SkillAtlasSkill 详情

hsb-flash

Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.

审核状态:已审核Quality 72Security 52

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。

项目 README

来源文件:README.md

抓取于 2026年8月9日

NVIDIA Agent Skills

Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.

NVIDIA Agent Skills Spec License

📖 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 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.

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

ProductDescriptionSkills
AIQNVIDIA AI-Q Blueprint - deploy local AI-Q services and run shallow or deep research workflows as agent skills.aiq-research, aiq-deploy
CUDA-QCUDA Quantum — onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.cudaq-guide
cuDFOfficial NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.accelerated-computing-cudf
cuOptGPU-accelerated optimization — vehicle routing, linear programming, quadratic programming, installation, server deployment, and developer tools.cuopt-install, cuopt-multi-objective-exploration, cuopt-numerical-optimization-api, cuopt-numerical-optimization-formulation, cuopt-routing-api-python, cuopt-server-api-python
cuPyNumericNumPy and SciPy on multi-node multi-GPU systems — skills to help with installing cuPyNumeric, migrating existing NumPy code, and doing parallel I/Ocupynumeric-hdf5, cupynumeric-install, cupynumeric-migration-readiness, cupynumeric-parallel-data-load
DALIGPU-accelerated data loading and processing with NVIDIA DALI.dali-dynamic-mode
Data DesignerBuild declarative synthetic dataset generation pipelines with NeMo Data Designer.data-designer
DeepStreamAgentic skills for guided DeepStream development.amc-run-sample-calibration, amc-run-video-calibration, amc-setup-calibration-stack, deepstream-dev, deepstream-generate-pipeline, deepstream-import-vision-model, deepstream-profile-pipeline, deepstream-sop
Digital HealthAgent skills for the clinical ASR evaluation flywheel — term curation, synthetic clinical-speech benchmark generation, KER (Keyword Error Rate) scoring, and fine-tune guidance.digital-health-clinical-asr-setup, digital-health-clinical-asr-build, digital-health-clinical-asr-eval, digital-health-clinical-asr-finetune
DOCATeach AI agents to use the NVIDIA DOCA SDK on BlueField DPUs and ConnectX NICs — setup, libraries, services, tools, deployment, and debugging.doca-bare-metal-deployment, doca-bf3-deployment, doca-bf4-deployment, doca-collectx-deployment, doca-container-deployment, doca-debug, doca-hardware-safety, doca-programming-guide, doca-public-knowledge-map, doca-setup, doca-structured-tools-contract, doca-upgrade, doca-version, doca-aes-gcm, doca-argp, doca-comch, doca-common, doca-compress, doca-devemu, doca-dma, doca-dpa, doca-dpdk-bridge, doca-erasure-coding, doca-eth, doca-flow, doca-flow-dpa-provider, doca-gpi, doca-gpunetio, doca-mgmt, doca-pcc, doca-pcc-ztr-rttcc-algo, doca-rdma, doca-rdmi, doca-rmax, doca-sha, doca-sta, doca-telemetry, doca-telemetry-exporter, doca-urom, doca-verbs, doca-argus, doca-dms, doca-firefly, doca-urom-svc, doca-bench, doca-bench-extension, doca-caps, doca-comm-channel-admin, doca-dpa-hl-tracer, doca-flow-dpa-perf, doca-flow-grpc-server, doca-flow-perf, doca-flow-tune, doca-gpunetio-ib-write-bw, doca-gpunetio-ib-write-lat, doca-pcc-counters, doca-sha-offload-engine, doca-socket-relay, doca-spcx-cc, doca-telemetry-utils
DynamoNVIDIA Dynamo deployment bring-up on Kubernetes — pick and deploy recipes, start router modes, validate disagg NIXL/UCX/NCCL interconnect, and triage day-2 failures.dynamo-interconnect-check, dynamo-recipe-runner, dynamo-router-starter, dynamo-troubleshoot
Earth2StudioOpen-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.earth2studio-create-datasource, earth2studio-create-diagnostic, earth2studio-create-prognostic, earth2studio-data-fetch, earth2studio-deterministic-forecast, earth2studio-discover, earth2studio-install
HoloHubBuild, run, debug, benchmark, and develop HoloHub applications and Holoscan Modules with validated lifecycle workflows.holohub-app-lifecycle, holohub-debug-build-run, holohub-module-lifecycle
Holoscan SDKInstall and set up the Holoscan SDK on any platform (container, Debian, Python, Conda, or source).holoscan-install-debian, holoscan-install-source, holoscan-install-wheel, holoscan-install-conda, holoscan-install-container, holoscan-setup
Holoscan Sensor BridgeAgent-ready skills for Holoscan Sensor Bridge devkit workflows, including demo environment bring-up, FPGA flashing for Lattice and VB1940 hardware, example application execution, QA test-plan automation, and support for configuring and using the Holoscan Sensor Bridge FPGA intellectual property (IP) core.hsb-setup, hsb-flash, hsb-app, hsb-test, hsb-ip-def, hsb-ip-packetizer, hsb-ip-create-top
Isaac for Healthcare WorkflowsAgent-ready skills for Isaac for Healthcare agentic and catheter-navigation workflows, covering task authoring, data pipelines, policy training and validation, CT-derived digital twins, DRR rendering, and interactive catheter simulation.i4h-workflow, i4h-workflow-setup, i4h-workflow-create, i4h-workflow-scene-edit, i4h-workflow-dataset-teleop, i4h-workflow-dataset-replay, i4h-workflow-dataset-mimic, i4h-workflow-dataset-annotate, i4h-workflow-dataset-convert, i4h-workflow-finetune, i4h-workflow-validate, i4h-workflow-e2e, i4h-lerobot-viz, i4h-catheter-navigation, i4h-catheter-navigation-setup, i4h-catheter-navigation-digital-twin, i4h-catheter-navigation-render-drr, i4h-catheter-navigation-viewport, i4h-catheter-navigation-smoke, i4h-catheter-navigation-e2e
Jetson BSPAgentic skills for setting up and customizing an NVIDIA Jetson Linux Board Support Package (BSP) — pick a target, prepare image and sources, customize IO (camera, PCIe, USB, pinmux, clocks, and more), then promote, flash, and validate.jetson-build-source, jetson-customize-camera, jetson-customize-clocks, jetson-customize-fan, jetson-customize-mgbe, jetson-customize-nvpmodel, jetson-customize-pcie, jetson-customize-pinmux, jetson-customize-uphy, jetson-customize-usb, jetson-derive-carrier, jetson-download-bsp, jetson-flash-image, jetson-generate-kb, jetson-init-image, jetson-init-source, jetson-init-target, jetson-link-docs, jetson-optimize-memory, jetson-print-bsp-info, jetson-promote-image, jetson-quick-start, jetson-set-target, jetson-validate-image
Jetson DeviceDevice-side agent skills for working with a live NVIDIA Jetson after boot — diagnostics, memory auditing, headless setup, inference memory tuning, LLM serving and benchmarking, packaging guidance, and speculative decoding.jetson-diagnostic, jetson-headless-mode, jetson-inference-mem-tune, jetson-llm-benchmark, jetson-llm-serve, jetson-memory-audit, jetson-package, jetson-print-device-info, jetson-speculative-decoding
Medical AI SkillsAgent-ready medical AI skills built on MONAI for DICOM handling, NVIDIA-hosted medical imaging model workflows, segmentation, synthesis, and evidence-oriented evaluation.dicom-metadata-extract, dicom-series-preflight, dicom-series-to-volume, nv-generate-ct-rflow, nv-generate-mr, nv-generate-mr-brain, nv-generate-mr-brain-finetune, nv-generate-vae-finetune, nv-reason-cxr, nv-segment-ct, nv-segment-ct-finetune, nv-segment-ctmr
Megatron-CoreLarge-scale distributed training — model parallelism, pipeline parallelism, and mixed precision.mcore-create-issue, mcore-linting-and-formatting, mcore-run-on-slurm, mcore-split-pr, mcore-testing
NeMo AutoModelNeMo AutoModel - PyTorch-native distributed training for LLMs/VLMs with Hugging Face support, recipes, launchers, and validation workflows.nemo-automodel-distributed-training, nemo-automodel-launcher-config, nemo-automodel-model-onboarding, nemo-automodel-recipe-development
NeMo MBridgeNeMo MBridge - PyTorch-native bridge between Hugging Face and Megatron-Core for checkpoint conversion, training recipes, and NVIDIA GPU performance workflows.nemo-mbridge-mlm-bridge-training, nemo-mbridge-multi-node-slurm, nemo-mbridge-perf-activation-recompute, nemo-mbridge-perf-cpu-offloading, nemo-mbridge-perf-cuda-graphs, nemo-mbridge-perf-expert-parallel-overlap, nemo-mbridge-perf-hierarchical-context-parallel, nemo-mbridge-perf-megatron-fsdp, nemo-mbridge-perf-memory-tuning, nemo-mbridge-perf-moe-comm-overlap, nemo-mbridge-perf-moe-dispatcher-selection, nemo-mbridge-perf-moe-hardware-configs, nemo-mbridge-perf-moe-long-context, nemo-mbridge-perf-moe-optimization-workflow, nemo-mbridge-perf-moe-vlm-training, nemo-mbridge-perf-parallelism-strategies, nemo-mbridge-perf-sequence-packing, nemo-mbridge-perf-tp-dp-comm-overlap, nemo-mbridge-recipe-recommender, nemo-mbridge-resiliency
NeMo PlatformNeMo Platform brings NVIDIA NeMo libraries together under one CLI, Python SDK, and web UInemo-evaluator-plugin, nemo-data-designer-plugin
NeMo RelaySkills to help get started and use NeMo Relay - a runtime for instrumenting and controlling AI agents across harnesses, applications, and frameworks.nemo-relay-install, nemo-relay-get-started, nemo-relay-instrument-calls, nemo-relay-instrument-context-isolation, nemo-relay-instrument-typed-wrappers, nemo-relay-plugin-adaptive-tuning, nemo-relay-plugin-build, nemo-relay-plugin-observability, nemo-relay-migrate-from-flow, nemo-relay-debug-runtime-integration
NeMo RetrieverNeMo Retriever - deploy NeMo Retriever Library locally, extract information from corpus of data, and answer questions against the corpus.nemo-retriever
NeMo-RLRLHF training on Ray — GRPO, DPO, and SFT for LLMs and VLMs with FSDP2 and Megatron-Core.launch-nemo-rl, nemo-rl-auto-research, nemo-rl-brev-etiquette, nemo-rl-docs, nemo-rl-session-memory
NemoClawSecure agent sandboxing — run OpenClaw inside NVIDIA OpenShell with managed inference, policy management, remote deployment, sandbox monitoring.nemoclaw-user-guide
NemotronAuthor end-to-end model development, customization, evaluation, and deployment pipelines using the NVIDIA AI stack.nemotron-customize, nemotron-retrieval-recipes, nemotron-policy-generator
Nemotron SpeechDeploy and operate NVIDIA Nemotron Speech (Riva) NIMs — ASR, TTS, and NMT, cloud-hosted via build.nvidia.com or self-hosted on your own GPU.nemotron-speech, nemotron-asr-finetune
Physical AIPhysical AI skills for simulation, synthetic data generation, training, validation and deployment and more.omniverse-cad-to-simready, omniverse-realtime-viewer, omniverse-usd-performance-tuning, physical-ai-infrastructure-setup-and-resilient-scaling, physical-ai-neural-reconstruction, physical-ai-defect-image-generation, physical-ai-video-data-augmentation, physical-ai-people-attribute-search
PhysicsNeMoNVIDIA PhysicsNeMo - Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods.physicsnemo-discover, physicsnemo-shard-tensor
Portfolio OptimizationGPU-accelerated Mean-CVaR portfolio optimization with NVIDIA cuOpt — CVaR optimization, efficient frontier, scenario generation, backtesting, and rebalancing.portfolio-optimization
RAG BlueprintRAG pipeline — deploy, configure, troubleshoot, and manage retrieval augmented generation with Docker Compose or Helm.rag-blueprint, rag-eval, rag-perf
Skill Card GeneratorReads an agent skill's source files and produces a skill card plus a review table. Use when a skill directory exists and a governance card needs to be generated or updated.skill-card-generator
TAO ToolkitNVIDIA TAO Toolkit - fine-tune and optimize 100+ pretrained vision AI models with your own data using low-code microservices, then export production-ready models for edge or cloud deployment.tao-analyze-changenet-rca, tao-finetune-huggingface-model, tao-port-huggingface-model, tao-run-automl, tao-run-automl-deft-pipeline, tao-run-deft-aoi, tao-run-inference-service, tao-train-single-step, paidf-anomalygen, tao-analyze-gaps-visual-changenet, tao-analyze-gaps-vlm-bcq, tao-convert-dataset-format, tao-generate-image-grounding, tao-generate-referring-expressions, tao-generate-video-reasoning-annotations, tao-mine-aoi-images, tao-route-visual-changenet-samples, tao-validate-dataset-format, tao-finetune-clip, tao-finetune-cosmos-embed, tao-finetune-cosmos-reason, tao-train-action-recognition, tao-train-bevfusion, tao-train-centerpose, tao-train-deformable-detr, tao-train-depth-anything-v2, tao-train-dino, tao-train-fast-foundation-stereo, tao-train-foundation-stereo, tao-train-grounding-dino, tao-train-image-classification, tao-train-mask-auto-encoder, tao-train-mask-auto-label, tao-train-mask-grounding-dino, tao-train-mask2former, tao-train-metric-learning-recognition, tao-train-nvdinov2, tao-train-nvpanoptix3d, tao-train-ocdnet, tao-train-ocrnet, tao-train-oneformer, tao-train-optical-inspection, tao-train-pointpillars, tao-train-pose-classification, tao-train-reid, tao-train-rtdetr, tao-train-segformer, tao-train-sparse4d, tao-train-visual-changenet, tao-run-on-brev, tao-run-on-docker, tao-run-on-kubernetes, tao-run-on-local-docker, tao-run-on-slurm, tao-run-platform, tao-setup-nvidia-gpu-host, tao-launch-workflow, tao-list-capabilities
TileGymTile-based GPU programming — adding new kernels, cross-framework conversion, and performance optimization.tilegym-adding-cutile-kernel, tilegym-converting-cutile-to-julia, tilegym-converting-cutile-to-triton, tilegym-cutile-autotuning, tilegym-cutile-python, tilegym-improve-cutile-kernel-perf, tilegym-monkey-patch-kernels-to-transformers
Video Search and SummarizationVSS Blueprint — deploy profiles, search and summarize video, generate analysis reports, manage alerts and incidents, query VIOS sensors, and use the RTVI VLM microservice.vss-ask-video, vss-deploy-dense-captioning, vss-deploy-detection-tracking-2d, vss-deploy-detection-tracking-3d, vss-deploy-profile, vss-deploy-video-embedding, vss-generate-video-calibration, vss-generate-video-report, vss-manage-alerts, vss-manage-video-io-storage, vss-query-analytics, vss-search-archive, vss-setup-behavior-analytics, vss-setup-video-analytics-api, vss-summarize-video

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:

ProductIssuesDiscussionsContributingSecurity
AIQIssuesDiscussionsContributingSecurity
CUDA-QIssuesDiscussionsContributingSecurity
cuDFIssuesDiscussionsContributingSecurity
cuOptIssuesDiscussionsContributingSecurity
cuPyNumericIssues—Contributing—
DALIIssues—Contributing—
Data DesignerIssuesDiscussionsContributingSecurity
DeepStreamIssues—ContributingSecurity
Digital HealthIssues—ContributingSecurity
DOCAIssues—ContributingSecurity
DynamoIssuesDiscussionsContributingSecurity
Earth2StudioIssuesDiscussionsContributing—
HoloHubIssues—ContributingSecurity
Holoscan SDKIssues—ContributingSecurity
Holoscan Sensor BridgeIssues—Contributing—
Isaac for Healthcare WorkflowsIssues—ContributingSecurity
Jetson BSPIssues—ContributingSecurity
Jetson DeviceIssues—ContributingSecurity
Medical AI SkillsIssues—ContributingSecurity
Megatron-CoreIssuesDiscussionsContributing—
NeMo AutoModelIssuesDiscussionsContributingSecurity
NeMo MBridgeIssuesDiscussionsContributingSecurity
NeMo PlatformIssuesDiscussionsContributingSecurity
NeMo RelayIssuesDiscussionsContributingSecurity
NeMo RetrieverIssuesDiscussionsContributingSecurity
NeMo-RLIssuesDiscussionsContributingSecurity
NemoClawIssuesDiscussionsContributingSecurity
NemotronIssuesDiscussionsContributingSecurity
Nemotron SpeechIssues—ContributingSecurity
Physical AIIssues—ContributingSecurity
PhysicsNeMoIssuesDiscussionsContributingSecurity
Portfolio OptimizationIssuesDiscussionsContributingSecurity
RAG BlueprintIssuesDiscussionsContributingSecurity
Skill Card GeneratorIssues—ContributingSecurity
TAO ToolkitIssuesDiscussionsContributingSecurity
TileGymIssues—ContributingSecurity
Video Search and SummarizationIssuesDiscussionsContributingSecurity

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 agent
  • skill-card.md — skill identity and governance card
  • skill.oms.sig — detached OMS signature (verifiable against nv-agent-root-cert.pem)
  • A Tier-3 evaluation dataset — accepted at evals/evals.json, evals/*.json, eval/*.json, or benchmark/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 against nv-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, or benchmark/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.md file at their root.
  • Metadata uses YAML frontmatter with required name and description fields.
  • Skills follow a progressive disclosure model — lightweight metadata loads at startup, full instructions load on activation.
  • Validate your skill using the skills-ref reference 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

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/NVIDIA/skills.git
  3. 将 "skills/hsb-flash" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/NVIDIA/skills.git
  3. 将 "skills/hsb-flash" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/NVIDIA/skills.git
  3. 将 "skills/hsb-flash" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/NVIDIA/skills.git
  3. 将 "skills/hsb-flash" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/NVIDIA/skills.git
  3. 将 "skills/hsb-flash" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: hsb-flash
description: Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must never be mixed.
author: "Holoscan Team <holoscan-team@nvidia.com>"
license: "Apache-2.0"
version: "1.0.0"
tags:
  - holoscan-sensor-bridge
  - hsb
  - fpga-flashing
tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - Bash
disable-model-invocation: true
allowed-tools: Read,Write,Edit,MultiEdit,Grep,Glob,Bash
metadata:
  author: "Holoscan Team <holoscan-team@nvidia.com>"
  team: holoscan
  tags:
    - holoscan-sensor-bridge
    - hsb
    - fpga-flashing
  agents:
    - claude-code
    - codex

HSB FPGA Flash

Use this skill when the user wants to flash (upgrade or downgrade) the FPGA firmware on an HSB board connected to a supported NVIDIA devkit.

This skill supports two board types:

  1. HSB Lattice boards — standalone FPGA board with a Lattice CPNX100 FPGA
  2. Leopard Imaging VB1940 — "all-in-one" camera with an integrated Lattice FPGA

CRITICAL SAFETY RULE: Never mix board-type commands. Using program_leopard_cpnx100 on a Lattice board or program_lattice_cpnx100 on a VB1940 can permanently brick the device. The skill must detect and confirm the board type before any flash operation, and refuse to proceed if the board type is ambiguous or mismatched.

This workflow has side effects (it permanently modifies FPGA firmware). Never run it automatically. Only run it when the user explicitly invokes it.

Usage warning: This skill flashes the FPGA with new firmware. Before invoking it, ask the user to make sure they have enough Claude Code usage/tokens to complete the workflow.

Before you start — required gates (do these first, in order)

Gate 1 — Read environment variables. Before doing anything else, check these variables and print their resolved values to the user:

SSH_TARGET      Remote devkit login (e.g. nvidia@192.168.1.50). Ask the user if not set.
REMOTE_ROOT     Remote working directory (e.g. /home/nvidia). Ask the user if not set.
REMOTE_SUDO     sudo / sudo -n / "" — default to "sudo" if not set.
REMOTE_SSH_OPTS Additional SSH options (optional).
HSB_PLATFORM    Platform hint (optional).

SSH_TARGET and REMOTE_ROOT are required. Stop and ask the user for them if either is missing.

Gate 2 — Present the flash summary and phase plan. Before taking any action:

If the user's request already includes board type, current FPGA version, and target FPGA version, state the following before the phase plan: flash tool (program_lattice_cpnx100 for Lattice, program_leopard_cpnx100 for VB1940 — never mix), manifest release and filename, CLI flags (--force --accept-eula), whether the procedure is single-step or two-step via gateway 2412. For VB1940, also state that no v2.0.0 interim repo is needed. For two-step upgrades from FPGA 2407, state that step 1 uses hololink --force fpga_version (not hololink enumerate, which is incompatible with FPGA 2407) and uses v2.0.0 flag placement: hololink --force program scripts/manifest.yaml --accept-eula (--force before the subcommand).

Then show the phase plan and ask explicitly: Shall I proceed with the flash workflow? [Y/n] — do not start Gate 3 until the user confirms:

HSB Flash — Phase Plan
  Phase 0: Token-budget preflight
  Phase 1: Verify board connectivity, detect board type (Lattice or VB1940), read FPGA version
  Phase 2: Select target FPGA version
  Phase 3: Prepare flash infrastructure and YAML files, present flash plan for approval
  Phase 4: Execute flashing procedure (with power cycle verification)
  Phase 5: Summary report (with option to save)
  Phase 6: Clean up flash artifacts

Gate 3 — Token-budget preflight (Phase 0). Run after the phase plan (Gate 2) has been presented and the user has confirmed. Do not run the token-budget check before the phase plan is shown. Do not proceed to Phase 1 until the budget check passes.

Gate 4 — Confirm board type explicitly. Before any flash command, confirm with the user whether the board is Lattice or VB1940. Never mix program_lattice_cpnx100 and program_leopard_cpnx100 — wrong tool can brick the device.

Instructions

Invoke this skill by typing /hsb-flash [OPTIONS]. The skill detects the board type automatically, presents a flashing plan, and prompts for confirmation before each flash step. See references/help-text.md for the full --help output.

What this skill must do

  1. Run the mandatory token-budget preflight before any remote command, repo checkout, container build, or flash preparation. Estimate the tokens needed to complete all phases, check the user's remaining subscription-plan usage with the best available Claude Code/account usage mechanism, display the estimate and result to the user, and stop if the available budget is insufficient or cannot be verified.
  2. Verify that an HSB board is connected to a devkit, that SSH and board connectivity work, read the current FPGA version, and identify the board type (Lattice or VB1940). Try hololink enumerate first; if it fails (which is expected for FPGA 2407 boards), fall back to hololink --force fpga_version. For Lattice boards, if all methods fail with the existing repo's container, checkout HSB release repo v2.0.0 and retry using the v2.0.0 container. If that also fails, assume the version is 2407 and continue. For VB1940 boards, ask the user if the version cannot be read.
  3. Ask the user for the target FPGA version they want to flash to (or accept "latest"). The available versions depend on the board type.
  4. Handle undocumented FPGA versions (applies to both Lattice and VB1940): If the current or target FPGA version is not listed in this skill's supported versions or mapping tables, it may belong to a newer HSB release not yet documented here, or it may be an unreleased development build. Proceed as follows:
    • Check for a newer release: Fetch the public release notes at https://github.com/nvidia-holoscan/holoscan-sensor-bridge/blob/main/RELEASE_NOTES.md and look for a release that introduces the undocumented FPGA version. If a matching release is found, checkout that release repo on the devkit and use it for flashing following the same rules described below for the detected board type. Also update this skill's mapping tables, supported FPGA versions lists, and transition matrices with the new release and its corresponding FPGA version.
    • Development or unreleased FPGA: If no published release corresponds to the FPGA version, use the existing HSB repo already on the devkit (from /hsb-setup) to flash, following the same rules for the detected board type. If the flash fails, report the error and prompt the user for further instructions.
  5. Determine the correct flashing procedure and prepare flash scripts and YAML files:
    • Lattice boards:
      1. Read the FPGA version currently flashed on the HSB board. Determine the required HSB release repo based on the flash direction: for upgrades, use the repo corresponding to the target FPGA version; for downgrades, use the repo corresponding to the current FPGA version (see "FPGA version to repo mapping" below). Checkout this repo if it does not already exist on the devkit.
      2. Copy the target FPGA manifest YAML from the relevant scripts/ directory of this skill to the checked-out repo, and patch the file as needed for any missing details (e.g., fpga_uuid).
      3. Determine the flashing procedure:
        • Single-step upgrade: If the current version is 2412 or newer and the target is also 2412 or newer, or if upgrading from any version to exactly 2412. Flash directly from the current version to the target using the repo that corresponds to the target FPGA version (see "FPGA version to repo mapping").
        • Single-step downgrade: If both the current and target versions are 2412 or newer. Flash directly from the current version to the target using the repo that matches the current FPGA version.
        • Two-step downgrade: If the target is older than 2412 (i.e., 2407) and the current version is newer than 2412. Step 1: flash from the current version to 2412 using the repo that matches the current FPGA version. Step 2: flash from 2412 to the target using HSB release repo v2.0.0. Power cycle required between steps. (Special case: if the current version is exactly 2412, only step 2 is needed.)
        • Two-step upgrade: If the current version is older than 2412 (i.e., 2407) and the target is newer than 2412. Step 1: flash from the current version to 2412 using v2.0.0 (which corresponds to target FPGA 2412). Step 2: flash from 2412 to the target using the repo that corresponds to the target FPGA version. Power cycle required between steps.
      4. Read the user guide of the HSB repo being used for flashing and extract the flash command. Always add --force and --accept-eula to ensure non-interactive execution inside the container. Note: v2.0.0 places --force before the subcommand and --accept-eula after — see "v2.0.0 CLI flag placement" below.
      5. After flashing is complete, clean up all interim HSB release repos that were checked out by this skill and differ from the user's original repo that existed on the devkit before the skill was invoked.
    • VB1940 cameras: Use the existing HSB repo on the devkit directly (no v2.0.0 interim repo needed). Flashing is always single-step. Present the full flashing plan to the user for approval.
  6. Execute the flashing procedure:
    • Perform required pre-flash safety checks (ping board, confirm board type and current FPGA version).
    • Run each flash step with full logging; announce the operation before flashing.
    • Require explicit user confirmation before each critical flash and after any required board/camera power cycle.
    • All program commands must be executed inside the demo container (no sudo needed within the container).
    • After flashing, verify the new FPGA version matches the intended target before proceeding.
    • Handle any error or mismatch by stopping the workflow, reporting the state, and offering to clean up.
  7. Produce a summary report of the entire procedure with the option to save it.
  8. Clean up all flash artifacts so the devkit is ready for the user to checkout any HSB release they need.

Supported board types

Board TypeIdentifierDescription
LatticelatticeHSB Lattice CPNX100-ETH-SENSOR-BRIDGE standalone FPGA board
VB1940vb1940Leopard Imaging VB1940 "all-in-one" Eagle Camera with integrated Lattice FPGA

The board type is detected from the hololink enumerate output during Phase 1 and confirmed with the user. If detection is ambiguous, the user must explicitly specify the board type.

Supported FPGA versions

Lattice board FPGA versions

VersionYAML Source ReleaseNotes
2407v2.0.0Oldest supported version
2412v2.0.0Gateway version for two-step flashing
2507v2.3.1
2510v2.5.0Latest supported version

VB1940 FPGA versions

VersionYAML Source ReleaseHSB ReleaseNotes
2507v2.3.0v2.3.0
2510v2.5.0v2.5.0Latest supported version

The VB1940 does not support versions 2407 or 2412 — these are Lattice-only.

Versions not listed above: FPGA versions newer than the latest documented version for either board type may still be flashable — see "Handling undocumented FPGA versions" below. For Lattice boards, versions older than 2407 or between known versions (e.g., 2409) are not supported. For VB1940, versions older than 2507 are not supported. In either case, refuse and show the supported versions for the board type.

Flashing infrastructure

See references/flashing-infrastructure.md for GitHub release tags, bundled manifest YAML layout, board-specific flash commands, v2.0.0 CLI flag differences, and FPGA 2407 enumerate workaround.

Repo selection and checkout (Lattice only)

The "Lattice board FPGA versions" table above determines which HSB release repo to use. The lookup key depends on direction:

  • Upgrades: Look up the target FPGA version's YAML Source Release.
  • Downgrades: Look up the current FPGA version's YAML Source Release.

Self-updating: If an undocumented FPGA version is encountered, the skill checks the public release notes for a matching HSB release (see "Handling undocumented FPGA versions"). If found, the skill updates the "Supported FPGA versions" tables, the transition matrix, and notes the new release's manifest files.

Repo checkout logic

  1. Check for an existing repo: If the user already has an HSB repo on the devkit (from /hsb-setup), read its version from the VERSION file.
  2. Determine the required repo: For upgrades, look up the target FPGA version in the mapping table. For downgrades, look up the current FPGA version.
  3. Checkout if needed: If the existing repo does not match the required version, clone and checkout the required repo version into a separate directory. The existing repo is left untouched.
  4. Two-step case: If a two-step flash is required, both step repos must be available. For two-step downgrade (current > 2412, target = 2407), step 1 uses the current FPGA's repo and step 2 uses v2.0.0. For two-step upgrade (current = 2407, target > 2412), step 1 uses v2.0.0 (target 2412's repo) and step 2 uses the repo corresponding to the final target FPGA version. If any required repo is not already present, it is checked out.

VB1940 note: VB1940 flashing always uses the existing repo on the devkit — the FPGA-to-repo mapping does not apply. The existing repo must be at version v2.3.0 or later. If no existing repo is found, instruct the user to run /hsb-setup first.

What to save from detection

During Phase 1, when scanning for an existing repo and detecting the board type, save these variables to the session state:

  • BOARD_TYPE — the detected board type: lattice or vb1940
  • EXISTING_REPO_DIR — absolute path to the existing HSB repo (empty if none found)
  • EXISTING_REPO_VERSION — the repo's release version (e.g., 2.3.1), read from the VERSION file
  • FLASH_REPO_DIR — absolute path to the repo that will be used for flashing (may differ from EXISTING_REPO_DIR if a different version was checked out)
  • FLASH_REPO_VERSION — the version of the flash repo (looked up from the FPGA-to-repo mapping)
  • INTERIM_REPOS — list of repo directories checked out by this skill (for cleanup in Phase 6)

Linux/Windows-friendly wrapper variables

Reuse the same environment variables from the hsb-setup skill:

  • SSH_TARGET for the remote login target (e.g. nvidia@agx-thor-host)
  • REMOTE_ROOT for the remote working directory where flash workspace will be created
  • REMOTE_SUDO for privileged commands
  • REMOTE_SSH_OPTS for additional SSH options
  • HSB_PLATFORM as an optional platform hint

If these are set, notify the user of these settings and use them without re-asking.

Before Phase 1, print the resolved remote execution settings.

Mandatory interaction pattern

Before making changes, show this phase plan:

  • Phase 0: Token-budget preflight; verify the user's remaining plan usage can cover a complete flash workflow
  • Phase 1: Verify board connectivity, detect board type (Lattice or VB1940), and read current FPGA version
  • Phase 2: Select target FPGA version (available versions depend on board type)
  • Phase 3: Prepare flash infrastructure and YAML files, present flashing plan for approval
    • Lattice: Checkout the required repo (target FPGA's repo for upgrades, current FPGA's repo for downgrades — if not already present), copy and patch manifest YAML
    • VB1940: Use existing repo directly
  • Phase 4: Execute flashing procedure (with power cycle verification)
  • Phase 5: Generate summary report (with option to save)
  • Phase 6: Clean up flash artifacts

Then execute one phase at a time.

After each non-final phase (Phases 0–5):

  1. Show a phase summary with key outcomes.
  2. Prompt the user with Proceed to Phase <N+1>? [Y/n] and specify what the next phase does. Wait for confirmation before continuing.

Exception: When --y (auto-approve mode) is active, phase gates are skipped and phases run automatically. See "Auto-approve mode (--y)" section for details.

If something fails, do not just dump raw logs. Summarize:

  • the exact command that failed
  • the likely root cause
  • what safe action you recommend
  • whether the issue is blocking

Phase details

See references/phase-details.md for full step-by-step phase instructions, flashing procedure logic, execution rules, safety constraints, phase gate rules, verbosity behavior, force mode, and auto-approve mode.

Built-in help (--help)

See references/help-text.md for the full --help output text.

Invocation examples

See references/help-text.md for the full --help output including all invocation examples.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!