Skill：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.
适用场景
教研备课
适合角色
介绍
以下内容整理自开源仓库 `NVIDIA/skills` 的 README / SKILL.md 摘要： <!-- SPDX-License-Identifier: Apache-2.0 AND CC-BY-4.0 --> <!-- Copyright (c) 2026 NVIDIA Corporation. All rights reserved. --> # NVIDIA Agent Skills **Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.** [](https://nvidia.com) [](https://agentskills.io) [](#license) > 📖 **Docs:** [docs.nvidia.com/skills](https://docs.nvidia.com/skills) · > 📺 **Livestream:** [From Vulnerable to Verified](https://www.youtube.com/watch?v=sVpKonYJ4D4&list=PL5B692fm6--vEL0FwctKghCpyEnBGAQJA&index=1) · > 📝 **Blog:** [NVIDIA Verified Agent Skills: Capability Governance for AI Agents](https://developer.nvidia.com/blog/nvidia-verified-agent-skills-provide-capability-governance-for-ai-agents/) --- Skills are portable instruction sets that teach AI agents how to use NVIDIA software optimally: Physical AI and robotics workflows, simulation, CUDA-X libraries, RAG and AI Blueprints, and platform tools. This repository is a catalog: skills are maintained in their respective product repos, and mirrored here daily via an automated sync pipeline. Skills are being added continuously, so check back for updates. We are building this infrastructure in the open, and contributions are welcome. See the [Roadmap](#roadmap) for what is planned next. --- ## Quickstart Install NVIDIA skills with the default [`skills` CLI](https://github.com/vercel-labs/skills) flow: ```bash 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. > **Requires a current `skills` CLI (v1.5.16 or newer).** Installing via `npx skills@latest add nvidia/skills` always uses the latest. On older CLIs (v1.5.15 and earlier), skills may install but not appear in Claude Code — see [Troubleshooting](docs/advanced-install.mdx#troubleshooting). 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. In Claude Code, run `/reload-skills` to load newly installed skills in your current session. ### Install One Skill Without Prompts Use this when you already know the skill name and want to skip prompts. ```bash npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --yes ``` Replace `cuopt-numerical-optimization-api` with any skill name from the [Skill Catalog](#skill-catal --- **说明**：内容由公开仓库整理，使用前请自行核对是否适合你的场景。
安装方式
1. 打开仓库：https://github.com/NVIDIA/skills 2. 查找 SKILL.md 或 README 中的安装章节 3. 克隆或下载所需 Skill 子目录到本地 skills 路径（如 `.cursor/skills/` 或 `.claude/skills/`） 4. 重启 / 重载 Agent 客户端 5. 用一条真实任务验证 Skill 是否被正确加载
适用平台
- Cursor
- Claude
- Codex