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-argp
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.
其他
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：1 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-argp" 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-argp" 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-argp" 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-argp" 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-argp" 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-argp
description: >
Use this skill for hands-on DOCA Arg Parser CLI work on a
shipped sample or new DOCA-using app — adding / removing /
renaming flags; wiring `doca_argp_init` → register params →
`doca_argp_start` → `doca_argp_destroy` in order; picking a
parameter type from the full public enum
(`DOCA_ARGP_TYPE_STRING`, `_INT`, `_BOOLEAN`, `_DEVICE`,
`_DEVICE_REP`, `_DOUBLE` — six values, not three);
preserving the standard `--device` / `--representor` /
`--json` (`-j`; real flag is `--json`, NOT `--json-config`) /
`--sdk-log-level` surface; or debugging
`DOCA_ERROR_BAD_STATE` / `INVALID_VALUE` / `NOT_SUPPORTED` /
`IO_FAILED` from `doca_argp_*`. Trigger on implicit
phrasings: "add a custom flag to a DOCA sample", "should I
use getopt here", "BAD_STATE registering a new param", "my
JSON config key is rejected", or "my sample's --json is
ignored". Refuse and route elsewhere for variadic-flag /
subcommand / shell-completion features, DOCA Core context,
or DOCA Log internals.
metadata:
kind: library
compatibility: >
Requires DOCA SDK installed at /opt/mellanox/doca on Linux
(Ubuntu 22.04/24.04 or RHEL/SLES) with a BlueField DPU or
ConnectX NIC attached. Reads the user's local install via
`pkg-config doca-argp` and inspects
/opt/mellanox/doca/{lib,include,samples,applications}.DOCA Arg Parser
Where to start: This skill assumes DOCA is already installed
and the user is doing hands-on CLI work on a DOCA sample or
new DOCA-using app. Open TASKS.md if the user wants
to do something (configure / build / modify / run / test /
debug); open CAPABILITIES.md when the
question is what can the Arg Parser express on this version. If
the user has not installed DOCA yet, route to
doca-setup first. If the user is
about to rewrite a sample's CLI with getopt / argparse /
custom parsing instead of reusing the Arg Parser, read the
load-bearing rule in
CAPABILITIES.md ## Capabilities and modes
before any code change.
Example questions this skill answers well
The CLASSES of Arg Parser questions this skill is built to answer, each with one worked example. The agent should treat the class as the load-bearing piece — the worked example is a single instance.
- "How do I add a new flag to a DOCA sample without breaking
the standard CLI?" — worked example: "add
--my-flagto/opt/mellanox/doca/samples/doca_dma/dma_local_copy/so the sample still accepts--device <PCI>and--sdk-log-level <level>the same way it did before". Answered by the reuse-the-Arg-Parser rule inCAPABILITIES.md ## Capabilities and modes- the register-before-start workflow in
TASKS.md ## modify.
- the register-before-start workflow in
- "Why does
doca_argp_param_set_*returnBAD_STATEon my second call?" — worked example: "registering a new param afterdoca_argp_starthas already parsed argv". Answered by the lifecycle order inCAPABILITIES.md ## Capabilities and modes- the error-taxonomy row in
CAPABILITIES.md ## Error taxonomyforDOCA_ERROR_BAD_STATE.
- the error-taxonomy row in
- "Can I drive a sample from a JSON file instead of a long
command line?" — worked example: "point a sample at
./my-config.jsonso the operator does not have to type out ten flags every time". Answered by the--json <path>integration inCAPABILITIES.md ## Capabilities and modes- the JSON-config-file workflow in
TASKS.md ## modifyandTASKS.md ## run.
- the JSON-config-file workflow in
- "My
--my-flag Xvalue is rejected asINVALID_VALUE— why?" — worked example: "declared the param asintbut passed--my-flag 0x40". Answered by the parameter-type table inCAPABILITIES.md ## Capabilities and modes- the type-mismatch row in
CAPABILITIES.md ## Error taxonomy.
- the type-mismatch row in
- "Is
doca-argpeven on my installed DOCA?" — worked example: "a colleague's sample mentions doca-argp but I want to confirm before I depend on it". Answered by the presence- version-detection rule in
CAPABILITIES.md ## Version compatibility, which cross-links the canonical detection chain indoca-version.
- version-detection rule in
- "Should I use doca-argp here, or is this case actually
outside its scope?" — worked example: "writing a host-side
CLI tool that never calls a
doca_*symbol". Answered by the path-selection rule inCAPABILITIES.md ## Capabilities and modesUse doca-argp when … / Do not use doca-argp when … bullets.
Audience
This skill serves external developers building or modifying
DOCA-using applications — i.e., users whose code already calls
doca_* (directly in C/C++, or through FFI/bindings from
another language) and who need the standard DOCA CLI surface so
operators of the resulting binary do not have to relearn how to
invoke each sample. It is not for NVIDIA developers
contributing to the Arg Parser library itself.
Language scope. DOCA Arg Parser ships as a C library with
pkg-config module name doca-argp. The shipped samples are
written in C. C and C++ consumers are the canonical case; the
worked examples in TASKS.md assume that path. Other-language
consumers (Rust, Go, Python, …) consume the same *.so through
FFI or language-specific bindings; the skill's contribution in
that case is to keep the lifecycle, parameter-type, JSON-config,
standard-flag-surface, and error-taxonomy guidance
language-neutral, and to route the agent to the public C ABI as
the authoritative surface that any wrapper will eventually call.
