DevOps 与云
部署、CI/CD、云平台和基础设施
Skills 列表
cloud-build-basics
Teaches the fundamentals of Google Cloud Build (GCB). Covers core concepts, API enablement, console navigation to the Build History page, and the end-to-end workflow for creating and manually running a basic build trigger. Do not use for managing private pools or complex pipeline architectures.
googleapplication-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment failures. Boundaries: - Only use for GCP-specific cloud infrastructure. - Only use for Terraform coding within the ADC context.
googlegoogle-cloud-storage-fuse
Mounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when interacting with gcsfuse: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune mount flags or config-file settings, apply workload profiles, keep ML checkpointing safe (rename atomicity, hierarchical namespace/HNS, close-time finalization, concurrent writers), or diagnose slow training, low throughput, or bill spikes with gcsfuse metrics. Covers mount semantics, gcsfuse CLI and config files, GKE gcsfuse CSI driver (Workload Identity principal:// bindings, profile StorageClasses, sidecar sizing), and Cloud Run volume mounts. Don't use for bucket administration or data management without a mount (google-cloud-storage-basics) or fully POSIX-compliant shared file systems (Filestore, Managed Lustre).
googlegke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or non-JobSet application issues.
googlegke-manifest-generation
Generates and updates secure, production-ready Kubernetes YAML manifests optimized for GKE Autopilot and GKE Standard clusters. Use when creating or modifying GKE deployment manifests, configuring container security contexts, setting CPU/memory resource limits, defining readiness/liveness/startup probes, mounting secrets and volumes, configuring GKE Gateway API routes, targeting Spot VMs, or deploying AI model inference workloads (vLLM, TGI, Gemma). Don't use for live cluster operations, pod troubleshooting (use gke-workload-troubleshooting), or cluster infrastructure provisioning (use gke-cluster-creation).
googlegke-cost-optimization
Optimizes GKE costs, rightsizes workloads, and configures Spot VMs, CUDs, cost allocation, and resource quotas. Use when optimizing GKE cluster or workload costs, configuring GKE cost allocation or quotas, rightsizing CPU/memory requests, or selecting Spot VMs and machine types. Don't use for general compute class provisioning or GPU Selection (use gke-compute-classes instead).
googlegoogle-cloud-solution-build-deploy-agents
Designs, builds, and deploys AI agents or multi-agent systems on Google Cloud. Provides an interactive workflow to gather requirements, recommend a tailored architecture, and generate deployment instructions. Use when designing or implementing agentic systems on Google Cloud. Don't use for general Google Cloud solution architecture (use google-cloud-solution-architecture instead) or for narrow tasks targeting a single product without agent context.
googlegoogle-cloud-solution-agentic-ai-borderless-data-lakehouse
Guides agents to discover requirements and design a governed, secure borderless open data lakehouse with agentic AI integration. Use when designing a multi-product architecture that connects data silos to AI agents, joining data across clouds, or running federated queries across Google Cloud and external data sources, including on-premises or other cloud providers. Don't use for simple single-cloud data warehouses or non-AI workloads.
googlegke-workload-scaling
Manages scaling for GKE workloads using HPA and VPA. Use when configuring Horizontal Pod Autoscaler (HPA), configuring Vertical Pod Autoscaler (VPA), or applying best practices for GKE workload autoscaling. Do not use for cluster-level autoscaling (Cluster Autoscaler), static cluster sizing, or configuring node-level machine styles directly.
googlecloud-logging-query-generation
Generates Logging Query Language (LQL) queries for Google Cloud Logging from natural language. Use this skill when you need to query log data or when you are debugging issues. You can filter log data by Google Cloud service. Don't use this skill to query other databases, such as SQL or Cloud Spanner.
googlegoogle-cloud-solution-agentic-ai-bidirectional-streaming
Guides agents to interactively discover customer requirements for live, bidirectional multi-agent AI systems that process continuous streams of multimodal data for real-time technical guidance and safety monitoring. Generates a custom Google Cloud solution that uses opinionated best practices and architecture guidance. Use when users need agentic assistance to design and create a multi-product solution in the cloud for live bidirectional multimodal streaming workloads. Don't use for simple text-based chat applications or workloads without real-time streaming requirements.
google
run-experiment
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
wanshuiyin
vercel-cli
从命令行部署、管理、检查和排查 Vercel 项目。用于 Vercel 部署、构建失败、项目和团队、环境变量、域名和 DNS、日志、指标、Speed Insights、Core Web Vitals、请求追踪、用量、活动、告警、防火墙规则、缓存、定时任务、部署钩子、Edge Config、功能标志、集成、连接器、Blob 存储、容器注册表 (VCR)、微前端、滚动发布、自定义环境、Sandbox、agent/MCP 设置、OAuth 应用、预览访问、本地开发或 `vercel api` 回退。
vercelgke-basics
负责管理 GKE 集群的核心创建与资源供应、凭据获取、Autopilot 与 Standard 模式的选择以及工作负载部署。适用于创建 GKE 集群、获取 kubectl 访问凭据、配置 Workload Identity，或在 Autopilot 和 Standard 模式之间做出决策等场景。请勿用于 GKE 专项网络配置（请使用 gke-networking）、高级安全加固（请使用 gke-platform-security 或 gke-workload-security）或集群升级（请使用 gke-upgrades）。
googleagent-platform-alert-configuration
基于 OpenTelemetry (OTel) 指标为 AI Agent 配置最佳实践告警策略。适用于分析、编写或部署告警策略，以监控 Agent 的延迟、错误率、Token 消耗及质量指标。注意：可靠性（Reliability）、成本（Cost）、安全防护（Safety）和系统安全（Security）告警使用通用 OTel 指标，支持跨运行时生效（如 Cloud Run、Vertex AI 等）；而质量（Quality）告警依赖 Vertex AI Online Monitors，仅适用于 Vertex AI 部署环境。
googlebigtable-basics
协助完成 Bigtable 的实例与表资源创建、高性能 Schema 设计以及数据查询。适用于设计 Bigtable 行键（row key）、配置列族（column family）、编写 SQL 查询或客户端代码（Java、Go、Python），以及排查性能瓶颈和热点（hotspotting）问题。也适用于使用 gcloud 或 cbt CLI 配置 Bigtable 集群。请勿用于常规 Cloud SQL 管理。
googleagent-platform-prompt-management
用于在 Agent Platform 中管理和编排 Prompt。适用于创建、列出、查询、版本控制或删除 Agent Platform 中的托管 Prompt。请勿用于模型训练、模型部署到 Endpoint，或管理非 Agent Platform 的 Prompt。
googlecloud-run-basics
管理 Cloud Run 服务、任务和工作者池。当您需要部署响应 HTTP 请求的应用程序（服务）、运行事件触发或定时任务（任务），或处理始终在线的基于拉取的背景处理（工作者池）时使用。
google
tailwind-4
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).
prowler-cloudzustand-5
Zustand 5 state management patterns. Trigger: When implementing client-side state with Zustand (stores, selectors, persist middleware, slices).
prowler-cloudzod-4
Zod 4 schema validation patterns. Trigger: When creating or updating Zod v4 schemas for validation/parsing (forms, request payloads, adapters), including v3 -> v4 migration patterns.
prowler-cloud
ray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
orchestra-researchray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
orchestra-researchllama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
orchestra-research