Skip to content

NVIDIA/skills

NVIDIA Agent Skills

Official, NVIDIA-verified skills for AI agents.

NVIDIA Agent Skills Spec License

📖 Docs: docs.nvidia.com/skills  ·  📺 Livestream: From Vulnerable to Verified  ·  📝 Blog: NVIDIA Verified Agent Skills: Capability Governance for AI Agents


Skills are portable instruction sets that teach AI agents how to use NVIDIA CUDA-X libraries, AI Blueprints, and platform tools correctly. This repository is a catalog: skills are maintained in their respective product repos and mirrored here daily via an automated sync pipeline. We are making NVIDIA skills available publicly and building this catalog in the open; see the Roadmap for what is planned next.


Quickstart

Install NVIDIA skills with the default skills CLI flow:

npx skills add nvidia/skills

The CLI runs through npx and prompts you to choose a skill and install destination. You do not need to clone this repo or copy skill folders by hand.

The skill is available the next time your agent loads skills and encounters a relevant task. For example, ask your agent to "solve a linear programming problem with cuOpt" and the skill guides it through the cuOpt Python API.

Install One Skill Without Prompts

Use this when you already know the skill name and want to skip prompts.

npx skills add nvidia/skills --skill cuopt-numerical-optimization-api-python --yes

Replace cuopt-numerical-optimization-api-python with any skill name from the Skill Catalog.

Install for a Specific Agent

Use --agent to target a specific AI coding agent. These are common client targets; for the full list of supported clients, see the skills CLI Supported Agents table.

Claude Code

npx skills add nvidia/skills --skill cuopt-numerical-optimization-api-python --agent claude-code

Codex

npx skills add nvidia/skills --skill cuopt-numerical-optimization-api-python --agent codex

Cursor

npx skills add nvidia/skills --skill cuopt-numerical-optimization-api-python --agent cursor

Kiro

npx skills add nvidia/skills --skill cuopt-numerical-optimization-api-python --agent kiro-cli

Use --agent more than once to install the same skill into multiple agents.

npx skills add nvidia/skills \
  --skill cuopt-numerical-optimization-api-python \
  --agent claude-code \
  --agent codex \
  --agent cursor \
  --agent kiro-cli

Browse the Catalog

Use this when you want to see available NVIDIA skills before installing anything.

npx skills add nvidia/skills --list

For non-interactive installs, global installs, agent-specific installs, updates, removals, and fallback manual copying, see Advanced installation.


