# NVIDIA/skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

Repository: https://github.com/NVIDIA/skills
Canonical: https://ross.abutalabs.com/products/nvidia-skills
Homepage: https://docs.nvidia.com/skills
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent-skills, agentic-ai, ai-agents, claude-code, codex, coding-agents, cuda, developer-tools, llm, omniverse, physical-ai, rag, robotics, simulation
Last push: 2026-08-25T21:11:32+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 13
- inputs: {"age_days": 189, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3110, forks 361 (observed 2026-08-28T04:07:43.828656+00:00)

## What it is
A catalog of NVIDIA-verified Agent Skills — portable instruction sets that teach AI coding agents like Claude Code and Codex how to use NVIDIA products (CUDA-X, Omniverse, Physical AI, robotics, RAG blueprints). It also documents a trust pipeline including SkillSpector scanning and OMS-based signing for skill verification.

## Use cases
- teach claude code to use cuda-x libraries
- install nvidia skills into codex or cursor
- run robotics and physical ai workflows with an ai agent
- solve optimization problems with cuopt via an agent
- scan agent skills for prompt injection before installing
- verify signed agent skills with omssf signatures
- set up rag pipelines using nvidia blueprints

## When to choose
- you use Claude Code, Codex, Cursor, or another Agent Skills-compatible agent with NVIDIA tooling
- you want vendor-verified, signed skills rather than community-written prompts
- you need guidance for CUDA, Omniverse, NeMo, or cuOpt workflows inside an agent

## When to avoid
- you don't use NVIDIA products or an Agent Skills-compatible coding agent
- you need a runtime agent framework rather than installable instruction sets
- you want fully offline skills — the catalog syncs from NVIDIA-hosted repos

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, prompt-engineering, rag, developer-tools, security
- domain: large-language-models, developer-tools, robotics, gpu-computing
- platform: cli, cross-platform
- tags: agent-skills, claude-code, codex, cuda, omniverse, simulation, skillspec, skillspector, capability-governance, nvidia, ai-agents, nodejs

## Member repositories
- NVIDIA/skills (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:43.828656+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:26:43.820368+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/skills (fetched 2026-08-28T04:07:43.828656+00:00, sha a7a8166c6339)
  - homepage: https://docs.nvidia.com/skills (fetched 2026-08-29T09:41:59.242727+00:00, sha b56d417b94e7)
  - site_page: https://docs.nvidia.com/skills/scanning-agent-skills (fetched 2026-08-29T09:41:59.245415+00:00, sha 02488ef7ae14)
  - site_page: https://docs.nvidia.com/skills/advanced-install (fetched 2026-08-29T09:41:59.247406+00:00, sha 174a02440d10)
  - site_page: https://docs.nvidia.com/skills/signing-agent-skills (fetched 2026-08-29T09:41:59.250642+00:00, sha 11876f632413)
  - site_page: https://www.nvidia.com/en-us/about-nvidia/privacy-policy (fetched 2026-08-29T09:41:59.253050+00:00, sha 5362c58d0750)
  - site_page: https://www.nvidia.com/en-us/about-nvidia/privacy-center (fetched 2026-08-29T09:41:59.255720+00:00, sha b098377da9cc)
  - site_page: https://www.nvidia.com/en-us/about-nvidia/terms-of-service (fetched 2026-08-29T09:41:59.257557+00:00, sha 85469b6ff0a1)
  - site_page: https://www.nvidia.com/en-us/about-nvidia/accessibility (fetched 2026-08-29T09:41:59.260133+00:00, sha 8f61ce4143ec)
  - site_page: https://www.nvidia.com/en-us/about-nvidia/company-policies (fetched 2026-08-29T09:41:59.261828+00:00, sha b169611fd7d6)
- Data as of 2026-08-30T08:39:29.467469+00:00.