代码审查 / GitHub MCP 推荐

Mobile game development principles. Touch input, battery, performance, app stores.

Build reactive backends with Convex functions, schema validation, auth integration, and deployment workflows. Use when building real-time apps with type-safe server functions and automatic caching.

Create, manage, and deploy Helm charts for Kubernetes package management.

Auto-scale LLM inference clusters on Kubernetes using KEDA, custom GPU metrics, and horizontal pod autoscaling.

Deploy and manage Azure Kubernetes Service clusters. Configure node pools, networking, and integrations. Use when running Kubernetes workloads on Azure.

Deploy and manage Google Kubernetes Engine clusters. Configure node pools, networking, and workload identity. Use when running Kubernetes on GCP.

Customize Kubernetes manifests without templating using Kustomize.

Operate GPU-backed Kubernetes clusters for AI inference and training with scheduling, autoscaling, node health, MIG partitioning, and cost controls.

Deploy, scale, and manage Kubernetes workloads.

Implement Kubernetes security contexts, Pod Security Standards, and network policies.

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants.

Manage container registries including ECR, ACR, GCR, and Docker Hub.

Design and implement CI/CD pipelines, Docker configurations, deployment strategies, and infrastructure automation with production-ready patterns.

Hunt Kubernetes & Docker

Secure Docker images and container runtime configurations.

Build, optimize, and troubleshoot Docker containers and images.

Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.

Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong.

Provision Cloud SQL and Spanner databases. Configure high availability, backups, and security. Use when deploying managed databases on GCP.

Maintain IT asset inventory and configuration management database. Track hardware, software, and cloud resources. Use when managing IT assets.

Administer PostgreSQL databases. Configure replication, backups, and performance tuning. Use when managing PostgreSQL deployments.

Administer MongoDB databases. Configure replica sets, sharding, and backups. Use when managing MongoDB deployments.

Operate MySQL-compatible databases on PlanetScale with branching workflows, safe migrations, and production rollouts.

Provision and manage RDS databases. Configure backups, replication, and security. Use when deploying managed relational databases on AWS.

Provision Azure SQL Database and Cosmos DB. Configure security, backups, and replication. Use when deploying managed databases on Azure.

Deploy, manage, and optimize vector databases for AI applications.

Implement database backup strategies. Configure automated backups, retention, and recovery testing. Use when designing backup and recovery procedures.

Deploy and manage the ELK Stack (Elasticsearch, Logstash, Kibana) for log aggregation and analysis.

Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server.

Deploy Azure resources with ARM templates and Bicep. Create modular deployments and manage dependencies. Use when deploying Azure-native IaC.

Configure zero-downtime deployment strategies including blue-green, canary, and rolling deployments.

Secure OpenClaw deployments with preflight hardening checks, CI/CD guardrails, container runtime restrictions, and post-deploy verification.

Deploy frontend and full-stack apps on Vercel with previews, edge functions, environment promotion, and production guardrails.

Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs.

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI).

Guide for creating and writing Expo native modules and views using the Expo Modules API (Swift, Kotlin, TypeScript). Covers module definition DSL, native views, shared objects, config plugins, lifecycle hooks, autolinking, and type system.

Hunt Next.js specific vulnerabilities

使用 PageHeader 与 PageLayout 添加或更新应用页面头部与布局。在创建新页面、修复不一致的页头，或把 Service Map / Kubernetes / dashboard 页面迁移到共享布局时使用。

面向 TypeScript 与 JavaScript 开发者（Node.js 与浏览器）的 CCXT 加密货币交易所库。同时覆盖 REST API（标准）与 WebSocket API（实时）。帮助安装 CCXT、连接交易所、获取行情、下单、流式接收 ticker/订单簿、处理鉴权与管理错误。适用于在 TypeScript/JavaScript 项目中对接加密货币交易所、交易机器人、套利系统或投资组合管理工具。包含 REST 与 WebSocket 示例。

通过日志与事件诊断 GKE 工作负载故障（CrashLoopBackOff、OOMKilled、ImagePullBackOff、Pending 等）。在 Pod 无法启动或反复崩溃时使用。不用于 GKE 集群基础设施供给、节点池创建，或非 Kubernetes 的 Google Cloud 服务。

为 Google Cloud 中具备检索增强生成（RAG）能力的企业搜索系统发现需求，并生成架构、设计与部署指导。当用户需要以支持向量的 SQL 数据库作为嵌入向量的存储与索引、使用开放模型与开源推理框架，并用 Kubernetes 容器承载所有应用组件时使用。切勿用于全托管 RAG、SaaS 搜索服务，或需要非 SQL 向量数据库的场景。

为 GKE Autopilot 与 GKE Standard 集群生成并更新安全、可用于生产的 Kubernetes YAML 清单。用于创建或修改 GKE 部署清单、配置容器安全上下文、设置 CPU/内存资源限制、定义就绪/存活/启动探针、挂载 Secret 与卷、配置 GKE Gateway API 路由、面向 Spot VM，或部署 AI 模型推理工作负载（vLLM、TGI、Gemma）。不用于实时集群操作、Pod 排障（用 gke-workload-troubleshooting）或集群基础设施供给（用 gke-cluster-creation）。

面向 CLI、移动端、Web 与后端的发布流水线。引导版本递增、构建、测试、发布与部署。以 Claude Code 原生体验取代旧的交互式 release-it 流程。当用户输入 /release，或要求发布、推送、部署或交付任意组件时使用。

Sparse-clue OSINT investigation methodology for extracting overlooked leads, connecting fragmented evidence, and testing explanations across sources. Use for multi-step CTF challenges, image/video geolocation, event reconstruction, public-account and entity verification, artifact interpretation, infrastructure research, or stalled investigations.

Design, implement, review, or refactor native macOS 27 Golden Gate interfaces in SwiftUI or AppKit. Use when a Mac app must match Apple's current macOS 27 UI kit and restrained Liquid Glass language: integrated windows, full-height sidebars, native toolbars, flat lists, tables, and forms, clear pane boundaries, accessible materials, and removal of unnecessary nested cards, framed panels, or glassmorphism. Also use for Figma macOS 27 design-to-code work and audits of interfaces that feel too boxed.

Contributing to the Twenty codebase itself (twentyhq/twenty server internals), not for building apps on top of Twenty. Implement action handlers for executing workspace migrations in Twenty. Use when creating database operations for syncable entities, implementing universal-to-flat entity transpilation, or handling create/update/delete actions in the runner layer.

Contributing to the Twenty codebase itself (twentyhq/twenty server internals), not for building apps on top of Twenty. Wire syncable entity services into NestJS modules, create service layer and resolvers for Twenty entities. Use when registering builders, validators, and action handlers in modules, creating business services, or exposing entities via GraphQL API with proper exception handling.

编写仓库内的 SKILL.md 文件：frontmatter 与结构。