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
vss-setup-video-analytics-api
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.
数据与 AIDevOps 与部署
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：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/vss-setup-video-analytics-api" 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/vss-setup-video-analytics-api" 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/vss-setup-video-analytics-api" 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/vss-setup-video-analytics-api" 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/vss-setup-video-analytics-api" 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: vss-setup-video-analytics-api
description: Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
license: Apache-2.0
metadata:
author: "NVIDIA Video Search and Summarization team"
version: "3.2.0"
github-url: "https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization"
tags: "nvidia blueprint operational deployment video-analytics-api rest-api"Purpose
Deploy the video-analytics-api REST service standalone with the user's chosen config, data-log bind, and Elasticsearch / Kafka connectivity.
Instructions
Follow the routing tables and step-by-step workflows below. Each section that ends in workflow, quick start, or flow is intended to be executed top-to-bottom. Detailed reference material lives in references/.
Examples
Worked end-to-end examples are kept under evals/ (each *.json manifest
contains a runnable scenario). Run a Tier-3 evaluation to replay them:
nv-base validate skills/vss-setup-video-analytics-api --agent-eval
A minimal standalone bring-up looks like:
cd $REPO/deploy/docker
export VSS_APPS_DIR=$(pwd)
export VSS_DATA_DIR=${VSS_DATA_DIR:-/tmp/vss-data}
mkdir -p "$VSS_DATA_DIR/data_log/vss_video_analytics_api"
docker compose -f services/analytics/video-analytics-api/compose.yml up -d vss-video-analytics-api
curl -sf http://localhost:8081/livez
Follow references/deploy-video-analytics-api-service.md for the full
workflow (config source, data-log bind, infrastructure dependencies, REST endpoints).
For the field-by-field JSON config reference, see references/configuration.md.
Limitations
- Requires the matching VSS profile / microservice to be deployed and reachable from the caller.
- NGC-hosted models and NIMs may be subject to rate-limits, GPU memory requirements, and license restrictions.
- Concurrency, GPU memory, and storage limits depend on the host hardware and the profile's compose file.
Troubleshooting
- Error: REST call returns connection refused. Cause: target microservice not running. Solution: probe
/docsor/health; redeploy viavss-deploy-profileor the matchingvss-deploy-*skill. - Error: HTTP 401/403 from NGC pulls. Cause: missing/expired
NGC_CLI_API_KEY. Solution:docker login nvcr.ioand re-export the key before retrying. - Error: container OOM or model fails to load. Cause: insufficient GPU memory for the selected profile. Solution: switch to a smaller variant or free GPUs via
docker compose down.
VSS Setup Video Analytics API — Standalone
Deploy just the vss-video-analytics-api container (the Node.js REST API from the upstream video-analytics-api repo), not as part of the full warehouse blueprint stack.
The full operational walkthrough — config-source options, data-log volume behavior, infrastructure dependencies, REST API endpoints, deploy + verify, troubleshooting — lives in references/deploy-video-analytics-api-service.md. The field-by-field JSON config reference lives in references/configuration.md. This SKILL.md only handles routing and prerequisites.
