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
Generate reproducible reports and summaries for completed NVFLARE Auto-FL campaigns.
NVIDIAOfficial
Validate Isaac for Healthcare workflows by executing simulator rollouts and verifying episode success.
NVIDIAOfficial
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
NVIDIAOfficial
A central router for managing NVIDIA Neural Reconstruction (NuRec) workflows and coordinating between specialized sibling skills.
NVIDIAOfficial
A standard workflow for training, evaluating, and exporting NVIDIA TAO models in a single, non-iterative execution.
NVIDIAOfficial
Analyze GPU utilization across Run:ai clusters to identify idle or underutilized resources.
NVIDIAOfficial
Use this skill for OpenFold2, NVIDIA's BioNeMo NIM microservice for monomer protein structure prediction. Invoke whenever the user mentions OpenFold2, AlphaFold2-like monomer folding, protein sequence-to-structure prediction, A3M MSAs, mmCIF templates, hosted NVIDIA API calls, or local Docker deployment.
NVIDIAOfficial
Orchestrate cartesian-product hyperparameter sweeps for Proteina-Complexa design pipelines.
NVIDIAOfficial
Diagnose terminal failures, crashes, and startup errors for Run:ai workloads.
NVIDIAOfficial
A multi-phase pipeline for fine-tuning AnomalyGen models and generating synthetic anomaly images.
NVIDIAOfficial
Guidelines for maintaining isolated scope stacks in concurrent NeMo Relay environments.
NVIDIAOfficial
A workflow for training, evaluating, and deploying Grounding DINO models for open-vocabulary object detection.
NVIDIAOfficial
A data-mover utility for TAO jobs that manages storage tiering, input staging, and output synchronization without the TAO SDK.
NVIDIAOfficial
Guidelines for selecting Jetson-compatible containers, Python packages, and GPU-native ML stacks.
NVIDIAOfficial
Train and deploy ST-GCN models for skeleton-based action recognition using NVIDIA TAO Toolkit.
NVIDIAOfficial
Discover, run, and debug Holoscan Sensor Bridge example applications on connected devkits.
NVIDIAOfficial
Performance benchmarking CLI for NVIDIA RAG Blueprint servers using config-driven profiling and load testing.
NVIDIAOfficial
Connect the Newton physics engine to Omniverse stages for simulation and rendering synchronization.
NVIDIAOfficial
Provides guidance on using the doca_caps CLI to inspect DOCA hardware, library availability, and device capabilities.
NVIDIAOfficial
Provides guidance for developing packet steering applications using the NVIDIA DOCA Flow library on supported NICs and DPUs.
NVIDIAOfficial
Configure Jetson UPHY lane allocation for Orin and Thor custom carrier boards.
NVIDIAOfficial
Serve and visually inspect converted LeRobot datasets in a browser for verification.
NVIDIAOfficial
Pretrain a new KERMT chemistry model from scratch using a custom corpus.
NVIDIAOfficial
Performs deep, image-evidence-driven root cause analysis for NVIDIA TAO Visual ChangeNet classification experiments.