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.
git clone https://github.com/NVIDIA/skills && cp skills/*.md ~/.claude/agents/Subagents overview
What people ask about skills
What is NVIDIA/skills?
+
NVIDIA/skills is subagents for the Claude AI ecosystem. 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. It has 2.6k GitHub stars and was last updated today.
How do I install skills?
+
You can install skills by cloning the repository (https://github.com/NVIDIA/skills) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is NVIDIA/skills safe to use?
+
NVIDIA/skills has not been audited yet by our security agent. Review the original repository on GitHub before using it in production.
Who maintains NVIDIA/skills?
+
NVIDIA/skills is maintained by NVIDIA. The last recorded GitHub activity is from today, with 15 open issues.
Are there alternatives to skills?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy skills to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/nvidia-skills)<a href="https://claudewave.com/repo/nvidia-skills"><img src="https://claudewave.com/api/badge/nvidia-skills" alt="Featured on ClaudeWave: NVIDIA/skills" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.