When to use
- "Deploy video analytics api" / "run video-analytics-api standalone"
- "I just want to run the REST API, not the full stack"
- "Use my own video-analytics-api config"
- "Point the API at a different Elasticsearch / Kafka"
- "Start the API without Kafka" / "run the API broker-less"
- "Check what REST endpoints are available"
Prerequisites
-
Repo checkout with
$VSS_APPS_DIRpointing at<repo>/deploy/docker/. Required by the service compose's volume binds. -
NGC credentials —
$NGC_CLI_API_KEYset so docker can pull the image. Seereferences/ngc-api-key-registry-login.md.Secure-handling note for
NGC_CLI_API_KEY: this key is a long-lived credential that pulls all NVIDIA private images available to your NGC org. Never commit the key, never paste it into chat, never store it in/tmp. Read it interactively (read -rs NGC_CLI_API_KEY) or load it from your secret manager (Vault, AWS Secrets Manager, sealed-secrets) at deploy time. Write any derived.envfiles withumask 077+chmod 600, add them to.gitignore, and rotate the key on a defined cadence and after every host decommission. If it has ever been exposed (host snapshot, shared screen, ticket attachment), rotate immediately. -
Docker runtime — Docker Engine 28.3.3 with Docker Compose plugin v2.39.1+. Verify with
docker --versionanddocker compose version. -
Elasticsearch — must be reachable at the URL configured in
elasticsearch.node. The server pings ES on startup; if unreachable, it exits (andrestart: alwaysbrings it back). If you need to bring up ES too, use the infra compose:docker compose -f services/infra/compose.yml up -d elasticsearch. -
Optional Kafka broker. The API can run without Kafka. If you want a quiet broker-less deployment, use the image-baked config or a custom config with
kafka.brokers: []; the service-shipped compose config points atlocalhost:9092, so Kafka-dependent features (dynamic config, dynamic calibration, RTLS/AMR) will fail until a broker is reachable. -
$VSS_DATA_DIRfor the default compose. The base compose bind-mounts$VSS_DATA_DIR/data_log/vss_video_analytics_apifor multipart upload handling and file-backed assets such as calibration images. Set the directory to a writable host path and pre-create it, or remove that mount if image uploads are not needed.
If any required prerequisite fails, surface the gap before going further.
Workflow
Hand the user references/deploy-video-analytics-api-service.md and walk them through its steps in order:
- Choose a config — image-baked default, service-shipped, or custom.
- Decide whether a data-log volume is needed for file uploads.
- Confirm infrastructure dependencies — Elasticsearch (required), Kafka (optional).
- Deploy + verify with
docker compose upand health check.
The compose-file edits, config options, deploy + verify commands, REST API endpoint table, and troubleshooting table all live in that reference — don't duplicate them here.
Endpoint Reference
Use references/deploy-video-analytics-api-service.md for the REST endpoint table and runtime dependency notes.
Kafka-dependent features (runtime, requires broker)
Once the container is up and a Kafka broker is reachable, three additional capabilities are available:
Dynamic config
The API acts as the producer for dynamic config updates. When an operator POSTs to /config, the API publishes an upsert message to the mdx-notification topic with Kafka key behavior-analytics-config. The downstream behavior-analytics container consumes this and ACKs back. The API also handles the bootstrap flow — when behavior-analytics starts, it publishes a request-config message, and the API replies with upsert-all containing the latest verified config from Elasticsearch.
Consumer-side validation, ACK semantics, and the full wire contract are documented in the vss-setup-behavior-analytics dynamic-config reference.
Dynamic calibration
The API produces calibration update notifications on mdx-notification with Kafka key calibration. Supports upsert-all (full snapshot), upsert (per-sensor merge), and delete (per-sensor removal). The downstream behavior-analytics container consumes these and applies them to the live calibration.
Consumer-side validation and per-action policy are documented in the vss-setup-behavior-analytics dynamic-calibration reference.
RTLS / AMR
The API consumes real-time location (mdx-rtls) and AMR (mdx-amr) messages from Kafka and exposes them via REST endpoints.
Routing rules
- If the user wants "the full stack" (UI / agent / perception): hand off to
vss-deploy-profilewith profilewarehouse(oralerts). Don't run this skill in parallel. - If the user wants to deploy the analytics pipeline (behavior creation, incident detection): hand off to
vss-setup-behavior-analytics. - If the user wants to publish a runtime config / calibration update through the REST API: confirm Kafka is reachable, then use the
/configor calibration endpoints and point them at the behavior-analytics dynamic-update references for the consumer wire contract. - If the user wants to understand the dynamic config / dynamic calibration wire contract from the consumer (behavior-analytics) side: point them at the
vss-setup-behavior-analyticsdynamic-config and dynamic-calibration references. - If the user wants to query or interact with the REST API endpoints: the deploy reference endpoint table covers what's available. For the full OpenAPI spec, see
src/app/specification/openapi.jsonin thevideo-analytics-apirepo.
bump:1
评论 (0)
暂无评论，成为第一个评论者吧！