Ross ROSS = Recommend OSS · open-source software intelligence for agents

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. observed · 2026-08-28

github.com/NVIDIA/skills · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

59/100

  • Activity 99
  • Release rhythm 35
  • Longevity 13

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 189
  • days_rel: n/a
  • days_push: 8
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

3110 stars · 361 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

agent-framework prompt-engineering rag developer-tools security large-language-models developer-tools robotics gpu-computing cli cross-platform agent-skills claude-code codex cuda omniverse simulation skillspec skillspector capability-governance nvidia ai-agents nodejs

10 sources

Member repositories

RepositoryRoleHealth v2
NVIDIA/skillsmain59

For agents

markdown · JSON · MCP: product_card(name="NVIDIA/skills")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem