复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
SkillAtlasSkill 详情
nvidia-skill-finder
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
审核状态：已审核Quality 72Security 70
项目 README
来源文件：README.md
NVIDIA Agent Skills
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
📖 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 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 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.
Requires a current
skillsCLI (v1.5.16 or newer). Installing vianpx skills@latest add nvidia/skillsalways uses the latest. On older CLIs (v1.5.15 and earlier), skills may install but not appear in Claude Code — see 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.
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --yes
Replace cuopt-numerical-optimization-api with any skill name from the Skill Catalog.
Install for a Specific Agent
Use --agent to target a specific AI coding agent. Initially, we'll support common client targets, expanding the list over time. For the full list of clients supported by the spec, see the skills CLI Supported Agents table.
Claude Code
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent claude-code
Codex
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent codex
Snowflake CoCo
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent cortex
Cursor
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent cursor
Kiro
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --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 \
--agent claude-code \
--agent codex \
--agent cursor \
--agent kiro-cli
Keep Skills Up to Date
New skills land continuously, and existing ones are revised, renamed, or consolidated as the catalog evolves. Refresh what you have installed with:
npx skills update
Run it interactively and the CLI also flags skills that were removed or merged upstream (for example, when several skills are consolidated into one) and offers to remove the stale local copies. Use npx skills list to see what is installed and npx skills check to preview what is out of date first.
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
Getting Help & Contributing
Where to file an issue depends on what's broken:
- Skill content issues (a specific skill has a bug, missing functionality, or incorrect content) — file in the source repo for that product, using the per-product table below.
- Catalog issues (catalog README errors, sync workflow problems, distribution channels, signing/verification flow, docs in this repo) — file here using the catalog issue templates: Bug Report, Feature Request, or Documentation Request or Correction.
- Questions or general discussion — use Discussions. The issue tracker is reserved for bug reports, feature proposals with a design, and documentation issues.
- Security vulnerabilities — follow the disclosure process in SECURITY.md; do not open a public issue.
Per-product source repo links:
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 the required artifacts before publishing, so every skill in the catalog carries:
SKILL.md— the skill instructions consumed by the agentskill-card.md— skill identity and governance cardskill.oms.sig— detached OMS signature (verifiable againstnv-agent-root-cert.pem)- A Tier-3 evaluation dataset — accepted at
evals/evals.json,evals/*.json,eval/*.json, orbenchmark/evals.json BENCHMARK.md— generated benchmark report capturing verifiable uplift data
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
A successful verification confirms that the skill contents have not been modified since signing by NVIDIA.
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
- ✅ Sync-time compliance gates — signature drift detection and missing-artifact enforcement
- ✅ Syndication to external marketplaces — Skills.sh, Codex plugin, Claude Code plugin, ClawHub, Hermes Hub
- 🔲 Syndication to additional MCP hubs and partner channels
Repository Structure
NVIDIA/skills/
├── skills/ # NVIDIA-verified skills (count grows continuously),
│ │ synced from upstream product repos
│ ├── README.md # Browser-facing install guidance
│ ├── <product-prefix>-*/ # Flat layout — one dir per skill, product-prefixed
│ │ # e.g. aiq-*, cuopt-*, cupynumeric-*,
│ │ # dali-*, deepstream-*, dicom-*, digital-health-*,
│ │ # dynamo-*, earth2studio-*, holoscan-*, hsb-*,
│ │ # jetson-*, launch-nemo-rl, mcore-*,
│ │ # nemo-automodel-*, nemo-data-designer-plugin,
│ │ # nemo-evaluator-plugin, nemo-mbridge-* (20 skills),
│ │ # nemo-retriever, nemo-rl-* (4 skills),
│ │ # nemoclaw-user-guide, nemotron-*, nemotron-speech,
│ │ # nv-* (medical AI), physicsnemo-*, rag-*,
│ │ # skill-card-generator, tao-*, tilegym-*,
│ │ # vss-* (15 skills), accelerated-computing-cudf,
│ │ # cudaq-guide, portfolio-optimization
│ ├── omniverse-*/ # Physical AI — manually staged (see manual-components.yml)
│ └── physical-ai-*/ # Physical AI — manually staged
├── components.d/ # Product registry — one file per component, teams onboard here
│ ├── README.md # Schema and onboarding instructions
│ └── <product>.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, author verify
│ └── scripts/ # regenerate-readme.sh, build-plugins.py,
│ # manual-components.yml (temp Physical AI catalog
│ # exception, removed after Computex 2026),
│ # marketplace/metadata.json (skill metadata sidecar)
├── nv-agent-root-cert.pem # Trust anchor for OMS signature verification
├── skills.sh.json # Skills.sh marketplace grouping config
├── CHANGELOG.md
├── CONTRIBUTING.md # Contribution guidelines
├── SECURITY.md # Security reporting policy
├── CODE_OF_CONDUCT.md # Community code of conduct
├── LICENSE-APACHE # Apache 2.0 (source code)
└── LICENSE-CC-BY-4.0 # CC BY 4.0 (documentation/skills)
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 againstnv-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, orbenchmark/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.mdfile at their root. - Metadata uses YAML frontmatter with required
nameanddescriptionfields. - Skills follow a progressive disclosure model — lightweight metadata loads at startup, full instructions load on activation.
