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
doca-caps
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
审核状态：已审核Quality 72Security 90
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.
其他
低风险
- 来源需自行核对维护者身份。
- 未检测到明显脚本安装指令。
- 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：0 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/doca-caps" 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/doca-caps" 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/doca-caps" 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/doca-caps" 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/doca-caps" 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
license: Apache-2.0
name: doca-caps
description: >
Use this skill when the user wants to invoke the read-only
doca_caps CLI to ask what DOCA sees on this host — listing
DOCA devices and PCIe addresses, listing representor devices,
asking which DOCA libraries are available on the current OS,
checking per-device per-library capabilities, scoping output
to a specific PCIe address, or capturing a side-effect-free
capability snapshot for a debug session or install
smoke-test. Trigger even when the user does not explicitly
mention "doca_caps" or "capabilities print tool" — typical
implicit phrasings include "what does DOCA actually see on
this box", "is my BlueField PF visible to DOCA", "is Flow
available on my RHEL host", "enumerate VF representors for
pf0", "doca_caps: command not found", or "empty output for
RDMA, is the tool broken". Refuse and route elsewhere for
DOCA installation, library-internal capability matrices
(Flow pipe creation, RDMA verbs features), streaming
telemetry / DTS, or modifying the shipped binary — those
belong to other skills.
metadata:
kind: tool
compatibility: >
Requires DOCA SDK ≥ 2.6.0 installed at /opt/mellanox/doca
on Linux (Ubuntu 22.04/24.04 or RHEL/SLES) with a BlueField
DPU or ConnectX NIC; runs identically on the host or on the
BlueField Arm side. Invokes
/opt/mellanox/doca/tools/doca_caps and reads
`pkg-config doca-common` to confirm the install.DOCA Capabilities Print Tool (doca_caps)
Where to start: This is a tool skill for invoking doca_caps,
a side-effect-free CLI. Open TASKS.md and start at
## run for the documented invocations, or
## test when using doca_caps as an install
smoke-test. Open CAPABILITIES.md when the
question is what kinds of capability families doca_caps reports.
If DOCA is not installed yet, route to
doca-setup first.
Example questions this skill answers well
The CLASSES of doca_caps questions this skill is built to answer,
each with one worked example. The class is the load-bearing piece;
the worked example is one instance.
- "What DOCA devices does this host see?" — worked example: "is
my BlueField PF visible to DOCA". Answered by the device
enumeration in
CAPABILITIES.md ## Capabilities and modes- the
--list-devsinvocation inTASKS.md ## run.
- the
- "Which DOCA libraries are available on this OS?" — worked
example: "is Flow available on my RHEL host". Answered by the
library-availability surface in
CAPABILITIES.md ## Capabilities and modes- the library-listing invocation in
TASKS.md ## run.
- the library-listing invocation in
- "Does this device support library X capability Y?" — worked
example: "does this device support Flow hairpin?". Answered by
the per-device per-library capability matrix in
CAPABILITIES.md ## Capabilities and modes- the
--pci-addr-scoped invocation inTASKS.md ## run.
- the
- "What representors are visible to DOCA?" — worked example:
"enumerate VF representors for pf0". Answered by the representor
enumeration in
CAPABILITIES.md ## Capabilities and modes- the
--list-rep-devsinvocation inTASKS.md ## run.
- the
- "I want a snapshot of state to attach to my debug session." —
worked example: "save device + library + capability output to a
file". Answered by the snapshot workflow in
TASKS.md ## testand consumed bydoca-debug ## teststep 3 (read-only triple) anddoca-programming-guide ## debug. - "
doca_capsreturned nothing for capability Y — what does that mean?" — worked example: "empty output for RDMA". Answered by the empty-output interpretation rules inTASKS.md ## debug+CAPABILITIES.md ## Error taxonomy.
