DevOps 与云
部署、CI/CD、云平台和基础设施
Skills 列表
google-agents-cli-deploy
当用户想要“部署 Agent”、“部署 ADK Agent”、“配置 CI/CD”、“配置 Secret 密钥”、“排查部署故障”，或需要关于 Agent Runtime、Cloud Run 或 GKE 部署目标的指导时，应使用此 Skill。 涵盖部署工作流、服务账号、版本回滚和生产基础设施。 属于 Google ADK (Agent Development Kit) Skill 套件的一部分。 切勿用于 API 代码模式（请使用 google-agents-cli-adk-code）、评估测试（请使用 google-agents-cli-eval）或项目脚手架搭建（请使用 google-agents-cli-scaffold）。
googlegoogle-agents-cli-publish
当用户想要“发布智能体”、“发布我的ADK智能体”、“向Gemini Enterprise注册智能体”、“发布到Gemini Enterprise”，或需要关于agents-cli publish gemini-enterprise命令的指导时，应使用此技能。当用户想要“在Agent Registry中管理智能体”或“列出/更新/删除已注册的智能体”时，也应使用此技能。涵盖ADK与A2A注册模式、编程式和交互式用法、标志参考、从部署元数据自动检测、Agent Registry集群管理以及故障排除。属于Google ADK（Agent Development Kit）技能套件的一部分。请勿用于部署（请使用google-agents-cli-deploy）。
google
tao-setup-nvidia-gpu-host
Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for Docker/local-Docker and Kubernetes GPU worker hosts. The `--check-only` path works on any Linux distribution; `--install` automates debian-family (Ubuntu/Debian/Pop!_OS/Mint/Zorin/Raspbian), rhel-family (Fedora/RHEL/Rocky/AlmaLinux), and suse-family (openSUSE/SLES) hosts, and prints actionable manual-install steps for everything else. Use when the user asks to "set up an NVIDIA GPU host", "check TAO Docker GPU runtime", or prepare a Kubernetes GPU worker for TAO.
nvidiaholoscan-install-container
Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
nvidiamcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
nvidiavss-setup-video-analytics-api
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
nvidiavss-deploy-video-embedding
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.
nvidiavss-query-analytics
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
nvidianemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
nvidiadynamo-router-starter
Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.
nvidiadynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
nvidiadynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
nvidia
k2
Build and troubleshoot Cloudflare K2 or K2 Streams durable logs. Use for stream setup, producing from Workers or HTTP, configuring retention and inputs, and consuming through subscriptions.
cloudflarenemotron-speech
Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
nvidiaphysical-ai-infrastructure-setup-and-resilient-scaling
Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.
nvidiacuopt-server-api-python
cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
nvidiacuopt-install
通过 pip、conda 或 Docker 安装适用于 Python、C 或服务器端的 cuOpt，并进行安装验证。如需从源码构建 cuOpt，请参阅 cuopt-developer。
nvidia
networkfirewall
Configures AWS Network Firewall, the managed stateful VPC firewall: deploying a firewall and routing traffic through its endpoints; centralizing inspection for many VPCs with a transit gateway-attached firewall that keeps stateful flows symmetric across Availability Zones; filtering outbound traffic by domain name; logging and rule tuning; TLS inspection with ACM certificates; writing Suricata rules; managing rules as CloudFormation/IaC; blocking an indicator mid-incident; migrating off a third-party firewall appliance; and diagnosing dropped traffic. Applicable when the user wants to inspect or filter VPC traffic at Layer 3 and 4, allow or block outbound domains, manage firewall rules as IaC, or decrypt TLS. Not applicable for AWS WAF Layer 7 rules (waf skill), Gateway Load Balancer appliance inspection (gatewayloadbalancer skill), Route 53 Resolver DNS Firewall (route53 skill), or transit gateway route tables and appliance-mode attachments (transitgateway skill).
awsaiq-deploy
当需要安装、部署、运行、验证、排查故障或停止 NVIDIA AI-Q Blueprint 基础设施时使用。
nvidia
performance
Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".
addyosmani
ctf-forensics
提供面向 CTF 竞赛的数字取证与信号分析技术。适用于分析磁盘镜像、内存转储、事件日志、网络抓包、加密货币交易、隐写术、PDF 分析、Windows 注册表、Volatility、PCAP、Docker 镜像、coredump、侧信道功耗轨迹、DTMF 音频频谱图、数据包时间间隔分析、CD 音轨镜像，以及恢复已删除的文件和凭据。
ljagiello
finviz-screener
Build and open FinViz screener URLs from natural language requests. Use when user wants to screen stocks, find stocks matching criteria, filter by fundamentals or technicals, or asks to open FinViz with specific conditions. Supports both Japanese and English input (e.g., "高配当で成長している小型株を探したい", "Find oversold large caps with high ROE").
tradermontysandbox-stable
Use when building or changing Cloudflare Sandbox apps on the current stable @cloudflare/sandbox package (default npm tag)—commands, sessions, files, ports, tunnels, terminals, bridge, production, or deprecated-API cleanup while staying on stable. Not for @cloudflare/sandbox@next (use sandbox-next) or for porting to 1.0 (use sandbox-migrate-to-next).
cloudflaresandbox-next
Use when building or changing Cloudflare Sandbox apps on @cloudflare/sandbox@next (Sandbox SDK 1.0 preview)—code execution, AI runners, interpreters, CI-like jobs, terminals, files, mounts, tunnels, preview URLs, lifecycle, or errors. Not for the default stable package (use sandbox-stable) or for porting stable to @next (use sandbox-migrate-to-next).
cloudflare