnostic counters on NVIDIA ConnectX and BlueField devices.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Mcore Split Pr

    NVIDIAOfficial

    Automates splitting large pull requests into smaller, manageable ones to minimize CODEOWNERS reviewer requirements.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Train and deploy fine-grained visual recognition models using metric learning and triplet or contrastive loss functions.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Convert Hugging Face Trainer-based training code into an NVFLARE federated learning job.

    Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
  • Nvidia App

    NVIDIAOfficial

    Manage NVIDIA App drivers, game optimizations, laptop features, and In-Game Overlay controls via MCP.

    Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Jetson Flash Image

    NVIDIAOfficial

    Flash a promoted BSP image to a Jetson device in recovery mode.

    Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Guides users through Holoscan SDK 5.x installation options when Conda packages are unavailable or unsupported.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • A top-level architectural guide for building and managing NVIDIA Omniverse USD-based realtime viewer applications.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Recommend an NVSHMEM remote transport configuration based on system hardware, installed plugins, and workload communication patterns.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
  • PyTorch-based image classification tool for training, distilling, quantizing, and deploying models using NVIDIA TAO.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Automated collection and packaging of NVSHMEM performance benchmarks and system topology evidence.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
  • Skill Card Generator

    NVIDIAOfficial

    Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.

    Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
    Link-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
  • I4h Workflow Train Rl

    NVIDIAOfficial

    Orchestrate reinforcement learning training, evaluation, and policy export for Isaac for Healthcare workflows.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Diagnose NVSHMEM runtime failures and generate structured bug reports.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues. Use when training, evaluating, exporting, or running inference for a TAO Optical Inspection model on AOI / quality-control data. Trigger phrases include "train optical inspection", "AOI defect detection", "Siamese defect classifier", "PCB / manufacturing inspection".

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
  • Train, evaluate, and deploy FoundationStereo models for stereo depth estimation and 3D reconstruction.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Provides tools for training, evaluating, and deploying the FastFoundationStereo depth estimation model within the TAO framework.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k
  • Nv Segment Ctmr

    NVIDIAOfficial

    A wrapper for running NVIDIA's NV-Segment-CTMR foundation model for CT and MRI NIfTI volume segmentation.

    Science and researchClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
  • A tool-integration skill for finetuning the NV-Generate-CTMR MAISI VAE model using NIfTI CT or MRI volumes.

    Software developmentClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k