Audience
This skill serves external operators, developers, and AI agents who need a side-effect-free way to ask "what does DOCA see on this host?" before doing anything that changes state. Concretely:
- An external developer who installed DOCA (or is using the public NGC
DOCA container per
doca-setup ## no-install) and wants to confirm the install can see hardware before writing code. - A platform operator deploying a DOCA service who wants a documented, read-only snapshot of which DOCA libraries this host actually supports and which capabilities each DOCA device offers.
- An AI agent producing a capability snapshot artifact during the
documented setup or programming-guide debug procedures (it's listed
as the canonical first step in
doca-setup ## testanddoca-programming-guide ## debug).
It is not for users debugging doca_caps itself, and not a
substitute for the live public Capabilities Print Tool guide.
doca_caps is shipped as a tool (a single CLI binary), not a
library you link against. The skill uses the same kind: tool
three-file shape as the rest of the bundle so the agent's task-verb
contract (configure / build / modify / run / test / debug) is uniform
across libraries, services, and tools — even when individual verbs
collapse to a routing stub for a shipped read-only binary.
When to load this skill
Load this skill when the user is — or the agent needs to — invoke
doca_caps on a real host with DOCA installed (or inside the public
NGC DOCA container). Concretely:
- Running
doca_caps --list-devsto enumerate DOCA devices. - Running
doca_caps --list-rep-devsto enumerate representor devices. - Scoping output to a specific PCIe address with
--pci-addr. - Listing the DOCA libraries the install reports as available on the current OS.
- Listing the available DOCA logger names.
- Capturing a documented, side-effect-free capability snapshot as
prerequisite evidence for later
## debugworkflows.
Do not load this skill for general DOCA orientation, library API
work, or installation. For those, use
doca-public-knowledge-map,
the matching libs/<library> skill, or
doca-setup.
What this skill provides
This is a thin loader. Substantive material lives in two companion files:
CAPABILITIES.md— whatdoca_capsreports (the five documented capability families: devices, representors, libraries, library capabilities, loggers), version availability and execution environment, the tool's narrow error surface, its observability role inside other skills' workflows, and its read-only safety posture.TASKS.md— step-by-step workflows for the in-scope task verbs:configure(route to install),build(route to install),modify(refuse),run(the documented invocations),test(capability snapshot as install smoke-test),debug(what to do when the tool reports nothing or fails), plus aDeferred task verbsblock routing out-of-scope questions.
The skill assumes a host where DOCA is already installed (or the public
NGC DOCA container is running) and the operator has whatever
permissions the public guide requires for doca_caps to enumerate
devices on their platform.
What this skill deliberately does not ship
This skill is agent guidance, not a samples or scripts bundle. To keep the boundary clean, it deliberately does not contain — and pull requests should not add:
- Pre-baked example output. Output is install- and hardware-specific. A captured example pinned to one platform and one DOCA version misleads operators on a different platform / version.
- Wrappers, parsers, or scripts in any language that consume
doca_capsoutput. The output format is documented; if a user wants to script against it, the right answer is "read the live guide, write the parser against your installed version". - A
samples/orreference/subtree. This is a thin loader for a documented CLI; substantive material lives on the public page and in--help.
Loading order
- Read this
SKILL.mdfirst to confirm the user's question is in scope (the user actually wants to invokedoca_caps, not learn about DOCA in general). - For what
doca_capsreports, version availability, error surface, and safety posture, see CAPABILITIES.md. - For the documented invocations and the capability-snapshot
workflow —
configure,build,modify,run,test,debug— see TASKS.md.
Related skills
doca-public-knowledge-map— routing to the public Capabilities Print Tool guide and the rest of the public DOCA documentation set.doca-setup— env preparation, install verification (doca_capsis the canonical first step there), and the I have no install yet path with the public NGC DOCA container.doca-programming-guide— cross-library programming patterns, including the## debugprocedure where the saveddoca_capssnapshot is consumed.- The matching
libs/<library>skill — for fine-grained, library-specific capability questions that go beyond whatdoca_capsexposes.
评论 (0)
暂无评论，成为第一个评论者吧！