Skill Catalog

Product Description Skills Catalog Source Version
AIQ NVIDIA AI-Q Blueprint - deploy local AI-Q services and run shallow or deep research workflows as agent skills. 2 skills/aiq-research/ Source bec3c75 · 2026-05-29
cuOpt GPU-accelerated optimization — vehicle routing, linear programming, quadratic programming, installation, server deployment, and developer tools. 12 skills/cuopt-developer/ Source dd11941 · 2026-05-29
cuPyNumeric NumPy and SciPy on multi-node multi-GPU systems — install and verify cuPyNumeric for Python. 1 skills/cupynumeric-install/ Source 7774592 · 2026-05-28
DALI GPU-accelerated data loading and processing with NVIDIA DALI. 1 skills/dali-dynamic-mode/ Source b1a2cd9 · 2026-05-29
DeepStream Agentic skills for guided DeepStream development. 2 skills/deepstream-dev/ Source 3daf16a · 2026-05-28
Dynamo NVIDIA Dynamo deployment bring-up on Kubernetes — pick and deploy recipes, start router modes, validate disagg NIXL/UCX/NCCL interconnect, and triage day-2 failures. 4 skills/dynamo-interconnect-check/ Source 7ca60df · 2026-05-29
Earth2Studio Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows. 4 skills/earth2studio-data-fetch/ Source 3727653 · 2026-05-29
Megatron-Core Large-scale distributed training — model parallelism, pipeline parallelism, and mixed precision. 5 skills/mcore-create-issue/ Source 6e0d14a · 2026-05-29
NeMo AutoModel NeMo AutoModel - PyTorch-native distributed training for LLMs/VLMs with Hugging Face support, recipes, launchers, and validation workflows. 4 skills/nemo-automodel-distributed-training/ Source 7dc827c · 2026-05-29
NeMo MBridge NeMo MBridge - PyTorch-native bridge between Hugging Face and Megatron-Core for checkpoint conversion, training recipes, and NVIDIA GPU performance workflows. 20 skills/nemo-mbridge-mlm-bridge-training/ Source bc0440f · 2026-05-29
NeMo-RL RLHF training on Ray — GRPO, DPO, and SFT for LLMs and VLMs with FSDP2 and Megatron-Core. 5 skills/NeMo-RL/ Source 166ca33 · 2026-05-29
NemoClaw Secure agent sandboxing — run OpenClaw inside NVIDIA OpenShell with managed inference, policy management, remote deployment, sandbox monitoring. 10 skills/nemoclaw-user-agent-skills/ Source f81f4ac · 2026-05-29
Nemotron Author end-to-end model development, customization, evaluation, and deployment pipelines using the NVIDIA AI stack. 1 skills/nemotron-customize/ Source 306b2f1 · 2026-05-29
NVIDIA Digital Health Examples Agent skills for the clinical ASR evaluation flywheel — term curation, synthetic clinical-speech benchmark generation, KER (Keyword Error Rate) scoring, and fine-tune guidance. 4 skills/digital-health-clinical-asr-setup/ Source 404c5ca · 2026-05-28
Omniverse Omniverse USD/Kit workflows — CAD-to-SimReady conversion, realtime viewer orchestration, and USD performance tuning. 3 omniverse-cad-to-simready/ · omniverse-realtime-viewer/ · omniverse-usd-performance-tuning/
Physical AI Physical AI development — infrastructure setup for synthetic data generation, resilient scaling, and neural reconstruction (NuRec/NRE). 2 physical-ai-infrastructure-setup-and-resilient-scaling/ · physical-ai-neural-reconstruction/
PhysicsNeMo NVIDIA PhysicsNeMo - Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods. 1 skills/physicsnemo-discover/ Source 8e46db6 · 2026-05-29
RAG Blueprint RAG pipeline — deploy, configure, troubleshoot, and manage retrieval augmented generation with Docker Compose or Helm. 3 skills/rag-blueprint/ Source bed5165 · 2026-05-30
Skill Card Generator Reads an agent skill's source files and produces a skill card plus a review table. Use when a skill directory exists and a governance card needs to be generated or updated. 1 skills/skill-card-generator/ Source 09b0d6b · 2026-05-28
TileGym Tile-based GPU programming — adding new kernels, cross-framework conversion, and performance optimization. 1 skills/tilegym-adding-cutile-kernel/ Source 2bf003b · 2026-05-29

Getting Help & Contributing

For skill-related issues, feature requests, new skill ideas, discussions, and contributions — use the source repo for the relevant product:

Product Issues Discussions Contributing Security
AIQ Issues Discussions Contributing Security
cuOpt Issues Discussions Contributing Security
cuPyNumeric Issues Discussions Contributing Security
DALI Issues Discussions Contributing Security
DeepStream Issues Discussions Contributing Security
Dynamo Issues Discussions Contributing Security
Earth2Studio Issues Discussions Contributing Security
Megatron-Core Issues Discussions Contributing Security
NeMo AutoModel Issues Discussions Contributing Security
NeMo MBridge Issues Discussions Contributing Security
NeMo-RL Issues Discussions Contributing Security
NemoClaw Issues Discussions Contributing Security
Nemotron Issues Discussions Contributing Security
NVIDIA Digital Health Examples Issues Discussions Contributing Security
Omniverse
Physical AI
PhysicsNeMo Issues Discussions Contributing Security
RAG Blueprint Issues Discussions Contributing Security
Skill Card Generator Issues Discussions Contributing Security
TileGym Issues Discussions Contributing Security

For issues with this catalog repo itself (README, structure, listing a new product): open an issue here.


Verifying Skills

Every published skill ships with a detached OMS signature (skill.oms.sig). The sync pipeline drops any skill missing skill.oms.sig, skill-card.md, or evals.json before publishing, so anything in the catalog has all three artifacts.

Verify a skill against the NVIDIA trust anchor nv-agent-root-cert.pem:

pip install model-signing
model_signing verify certificate SKILL_DIR \
  --signature SKILL_DIR/skill.oms.sig \
  --certificate_chain nv-agent-root-cert.pem \
  --ignore_unsigned_files

See Verify Signed Agent Skills for signature layout, the trust pipeline, and policy options.


