AutoGineer

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

  • I4h Workflow Finetune

    NVIDIAOfficial

    Fine-tune manifest-backed GR00T or openpi remote tasks using compatible LeRobot datasets.

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

  • Tao Train Pointpillars

    NVIDIAOfficial

    Train, evaluate, and deploy PointPillars 3D object detection models for LiDAR point clouds.

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

  • Doca Perftest

    NVIDIAOfficial

    Provides guidance for running the doca_perftest RDMA benchmark tool to measure network performance metrics.

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

  • Kermt Continue Pretrain

    NVIDIAOfficial

    Orchestrates containerized continued pretraining for KERMT models on custom SMILES corpora.

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

  • Doca Rmax

    NVIDIAOfficial

    Guidance for integrating NVIDIA DOCA Rivermax to handle timing-precise media-over-IP streams on BlueField DPUs.

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

  • Tao Train Depth Anything V2

    NVIDIAOfficial

    Train, evaluate, and export Depth Anything v2 monocular depth estimation models using the NVIDIA TAO toolkit.

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

  • Cuml

    NVIDIAOfficial

    Assists with developing, debugging, and upgrading Python code using NVIDIA cuML for GPU-accelerated machine learning.

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

  • Warp Eval

    NVIDIAOfficial

    Evaluate if a code bottleneck is a suitable candidate for NVIDIA Warp acceleration.

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

  • Ethos Explore

    NVIDIAOfficial

    Captures an AI agent's intended behavior into a durable ethos.md contract through codebase analysis and a mandatory intent interview.

    Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k

  • Cuopt Numerical Optimization Formulation

    NVIDIAOfficial

    A conceptual guide for translating business problems into linear, mixed-integer, and quadratic optimization formulations.

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

  • Accelerated Computing Cudf

    NVIDIAOfficial

    Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

    Data and AIClaude CodeClaude appsOpenAI Codex+14 more
    Link-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k

  • Jetson Video Setup

    NVIDIAOfficial

    Inspect, install, and verify NVIDIA Video Codec SDK and PyNvVideoCodec readiness on Jetson devices.

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

  • Nvidia Ontology Query

    NVIDIAOfficial

    A workflow for querying and validating grounded answers from the Auto Ontology system using MCP or REST.

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

  • Nvflare Orient

    NVIDIAOfficial

    Routes ambiguous NVFLARE requests to the appropriate specialized workflow skill based on project evidence.

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

  • Doca Telemetry

    NVIDIAOfficial

    Read hardware-counter snapshots from NVIDIA DOCA-enabled devices using per-domain telemetry reader libraries.

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

  • Tao Run Automl Deft Pipeline

    NVIDIAOfficial

    A three-phase pipeline chaining AutoML hyperparameter optimization with the DEFT iterative data-improvement loop for model refinement.

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

  • Nemo Mbridge Perf Moe Vlm Training

    NVIDIAOfficial

    Practical performance optimization and training strategies for Mixture-of-Experts (MoE) Vision Language Models (VLMs).

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

  • Tao Generate Image Grounding

    NVIDIAOfficial

    A two-step pipeline that uses vision-language models to extract referring expressions from captions and ground them to pixel-space bounding boxes.

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

  • Launch Nemo Rl

    NVIDIAOfficial

    A playbook for managing NeMo-RL training jobs and RayClusters on Kubernetes using the nrl-k8s CLI.

    Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k

  • Jetson Customize Clocks

    NVIDIAOfficial

    Configure Jetson CPU, GPU, and EMC clock ceilings and DVFS behavior by modifying BPMP DTB and nvpower.sh before flashing.

    Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
    Apache-2.0Medium riskGitHub stars of the source repository3.9k

  • Earth2studio Deterministic Forecast

    NVIDIAOfficial

    Build deterministic weather forecast inference scripts using the Earth2Studio framework.

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

  • Evo2 Nim

    NVIDIAOfficial

    Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker deployment, local forward passes, layer outputs, logits, sampled probabilities, and BioNeMo NIM workflows.

    Science and researchClaude CodeClaude appsOpenAI Codex+14 more
    Link-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k

  • Nvflare Convert Lightning

    NVIDIAOfficial

    Convert PyTorch Lightning training code into an NVFLARE federated learning job.

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

  • Dicom Metadata Extract

    NVIDIAOfficial

    Extracts metadata from DICOM files and flags potential PHI using standard tags.

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