- Validate your skill using the
skills-refreference library.
License
Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
This code is dual-licensed with documentation/skills under the CC-BY-4.0 AND source code under Apache-2.0 license terms. The full license texts can be found in LICENSE-APACHE and LICENSE-CC-BY-4.0 respectively.
Agent / MCP / Skill 创作
中风险
- 来源需自行核对维护者身份。
- 包含脚本或命令调用，安装前请复核。
- 可能需要外部 token、网络权限或第三方服务。
- 未检测到高风险命令。
- 扫描发现：2 条。
Codex — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/nvidia-skill-finder" 文件夹复制到 Codex 的 skills 目录中。
- 重启 Codex 让新的 skill 生效。
Codex — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Codex 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Codex 让新的 skill 生效。
Claude Code — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/nvidia-skill-finder" 文件夹复制到 Claude Code 的 skills 目录中。
- 重启 Claude Code 让新的 skill 生效。
Claude Code — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Claude Code 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Claude Code 让新的 skill 生效。
Cursor — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/nvidia-skill-finder" 文件夹复制到 Cursor 的 skills 目录中。
- 重启 Cursor 让新的 skill 生效。
Cursor — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Cursor 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Cursor 让新的 skill 生效。
GitHub Copilot — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/nvidia-skill-finder" 文件夹复制到 GitHub Copilot 的 skills 目录中。
- 重启 GitHub Copilot 让新的 skill 生效。
GitHub Copilot — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 GitHub Copilot 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 GitHub Copilot 让新的 skill 生效。
Windsurf — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/nvidia-skill-finder" 文件夹复制到 Windsurf 的 skills 目录中。
- 重启 Windsurf 让新的 skill 生效。
Windsurf — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Windsurf 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: nvidia-skill-finder
description: >-
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.
license: CC-BY-4.0 AND Apache-2.0
metadata:
author: NVIDIA
tags:
- nvidia
- skills
- discovery
- catalog
- router
domain: agent-skillsNVIDIA Skill Finder
Purpose
Help users discover, install, and start using NVIDIA skills that may not be installed yet. Treat this skill as a stable NVIDIA capability detector and catalog router, not as a mirror of every external skill's trigger text.
Use the live catalog as the source of truth for specific skill names, descriptions, and availability. Keep only stable taxonomy guidance here.
When to Use this Skill
Use this skill to find the best NVIDIA skill for a product, task, or workflow. The user does not need to explicitly ask for a skill. If the request is about NVIDIA hardware, software, SDKs, drivers, setup, troubleshooting, or an NVIDIA-adjacent workflow, check whether the live catalog has a skill that could help before proceeding too far with general guidance.
Typical triggers:
- Asks "how do I do X" where X might be a common task that an NVIDIA skill can help with.
- Says "find a skill for X" or "is there a skill for X".
- Expresses interest in extending agent capabilities in NVIDIA domains.
- Mentions they need help with a specific NVIDIA catalog domain covered below.
- Asks about installing, configuring, troubleshooting, or using an NVIDIA product, device, SDK, or service.
Continue with this skill only when the request is plausibly related to an NVIDIA product area or taxonomy category.
Strong signals:
- The user mentions NVIDIA, CUDA, GPU acceleration, NIM, NeMo, Omniverse, OpenUSD, SimReady, cuOpt, RAPIDS/cuDF, cuPyNumeric, Dynamo, Holoscan, TensorRT, VSS, DeepStream, Jetson, JetPack, L4T, BSP, SDK Manager, TAO, NGC, NVCF, or another NVIDIA product.
- The task maps strongly to an NVIDIA catalog lane such as Agentic AI, Physical AI, Robotics, Vision AI, Conversational AI, Simulation and Modeling, Data Science, Training AI, Inference AI, Decision Optimization, GPU Development, Quantum Computing, Infrastructure, or Networking.
- The task uses distinctive phrases such as RAG/deep research, vehicle routing, LP/MILP/QP, GPU DataFrames, multi-GPU NumPy/SciPy, KV-aware routing, Jetson driver install, JetPack flashing, BSP download, SDK Manager setup, CAD-to-SimReady, OpenUSD optimization, VSS/video search/summarization, DICOM workflows, robotics simulation, Holoscan setup, or synthetic data generation.
Read references/taxonomy-routing.md only when the request is taxonomy-only, ambiguous, or needs browse/domain mapping. For obvious product-name matches, go directly to live catalog lookup.
Implicit Invocation Constraints
Implicit invocation is intentional: this skill acts as a NVIDIA capability detector and catalog router. This scopes the skill to NVIDIA relevance; it does not narrow it. Use the full trigger breadth in "When to Use this Skill" — including the softer "how do I do X" triggers and any request plausibly related to an NVIDIA product area or catalog taxonomy lane.
The gate is relevance, not consent. Do not activate for the generic software tasks in "When Not to Use this Skill" unless they also carry an NVIDIA, GPU, accelerated-computing, or distinctive NVIDIA workflow signal.
Recommending a skill is always allowed once the request is relevant. Installing
or modifying skills is not: never run an install (e.g. npx skills add) or
change agent capabilities without explicit user approval. A catalog match is
only a recommendation until the user confirms.
When Not to Use this Skill
Stay quiet when the request is generic:
- "route" means an HTTP route, Express route, file route, or request routing.
- "optimize" means ordinary web performance, CSS, bundle size, SQL tuning, or generic code cleanup.
- "deploy" means generic Kubernetes, cloud, CI/CD, or web hosting.
- "AI", "data science", or "infrastructure" appears without NVIDIA, GPU, accelerated-computing, or one of the distinctive intent signals above.
- "video" means ordinary trimming, captions, export, or social-media editing.
If relevance is uncertain, do not interrupt the user's main task. Mention the NVIDIA catalog only as an optional aside after answering, or ask one concise clarifying question if the choice materially changes the work.
Instructions
How to Help Users Find Skills - a Discovery Workflow
This skill's first job is skill discovery. For NVIDIA-related requests, do a catalog check before using general web search, NVIDIA product docs, or general product knowledge as the main answer. Product documentation can help after the catalog check, but it is not a substitute for checking the NVIDIA skills catalog.
Catalog check means one of:
npx skills add nvidia/skills --listhttps://github.com/NVIDIA/skills/tree/main/skillshttps://build.nvidia.com/skillshttps://raw.githubusercontent.com/NVIDIA/skills/main/skills.sh.json
- Check whether the relevant NVIDIA skill is already installed or already in context. If it is, hand off to that skill instead of recommending install.
- Query the live catalog before naming a specific install target or giving the main product answer. When shell access is available, attempt this command first:
npx skills add nvidia/skills --list
Use the fallback catalog sources only if the CLI is unavailable, blocked, or fails:
- https://github.com/NVIDIA/skills/tree/main/skills
- https://build.nvidia.com/skills
- https://raw.githubusercontent.com/NVIDIA/skills/main/skills.sh.json
Do not count a general web search, developer.nvidia.com product documentation, or docs.nvidia.com product documentation as the catalog check.
- Match the request against current skill names, descriptions, product groups, and skill cards. Prefer NVIDIA-verified catalog entries over memory.
- If a current catalog skill strongly matches, recommend it before continuing with general product guidance. Recommend at most three skills, ordered by confidence. For each, include: skill name, why it fits, install command, and first useful prompt.
- Ask before installing. Do not run
npx skills addunless the user approves.
Recommendation Format
For a strong match that is not installed:
The NVIDIA <product or skill family> skill could help with this. Would you like me to install <skill-name>?
Use the active agent target when known:
npx skills add nvidia/skills --skill <skill-name> --agent codex --global --yes
npx skills add nvidia/skills --skill <skill-name> --agent claude-code --global --yes
If the agent target is unknown, omit --agent and let the CLI prompt:
npx skills add nvidia/skills --skill <skill-name> --global --yes
After install, tell the user to restart or reload the agent if their client does not pick up newly installed skills immediately.
Confidence Rules
- High confidence: product name or distinctive intent maps cleanly to one current catalog skill or skill family.
- Medium confidence: taxonomy lane matches but several skills may apply. Offer a short shortlist and ask which direction matches the user's task.
- Low confidence: only generic wording matches. Do the user's task without recommending an NVIDIA skill.
Do not fabricate catalog entries or guess at skill names. If catalog lookup
fails, say the catalog could not be checked and do not name a concrete slug or
emit an npx skills add ... --skill <name> install command. Offer to share the
catalog URL, retry lookup, or continue with general help.
When No Skills are Found
Say that no strong NVIDIA catalog match was found, then either:
- search the broader ecosystem with npx skills find , or
- offer to help directly without a skill, or
- suggest creating a new skill if the workflow is recurring.
评论 (0)
暂无评论，成为第一个评论者吧！