When to load this skill
Load this skill when the user is doing hands-on DOCA Arg Parser work, in any language. Concretely:
- Adding, removing, or renaming a CLI flag on a shipped DOCA
sample or on a new app that wants to share the standard DOCA
CLI surface (
--device <PCI>,--representor <name>,--rep-list,--json <path>,--sdk-log-level <level>). - Wiring
doca_argp_init/doca_argp_start/doca_argp_destroyinto amain(), including the register-before-start lifecycle and the cleanup-on-exit contract. - Registering a
doca_argp_param(short name, long name, value callback, description for--help) with a parameter type drawn from the six-value public enum: string, int, boolean, device, device representor, or double. A JSON config file is an input surface for those parameters, not a parameter type. - Reading complex configurations from a JSON file via the shared
--json <path>flag instead of expanding the command line. - Confirming the build- and runtime-side Arg Parser version on
the user's install (
pkg-config --exists doca-argp,pkg-config --modversion doca-argp) before depending on it. - Debugging a
DOCA_ERROR_*returned from adoca_argp_*call (lifecycle vs. type-mismatch vs. unknown JSON key vs. unreadable file). - Designing or extending non-C bindings (Rust, Go, Python, …) that wrap the Arg Parser C ABI — for the lifecycle, parameter-type, JSON-config, and standard-flag rules the wrapper must honor.
Do not load this skill for general DOCA orientation, install
of DOCA itself, or non-Arg-Parser library questions. For those,
use
doca-public-knowledge-map.
What this skill provides
This is a thin loader. The body keeps only the orientation needed to pick the right next file. The substantive Arg-Parser-specific material lives in two companion files:
CAPABILITIES.md— what the Arg Parser can express on this version: the param-registration model, the small set of public parameter types, the standard DOCA CLI surface every sample shares, the--json <path>file integration, the register-before-start lifecycle, the Arg Parser error taxonomy (mapped onto the cross-libraryDOCA_ERROR_*set), the observability surface (the--helpoutput and the DOCA Log channel), and the safety / path-selection policy (when reusing doca-argp is mandatory; when a language-native parser is the right answer).TASKS.md— step-by-step workflows for the six in-scope Arg Parser verbs:configure,build,modify,run,test,debug. Plus aDeferred task verbsblock that points out-of-scope questions at the right next skill.
The skill assumes a host or BlueField where DOCA is already
installed at the standard location. It does not cover installing
DOCA — that path goes through
doca-setup.
What this skill deliberately does not ship
This skill is agent guidance, not a samples or templates bundle. To keep the boundary clean, it deliberately does not contain — and pull requests should not add:
- Pre-written DOCA Arg Parser usage code, in any language.
The verified Arg Parser usage is the
*_main.cfile in every shipped DOCA sample at/opt/mellanox/doca/samples/<library>/<sample>/. The agent's job is to route the user to that file and prescribe a minimum-diff modification on it via the universal modify-a-sample workflow indoca-programming-guide, layered with the Arg-Parser-specific overrides inTASKS.md ## modify. - Standalone build manifests (
meson.build,CMakeLists.txt,Cargo.toml, …) parked inside the skill. The agent constructs the build manifest in the user's project directory against the user's installed DOCA, wherepkg-config --modversion doca-argpis the source of truth. - A
samples/,bindings/, orreference/subtree of any kind. A mock or incomplete artifact in this skill's tree, even one labeled "reference", is misleading: users will read it as buildable.
Loading order
- Read this
SKILL.mdfirst to confirm the user's question is in scope. - For the param-registration model, parameter types, the
standard DOCA CLI surface, the
--json <path>rule, the register-before-start lifecycle, error taxonomy, observability, and the path-selection / safety policy, see CAPABILITIES.md. - For step-by-step workflows — configure, build, modify, run, test, debug — see TASKS.md.
Both companion files cross-link to each other,
doca-version for the canonical
version-handling rules, and
doca-public-knowledge-map
whenever the right answer is "look it up in the public docs or
the installed package layout" rather than "Arg-Parser-specific
guidance".
Related skills
doca-public-knowledge-map— the routing table for every public DOCA documentation source and the on-disk layout of an installed DOCA package. The Arg Parser URL ishttps://docs.nvidia.com/doca/sdk/DOCA-Arg-Parser/index.html; the canonical on-disk usage example is any sample's*_main.cunder/opt/mellanox/doca/samples/.doca-setup— env preparation, install verification, and the I have no install yet path with the public NGC DOCA container. This skill assumes its preconditions are satisfied.doca-version— canonical DOCA version-handling rules. This skill's## Version compatibilitycross-links the four-way match rule and adds the Arg-Parser-specific presence-check overlay.doca-structured-tools-contract— the bundle's structured-tools precedence rule (detect / prefer / fall back / report). The Command appendix in TASKS.md honors this contract.doca-programming-guide— general DOCA programming patterns shared by every library: the canonicalpkg-config+ meson build pattern, the universal modify-a-shipped-sample first-app workflow, the universal lifecycle, the cross-libraryDOCA_ERROR_*taxonomy, and the program-side debug order. This skill layers Arg-Parser specifics on top.doca-debug— the cross-cutting debug ladder (install / version / build / link / runtime / program / driver). Arg-Parser-specific debug (lifecycle violations, type-mismatch on a registered param, unknown JSON key) overlays on top of that ladder.
评论 (0)
暂无评论，成为第一个评论者吧！