Tao Train Nvdinov2
NVIDIAOfficial
NVIDIA TAO skill for self-supervised visual representation learning using NVDINOv2.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskGitHub stars of the source repository3.9k
Agent Skills
Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
Results
5813 skills
Cuequivariance Torch
NVIDIAOfficial
A guide for building and debugging equivariant neural networks using cuEquivariance and PyTorch.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Nvflare Autofl Report
NVIDIAOfficial
Generate reproducible reports and summaries for completed NVFLARE Auto-FL campaigns.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
I4h Workflow Validate
NVIDIAOfficial
Validate Isaac for Healthcare workflows by executing simulator rollouts and verifying episode success.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Deepstream Sop
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.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskHas scriptsGitHub stars of the source repository3.9k
Physical AI Neural Reconstruction
NVIDIAOfficial
A central router for managing NVIDIA Neural Reconstruction (NuRec) workflows and coordinating between specialized sibling skills.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Train Single Step
NVIDIAOfficial
A standard workflow for training, evaluating, and exporting NVIDIA TAO models in a single, non-iterative execution.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Runai Get Utilization Overview
NVIDIAOfficial
Analyze GPU utilization across Run:ai clusters to identify idle or underutilized resources.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Openfold2 Nim
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.
Science and researchClaude CodeClaude appsOpenAI Codex+14 moreLink-onlyMedium riskGitHub stars of the source repository3.9k
Complexa Sweep
NVIDIAOfficial
Orchestrate cartesian-product hyperparameter sweeps for Proteina-Complexa design pipelines.
Science and researchClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Runai Diagnose Failed Workload
NVIDIAOfficial
Diagnose terminal failures, crashes, and startup errors for Run:ai workloads.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Tao Generate Anomalies
NVIDIAOfficial
A multi-phase pipeline for fine-tuning AnomalyGen models and generating synthetic anomaly images.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Nemo Relay Instrument Context Isolation
NVIDIAOfficial
Guidelines for maintaining isolated scope stacks in concurrent NeMo Relay environments.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Train Grounding Dino
NVIDIAOfficial
A workflow for training, evaluating, and deploying Grounding DINO models for open-vocabulary object detection.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Tao Data Io
NVIDIAOfficial
A data-mover utility for TAO jobs that manages storage tiering, input staging, and output synchronization without the TAO SDK.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Jetson Package
NVIDIAOfficial
Guidelines for selecting Jetson-compatible containers, Python packages, and GPU-native ML stacks.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskHas scriptsGitHub stars of the source repository3.9k
Tao Train Pose Classification
NVIDIAOfficial
Train and deploy ST-GCN models for skeleton-based action recognition using NVIDIA TAO Toolkit.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Hsb App
NVIDIAOfficial
Discover, run, and debug Holoscan Sensor Bridge example applications on connected devkits.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
RAG Perf
NVIDIAOfficial
Performance benchmarking CLI for NVIDIA RAG Blueprint servers using config-driven profiling and load testing.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Using Ovnewton
NVIDIAOfficial
Connect the Newton physics engine to Omniverse stages for simulation and rendering synchronization.
Automation and integrationsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Doca Caps
NVIDIAOfficial
Provides guidance on using the doca_caps CLI to inspect DOCA hardware, library availability, and device capabilities.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Doca Flow
NVIDIAOfficial
Provides guidance for developing packet steering applications using the NVIDIA DOCA Flow library on supported NICs and DPUs.
Software developmentClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
Jetson Customize Uphy
NVIDIAOfficial
Configure Jetson UPHY lane allocation for Orin and Thor custom carrier boards.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k
I4h Lerobot Viz
NVIDIAOfficial
Serve and visually inspect converted LeRobot datasets in a browser for verification.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0Medium riskGitHub stars of the source repository3.9k