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
jetson-init-image
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
审核状态：已审核Quality 72Security 52
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
高风险
- 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。
- 存在潜在风险命令，请谨慎安装。
- 扫描发现：3 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/jetson-init-image" 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/jetson-init-image" 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/jetson-init-image" 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/jetson-init-image" 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/jetson-init-image" 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: jetson-init-image
description: >-
Extract Jetson Linux + sample-rootfs tarballs and run
apply_binaries.sh for the active target, then record bsp_image in
the profile. Use after jetson-init-target; not for source-tree
setup.
version: 0.0.1
license: "Apache-2.0"
metadata:
data-classification: public
author: "Jetson Team"
tags:
- bsp
- image
- bootstrap
domain: metaInitialize BSP Image
Output is only bsp_image: in the active profile: derived version
plus root_path only when overriding <workspace>/Image.
When to invoke
- The user asks to extract, prepare, or initialize the BSP image.
- A downstream skill reports missing
<bsp_image.root_path>/Linux_for_Tegra/. - The active profile has no
bsp_image:block yet.
Procedure
Resolve target and image path
Resolve the active profile per
../../context/target-platform-contract.md.
Refuse if there is no active profile or reference_devkit: is missing.
<workspace> is the parent of the active profile's target-platform/
directory. <bsp_image.root_path> defaults to <workspace>/Image.
| Profile state | Action |
|---|---|
bsp_image.root_path exists | Use it without prompting. |
bsp_image: exists without root_path | Use <workspace>/Image. |
No bsp_image: block | Ask once: Enter for default, or absolute override path. |
For an override, validate that the closest existing parent is writable.
Omit root_path when the default is used.
Determine GPU stack
Use the shared GPU-driver invariant from
../../context/target-platform-contract.md.
Derive the expected stack from reference_devkit.module.id and the
catalogue:
| Chip family | Module IDs | Stack | apply_binaries.sh flag |
|---|---|---|---|
| T234 / Orin | p3701, p3767 | nvgpu | none |
| T264 and later / Thor+ | p3834 | OpenRM | --openrm |
Refuse unknown module IDs. The --openrm flag is only valid on BSP
releases that ship the OpenRM stack; if the active BSP doesn't expose
the flag, omit it regardless of what the target wants.
Reuse or extract
If <bsp_image.root_path>/Linux_for_Tegra/ already exists:
-
Do not extract over it unless the user explicitly requested re-extraction and accepted the overwrite risk.
-
Derive the on-disk version from
Linux_for_Tegra/nv_tegra_release. Ask before replacing a different recordedbsp_image.version. -
Verify the installed GPU stack against the platform-derived expectation when possible. Detection precedence (first probe that yields a definitive answer wins):
Linux_for_Tegra/rootfs/etc/nv_tegra_releasecarries anINSTALL_TYPE=token on BSP releases that expose it (newer lines). Read and compare directly.- Otherwise,
find Linux_for_Tegra -name nvgpu.ko: present → nvgpu, absent → OpenRM. - If the chip family has only ever shipped one stack (e.g. T234 / Orin is always nvgpu in current BSPs), fall back to the catalogue-derived expectation without disk probing.
If the installed stack conflicts with the active target, refuse and ask the user to re-extract with the correct stack or fix the target profile. Otherwise skip extraction and update the profile.
Locate tarballs
When extraction is needed, search:
<bsp_image.root_path>/<workspace>/- current working directory
Prompt for absolute paths for anything missing. Required filenames:
Jetson_Linux_R<ver>_aarch64.tbz2Tegra_Linux_Sample-Root-Filesystem_R<ver>_aarch64.tbz2
Both filenames must contain the same R<ver> token. Refuse mismatches
and record <ver> as bsp_image.version. Do not download tarballs.
Extract and apply binaries
Use absolute tarball paths; they may live outside
<bsp_image.root_path>.
ROOT="<bsp_image.root_path>"
BSP_TARBALL="<absolute path to Jetson_Linux_R<ver>_aarch64.tbz2>"
ROOTFS_TARBALL="<absolute path to Tegra_Linux_Sample-Root-Filesystem_R<ver>_aarch64.tbz2>"
mkdir -p "$ROOT"
tar xjf "$BSP_TARBALL" -C "$ROOT"
sudo tar xpjf "$ROOTFS_TARBALL" -C "$ROOT/Linux_for_Tegra/rootfs"
cd "$ROOT/Linux_for_Tegra"
if [ "$GPU_STACK" = "openrm" ]; then
sudo ./apply_binaries.sh --openrm
else
sudo ./apply_binaries.sh
fi
Set GPU_STACK from the "Determine GPU stack" step above. Abort on the first failing command and
surface the failed command.
Update the active profile
Persist the resolved BSP image metadata in the active target profile so
later skills can find the BSP without re-prompting. Preserve existing
blocks, comments, and quoted SKU values; use a round-tripping YAML
writer such as ruamel.yaml.
bsp_image:
root_path: <absolute override path> # omit for <workspace>/Image
version: "<derived version>"
Rules:
- Same version and same root path: no rewrite.
- Different version: ask before updating.
- Different recorded
root_path: refuse automatic rewrite. - Always quote
version.
Finish
Report the image path, extracted vs reused state, GPU stack, derived
version, and profile update status. Then suggest /jetson-init-source.
Purpose
Materialize Linux_for_Tegra/ on disk by extracting the right Jetson
Linux + sample-rootfs tarballs and running apply_binaries.sh with
the GPU-stack flag derived from the active target (nvgpu for T234,
OpenRM for T264+). Then commit the derived BSP version into the
profile's bsp_image: block.
Prerequisites
- Active target profile resolved per
../../context/target-platform-contract.md. - Jetson Linux BSP tarball and matching sample-rootfs tarball staged
on disk (e.g. by
/jetson-download-bspor hand-placed). - Write access to the workspace
Image/root (or the overridebsp_image.root_path). sudoavailable forapply_binaries.sh.
Limitations
- Writes only the
bsp_image:block; source tree, documents, and carrier profile are owned by sibling skills. - Refuses to overwrite an existing
Linux_for_Tegra/without explicit user direction. - Does not download tarballs; rely on
/jetson-download-bspor hand-stage the inputs.
Troubleshooting
apply_binaries.shexits non-zero — re-read its console output; most failures are missingsudo, missing rootfs tarball, or wrong GPU stack flag for the SoC generation.nv_tegra_releaseabsent after extract — extraction stopped early; verify tarball integrity and rerun.- Recorded
versiondisagrees with the tarball filename — the tarball was renamed; trust the value parsed fromLinux_for_Tegra/nv_tegra_releaseover filenames. - Different recorded
root_pathalready in profile — refuse and ask the user to confirm before overwriting.
评论 (0)
暂无评论，成为第一个评论者吧！