Roadmap

  • ✅ Public skills catalog with NVIDIA-verified skills across multiple products
  • ✅ Automated sync pipeline with skills mirrored from product repos daily
  • ✅ Security scanning for all published skills covering instruction safety and supply-chain integrity
  • ✅ Skills signing so every published skill carries a verifiable NVIDIA signature
  • ✅ Skills universal evaluation criteria and task-specific criteria
  • ✅ Skill Card with machine-readable metadata for identity, provenance, quality, and behavioral boundaries
  • 🔲 Compliance gates before external publication
  • 🔲 Syndication to external marketplaces and MCP hubs

Repository Structure

NVIDIA/skills/
├── skills/                      # Verified skills, mirrored from product repos
│   ├── README.md                 # Install guidance for people browsing this folder
│   ├── aiq-deploy/               # AIQ — deploy AI-Q services
│   ├── aiq-research/             # AIQ — research workflows
│   ├── cuopt-developer/          # cuOpt — internals & contribution
│   ├── cuopt-install/            # cuOpt — installation
│   ├── cuopt-routing-api-python/ # cuOpt — VRP/TSP routing (Python)
│   ├── dali-dynamic-mode/        # DALI — dynamic-mode pipeline authoring
│   ├── deepstream-dev/           # DeepStream — guided development
│   ├── dynamo-recipe-runner/     # Dynamo — Kubernetes recipe deploys
│   ├── nemo-automodel-*/         # NeMo AutoModel — distributed training (4 skills)
│   ├── nemoclaw-user-*/          # NemoClaw — secure agent sandboxing (10 skills)
│   ├── nemotron-customize/       # Nemotron — model customization
│   ├── rag-blueprint/            # RAG Blueprint — RAG pipeline
│   ├── skill-card-generator/     # Trustworthy-AI — skill card generation
│   └── tilegym-adding-cutile-kernel/  # TileGym — cuTile kernel authoring
│                                 # Each skill lives flat at top level (no product parent
│                                 # dir), so `npx skills add --skill <name>` resolves cleanly
├── components.d/                # Product registry — one file per component, teams onboard here
│   ├── README.md                 # Schema and onboarding instructions
│   ├── aiq.yml
│   ├── cuopt.yml
│   └── …                         # one file per registered product
├── plugins/                     # Packaged plugin distributions
│   └── nvidia-skills/            # Curated NVIDIA skills bundle (Claude Code, Codex)
├── plugins.d/                   # Plugin build registry — config for `build-plugins.py`
│   ├── README.md
│   ├── _defaults.yml
│   └── nvidia-skills.yml
├── .claude-plugin/              # Claude Code marketplace metadata
│   └── marketplace.json
├── .agents/plugins/             # Agent marketplace metadata (other clients)
│   └── marketplace.json
├── docs/                        # Long-form documentation (published via Fern)
│   ├── README.md                 # How to build the docs locally
│   ├── index.mdx
│   ├── advanced-install.mdx
│   ├── agent-skill-trust-pipeline.mdx
│   ├── release-checklist.mdx
│   ├── scanning-agent-skills.mdx
│   ├── signing-agent-skills.mdx
│   └── skill-cards.mdx
├── fern/                        # Fern docs site configuration
├── .github/
│   ├── workflows/                # Sync pipeline, plugin validation, DCO check
│   └── scripts/                  # regenerate-readme.sh, build-plugins.py
├── nv-agent-root-cert.pem       # Trust anchor for OMS signature verification
├── CHANGELOG.md
├── CONTRIBUTING.md              # Contribution guidelines
├── SECURITY.md                  # Security reporting policy
├── CODE_OF_CONDUCT.md           # Community code of conduct
└── LICENSE                      # Apache 2.0 / CC BY 4.0

Skills are maintained in their respective product repos (see the Source column in the Skill Catalog) and synced to this repo daily. Products only appear under skills/ after the sync pipeline confirms each skill carries:

  • skill.oms.sig — detached OMS-format signature (verifiable against nv-agent-root-cert.pem)
  • skill-card.md — skill identity and governance card
  • A Tier-3 evaluation dataset — accepted at evals/evals.json, evals/*.json, eval/*.json, or benchmark/evals.json

When evaluation runs produce a BENCHMARK.md, it ships alongside the skill so consumers can see verifiable benchmark uplift data.


Standards & Compatibility

This repository adheres to the Agent Skills specification:

  • Skills are portable directories with a SKILL.md file at their root.
  • Metadata uses YAML frontmatter with required name and description fields.
  • Skills follow a progressive disclosure model — lightweight metadata loads at startup, full instructions load on activation.
  • Validate your skill using the skills-ref reference library.

License

This project is dual-licensed under the Apache License 2.0 and Creative Commons Attribution 4.0 International (CC BY 4.0).

About

AI agent skills published by NVIDIA

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors