Infrastructure plugins

Design and document backend architectures using patterns like Clean Architecture, Domain-Driven Design, microservices, and event sourcing with CQRS, while generating architecture diagrams and managing Architecture Decision Records (ADRs) with MADR templates.

Build and manage cloud infrastructure and deployment pipelines with AWS serverless, Docker, Kubernetes, Terraform, and CI/CD workflows, including environment setup, containerization, GitOps, and production deployment strategies.

Extend Claude Code with a dedicated DevOps team for cloud infrastructure lifecycle management—designing, deploying, securing, and operating production systems across AWS, Azure, and GCP using Kubernetes, Terraform, CI/CD, and SRE practices.

Connect Claude to a private MCP server through an Anthropic-operated tunnel by running a Docker Compose stack that provisions certificates, proxy config, and a Cloudflare tunnel.

Integrate Terraform Cloud/Enterprise into your local IaC workflow via Docker subprocess, using TFE_TOKEN to manage workspaces, run plans, apply deployments, inspect and manipulate state for automated infrastructure provisioning and updates.

Launch GPU/TPU clusters, training jobs, and inference servers across 25+ clouds using SkyPilot. Deploy to Kubernetes pods and Slurm jobs; debug YAML configs and optimize costs in your AI workflow.

Build, deploy, and manage the full Cloudflare platform — Workers, Durable Objects, AI agents, email, Zero Trust, and web performance — with skills for scaffolding projects, writing production code, managing infrastructure via Wrangler CLI and API, and auditing Core Web Vitals.

Diagnose Mooncake deployment and runtime issues by checking services, RDMA devices, environment variables, connectivity, and logs, with automatic fix suggestions.

Analyze your codebase and infrastructure for performance bottlenecks across frontend, backend, and architecture. Get prioritized optimization recommendations, impact estimates, quick wins, phased implementation roadmaps, and code examples to improve speed and efficiency.

Generate complete Ansible playbooks, roles, inventories, and configurations to automate server provisioning, app deployments, service setups, and idempotent DevOps workflows with production-ready YAML, best practices, security hardening, and built-in documentation.

Generate production-ready Docker Compose YAML files for multi-container applications, configuring services, networks, volumes, health checks, resource limits, dependencies, and environment overrides for dev and prod workflows.

Generate production-ready Helm 3 charts for Kubernetes apps from natural language descriptions. Produces Chart.yaml, values.yaml with multi-environment overrides, Go templates, helpers, health probes, security contexts, and applies best practices for scalability, security, and documentation.

Integrate secrets managers like Vault, AWS Secrets Manager, GCP Secret Manager, and Azure Key Vault into applications and infrastructure. Generate policies, auth configs, rotation schedules, Kubernetes manifests, retrieval code, setup scripts, and documentation from simple inputs.

Generate production-ready Google Cloud code examples, starter kits, and templates for AI agents and apps from official ADK, Genkit, and Vertex AI sources. Adapt to Python, TypeScript, or Go with security, monitoring, Firebase, and Terraform IaC integration.

Optimize Ethereum and L2 transaction gas fees by fetching real-time prices, estimating DeFi costs, predicting patterns, identifying optimal timing windows, and recommending cheaper sidechain routes like Polygon for maximum savings.

Generate modular, production-ready Infrastructure as Code configurations for Terraform, CloudFormation, Pulumi, ARM templates, and CDK across AWS, GCP, and Azure clouds, including variables, outputs, and remote state setup.

Generate production-ready, reusable Terraform modules for AWS, GCP, and Azure from a name and description. Automatically includes variables, outputs, validations, security best practices, scalable architecture, examples, and auto-generated README documentation.

Generate production-ready GitOps workflows for Kubernetes using ArgoCD or Flux, creating manifests, sync policies, multi-environment promotions, RBAC configurations, notifications, and CI/CD integrations for secure, scalable continuous deployments.

Manage environment configurations and secrets across dev/staging/prod deployments using .env files, Kubernetes ConfigMaps/Secrets, and AWS SSM. Audit values, encrypt secrets with sops, validate schemas, detect drift, and run promotion workflows. Generate secure, scalable DevOps setup code for Docker, Kubernetes, Terraform, AWS, and GCP infrastructure.

Monitor CPU, memory, disk I/O, network usage, DB connections, and processes on Linux systems to identify bottlenecks, then generate monitoring code, dashboard configs, alerts, and right-sizing recommendations for resource optimization and cost reduction.

Provision secure GCP infrastructure for Vertex AI ADK and Agent Engine deployments using Terraform. Automate setup of Agent Engine runtime, code execution sandbox, Memory Bank, VPC Service Controls, IAM roles, and networking to enable scalable AI agent workflows.

Provision Terraform infrastructure for Genkit AI apps on Firebase Functions, Cloud Run, or GKE, handling secrets, monitoring dashboards, auto-scaling, and CI/CD pipelines in a single workflow.

Provision Vertex AI infrastructure on GCP using Terraform modules to deploy Model Garden models, Gemini endpoints, vector search indices, ML pipelines, encryption, auto-scaling, and IAM roles for Agent Engine.

Build .NET applications that provision Azure infrastructure (databases, caches, bots), integrate AI services (agents, OpenAI, voice, document intelligence, search), manage events/messaging (Event Grid, Hubs, Service Bus), authenticate via Entra ID, and handle Key Vault cryptography using official SDKs and ARM clients.

Build production-ready API gateways for microservices, implementing intelligent routing, authentication, rate limiting, load balancing, circuit breakers, health checks, and response transformations. Deploy to Kong, Express Gateway, AWS API Gateway, or custom Node.js/Go/Express servers to proxy and manage backend traffic securely.

Generate .devcontainer configurations for Python, Node, Rust, and Go projects with integrated Claude Code plugins, language tooling like uv/fnm, and persistent volumes to create isolated, reproducible development environments.

Automate Vast.ai GPU rentals for ML workflows: search offers by price/specs, provision instances, deploy Docker jobs via SSH/CLI, optimize costs with spot instances and auto-teardown, troubleshoot errors, monitor metrics, handle preemptions, and integrate into GitHub Actions CI/CD.

Audit Terraform, Kubernetes, and cloud configurations for CIS, SOC2, HIPAA, PCI-DSS compliance using Checkov, tfsec, and OPA. Generate detailed reports, remediation patches, CI/CD gating steps, plus production-ready secure DevOps configurations, setup code, and documentation with security-first best practices.

Automate intelligent YAML validation, linting, schema inference, normalization, and transformation for Kubernetes manifests, GitHub Actions workflows, and Docker Compose files. Receive minimal patches, detailed issues, and ready-to-run validation commands to fix configs quickly.

Analyze AWS, GCP, and Azure costs through APIs to identify idle resources, top spenders, and savings opportunities like rightsizing, reservations, spot instances, and storage tiering. Generate Terraform IaC changes, cost reports, alerts, and optimized DevOps configurations from infrastructure descriptions.

Deploy centralized log aggregation stacks like ELK, Grafana Loki, or Splunk on Docker or Kubernetes, complete with shippers, parsing rules, retention policies, dashboards, alerting, and RBAC. Generate YAML configurations, feature lists, documentation, and code for DevOps logging infrastructure.

Generate disaster recovery plans for cloud infrastructure, defining RTO/RPO targets, multi-region failover, Terraform standby resources, database replication, failover scripts, runbooks, plus production-ready DevOps configs and documentation.

Design and execute chaos engineering experiments to inject failures like network latency, service crashes, resource exhaustion into Kubernetes clusters and Docker containers, validating distributed system resilience and recovery using tools like Chaos Mesh and AWS FIS.

Generate production-ready service mesh configurations for Kubernetes microservices using Istio, Linkerd, or Consul Connect. Automate mTLS encryption, traffic routing, resilience policies, observability setups, plus supporting code and documentation based on your infrastructure requirements.

Configure auto-scaling policies for AWS ASG, GCP MIG, Azure VMSS, and Kubernetes HPA. Generate Terraform, YAML, or CLI configs tailored with metric thresholds and cooldowns. Create production-ready DevOps setups, code, and documentation for scalable secure infrastructure.

Set up automated metrics collection across compute, storage, network, containers, load balancers, and databases. Generate agent configurations, inventories, dashboards, alerts, and integrations with Prometheus, Datadog, or CloudWatch to enable performance monitoring and troubleshooting.

Scan Docker images and Dockerfiles for vulnerabilities, misconfigurations, and compliance using Trivy, Grype, Snyk, and Hadolint. Generate remediation reports with CI/CD integration plus production-ready secure container configurations, setup code, and documentation.

Orchestrate multi-stage deployment pipelines across dev, staging, and prod environments using Kubernetes and CI/CD platforms like GitHub Actions and Jenkins. Apply strategies such as blue-green, canary, and rolling updates. Generate production-ready pipeline configurations, setup code, and documentation tailored to Docker, Terraform, and AWS infrastructure.

Generate Kubernetes NetworkPolicy manifests enforcing zero-trust networking via ingress/egress rules with pod labels, namespaces, CIDRs, and ports. Create production-ready configurations, setup code, and documentation matching your infrastructure and security requirements.

Analyze infrastructure capacity by evaluating CPU, memory, storage, and network utilization to forecast growth trends, identify bottlenecks, project future needs, and receive scaling recommendations with cost estimates and monitoring setups.

Detect drift between cloud infrastructure and IaC definitions using Terraform plan, CloudFormation detect-stack-drift, or Pulumi preview. Parse changes into resource-level reports with remediation suggestions. Generate production-ready DevOps configurations, setup code, and documentation from infrastructure specs.

Generate production-ready load balancer configurations for AWS ALB/NLB, GCP, Nginx, and HAProxy by providing DevOps requirements and infrastructure specs. Outputs include health checks, SSL termination, routing rules, sticky sessions, monitoring, setup code, and documentation.

Test load balancing strategies by validating traffic distribution, health checks, failover, session persistence, and SSL on live NGINX, HAProxy, AWS ALB/NLB, GCP, and Kubernetes Ingress setups. Generate Jest test suites to verify these behaviors across backends.

Implement backup strategies for databases (PostgreSQL, MySQL, MongoDB), filesystems, and AWS resources using tar, rsync, pg_dump, and S3. Automate scheduling, retention, encryption, verification, and disaster recovery, while generating configs, setup code, and documentation for production DevOps.

Audit IaC templates like Terraform and CloudFormation, Docker and Kubernetes manifests, nginx configs, and app settings for security misconfigurations against OWASP and CIS benchmarks. Scan current projects for issues in code and settings, reporting problems with potential fixes.

Deploy, scale, manage, and optimize full-stack apps on Fly.io: from hello-world launches and GitHub Actions CI/CD to multi-region architectures, Postgres/Redis clusters, performance tuning, cost optimization, security hardening, error diagnosis, and Machines API scripting.

Research infrastructure best practices via enhanced web search and automatically generate deployable Terraform modules, Dockerfiles, Kubernetes manifests, Pulumi programs, and CI/CD pipelines for AWS, GCP, or Azure deployments.

Automate Oracle Cloud Infrastructure (OCI) management: provision compute instances, VCNs, databases; deploy containers to Kubernetes; configure RBAC, monitoring, budgets; set up Terraform CI/CD pipelines; troubleshoot errors, handle migrations from AWS/Azure, and optimize performance/costs using Python SDK, CLI, and bash skills.

Integrate QuickNode RPC endpoints into Ethereum and Solana dApps using ethers.js in TypeScript/Node.js: set up connections, query blocks/balances/transactions/NFTs, send transactions, handle errors/rate limits, enable real-time Streams/webhooks, tune performance/costs, secure setups, and follow CI/prod checklists.

Deploy, debug, optimize, monitor, and secure GPU-accelerated ML inference and training workloads on CoreWeave Kubernetes clusters, including cost tuning, data handling, migrations from AWS/GCP/Azure, CI/CD automation, and production checklists.

Optimize Kubernetes costs with Cast AI: deploy agents via Helm or Terraform, configure autoscalers and policies for spot instances and right-sizing, integrate cost checks into GitHub Actions CI/CD, debug agent issues, secure RBAC and API keys, and monitor savings across EKS/GKE/AKS using 18 targeted skills.

Manage and deploy Azure cloud resources from Claude Code: provision infrastructure with Terraform/Bicep, deploy apps (Python web apps, Copilot SDK, containers), monitor with Application Insights, handle RBAC and Entra ID authentication, migrate from AWS/GCP, analyze costs, run AI workloads (AI Search, OpenAI, Foundry agents), and ensure compliance.

Debug Buttercup CRS deployments on Kubernetes by triaging pod crashes, restart loops, Redis failures, DinD issues, queues, and service problems in the crs namespace using kubectl events and logs.

Delegate specialized AI agents to design cost-optimized cloud architectures on AWS/Azure/GCP using Terraform, administer and optimize PostgreSQL/MySQL/MongoDB databases, troubleshoot DevOps outages with logs/metrics analysis, configure CI/CD pipelines with Docker/Kubernetes, and debug networks with nginx/HAProxy.

Build NVIDIA-powered workflows across GPU acceleration, CUDA, AI inference, robotics, Omniverse USD scenes, and Physical AI — from setup and validation to deployment and optimization on Docker, Kubernetes, or Azure.

Delegate specialized AI agents to build secure Solidity smart contracts, DeFi protocols, and full Web3 apps including tests, gas optimization, audits, and frontend integration. Develop production Hyperledger Fabric v2.5/v3 enterprise blockchains with Go/Java/TypeScript chaincode, network architecture, Kubernetes deployments, Raft/SmartBFT consensus, channels, MSPs, and privacy features.

Generate and format Terraform HCL code per HashiCorp style guides, bulk import existing AWS and Azure resources into state via search queries, certify modules for AVM compliance, and author .tftest.hcl tests for validation, mocks, and CI/CD pipelines.

Develop Terraform providers in Go with Plugin Framework: scaffold projects, implement resources/data sources/actions with CRUD and lifecycle hooks, run acceptance tests via patterns and TF_ACC, generate/validate Registry docs using tfplugindocs.

Manage the full AWS lifecycle from infrastructure-as-code and serverless deployments to cost optimization, observability, and AI/ML on Bedrock, with SDK patterns for JavaScript, Python, and Swift.

Refactor monolithic Terraform configurations into reusable modules following HashiCorp best practices, including clear interfaces, encapsulation, documentation, testing, and state migration. Generate, modify, validate, and manage Terraform Stacks for multi-region and multi-environment infrastructure deployments from local, public, or private sources.

Build custom AMIs for AWS EC2, Azure managed images and Compute Gallery images, and Windows VM images using Packer builders with HCL templates, provisioners like PowerShell and WinRM, multi-region copies, and authentication setups.

Push Packer build metadata to HCP Packer registry for image versioning, governance, and lifecycle tracking. Configure HCL with AWS examples, authentication, and GitHub Actions CI/CD integration to automate image management in pipelines.

Build optimized Docker images from context using best practices for caching, security, and minimal size, or optimize existing Dockerfiles for faster builds and smaller footprints. Includes automated analysis, smoke tests, vulnerability scans, size/layer comparisons, and detailed reports.

Deploy applications to AWS with architecture recommendations, cost estimates, and infrastructure-as-code generation using CDK, CloudFormation, or Terraform. Generates validated AWS architecture diagrams as draw.io XML and queries AWS pricing data for cost estimation.

Search academic papers across arXiv, PubMed, IEEE Xplore, Scopus, ACM DL, and Semantic Scholar by keywords, authors, or topics using Docker-hosted MCP tools integrated into Claude Code. Setup verifies Docker, pulls the image, and restarts the environment for seamless access.

Provides 193+ expert skills for every major Azure service—compute, data, AI/ML, networking, security, and management—delivering troubleshooting, architecture guidance, deployment patterns, and best practices directly in your development workflow.

Interactively configure secure Google Cloud Storage buckets and Cloud Run services following best practices, generating Terraform or gcloud commands, Dockerfiles, IAM setups, scaling, monitoring, CI configs, and documentation for quick deployment.

Debug failing Kubernetes pods with kubectl by analyzing events, logs, status, resources, and configs to diagnose root causes with evidence and suggested fixes. Generate production-ready Kubernetes manifests (Deployment, Service, ConfigMap, Secret, Ingress, HPA) from Dockerfile, .env files, and docker-compose, including Kustomize overlays, validation, and best practices.

Generate complete, validated Terraform modules by prompting for purpose like networking or compute, including full dir structure, vars, resources, outputs, README, and examples. Plan infrastructure changes with summarized diffs, risk highlights, cost estimates, confirmation, then apply.

Fully manage Ubiquiti UniFi networks via Rust CLI, TUI, and AI agent for VLANs, SSIDs, firewalls, NAT, DHCP reservations, clients, devices, events, stats, DPI, backups, and raw API access. Audit configurations for security vulnerabilities like open WiFi or permissive rules with ranked remediations. Run health checks on controllers, devices, alarms, and clients. Deploy autonomous agents for diagnostics and ongoing control.

Build, train, and deploy AI models on AWS SageMaker with deep ML expertise: validate datasets, fine-tune models (SFT, DPO, RLVR), generate Jupyter notebooks, evaluate model quality, and diagnose HyperPod cluster issues (NCCL, GPU, Slurm, EKS) — all from your coding assistant.

Manage and monitor UniFi network infrastructure — devices, clients, firewall, VPN, routing, and WLANs — via natural language or MCP tools, with built-in safety controls, rollback, health diagnostics, and firewall policy auditing.

Manage Azure cloud resources, deploy applications, and monitor infrastructure directly from Claude Code. Covers provisioning, cost analysis, security audits, AI services, Kubernetes, and migration from other clouds.

Provision and manage Hetzner Cloud infrastructure using guided hcloud CLI sessions: interactively build decision trees to deploy servers, networks, firewalls, load balancers, volumes, and storage with precise commands.

Manage Oracle Cloud Infrastructure resources with guidance on OKE cluster design, networking, troubleshooting, and Enterprise AI workflows including Generative AI, RAG, agents, cost estimation, and governance

Interactively configure secure AWS S3 buckets with encryption, versioning, lifecycle rules, and logging, then generate CloudFormation or CDK IaC plus documentation. Set up complete Lambda functions with handler code in Node/Python/Go, IAM roles, DynamoDB triggers, and IaC via CloudFormation/SAM/CDK.

Automate full-stack deployment setup by generating tailored GitHub Actions CI/CD workflows with lint/test/build/deploy jobs, optimized multi-stage Dockerfiles for Node.js/Python/Go/Rust/Java projects, and production Kubernetes manifests including Deployment/Service/Ingress/HPA/NetworkPolicy.

Generate monitoring dashboards for Grafana, Datadog, or CloudWatch with metrics, panels, layouts, interactions, and observability settings. Set up alerting for app and infrastructure metrics including thresholds, runbooks, and tests with stack summaries.

Interactively configure secure Azure Blob Storage accounts with encryption, lifecycle policies, network rules, and IaC templates, then set up and deploy Azure Functions apps complete with triggers, bindings, auth, monitoring, and CI/CD pipelines.

Audit infrastructure for security vulnerabilities, misconfigurations, optimizations, and compliance, generating reports with prioritized findings, remediations, and cost estimates. Plan and execute updates through a 7-step process featuring risk assessment, staging tests, backups, verification, and rollback procedures.

Build, debug, and deploy Microsoft 365 Agents SDK agents in TypeScript/JavaScript. Debug via checklists for build verification, DEBUG logs, .env validation, Azure AD auth, and Agents Playground testing. Host multichannel agents for Teams/Copilot/web using @microsoft/agents-hosting-express with Azure setup. Provision Azure Bot resources and configure auth (Managed Identity, secrets) via az CLI for Node or dotnet apps.

Orchestrate IaC workflows with Atmos CLI across Terraform, Helmfile, Ansible, and Packer stacks: configure components/stacks with inheritance and YAML functions, manage multi-cloud auth/stores, validate schemas/policies, vendor modules, introspect changes, execute GitOps CI/CD, and run multi-step automation.

Navigate Cloudflare's full product suite—compute (Workers, Pages), storage (R2, D1, KV), AI (Workers AI, Vectorize), networking, security, and IaC (Terraform, Pulumi)—via interactive decision trees to select services and retrieve prioritized documentation for deployments.

Launch, control, and debug Polar's Docker local dev environment for FastAPI API, Next.js web app, PostgreSQL, and Redis—start/stop services, tail logs, shell access, status checks. Reference and implement billing workflows: Stripe subscriptions, checkouts, proration, dunning, benefit provisioning in Django backend.

Set up Azure MCP server with Azure CLI authentication and manage 40+ Azure services like Storage, Key Vault, Cosmos DB, AKS clusters, and Log Analytics directly in Claude conversations. Handles prerequisites (Azure CLI, Node.js 20+, RBAC), login verification, and resource operations including listing, creating, and querying.

Design, build, deploy, test, and debug serverless applications on AWS using SAM, CDK, Lambda, API Gateway, EventBridge, and Step Functions, with infrastructure-as-code templates and CI/CD pipelines.

Generate production-ready AWS CloudFormation templates for VPCs, EC2, ECS, RDS, DynamoDB, Lambda, S3, CloudFront, ElastiCache, Bedrock, and security groups; deploy ECS services via GitHub Actions CI/CD; bootstrap SAM projects; create Draw.io architecture diagrams; automate AWS CLI workflows; optimize costs; and review designs with expert agents.

Manage the full lifecycle of LLM evaluations on Slurm clusters: launch, monitor, debug, and analyze results via NeMo Evaluator SDK. Create custom benchmarks with the BYOB framework and interactively configure evaluation launchers.

Orchestrate AWS Amplify Gen 2 workflows to build full-stack web and mobile apps with authentication, data models, storage, GraphQL APIs, and Lambda functions, then deploy to sandbox or production using React, Next.js, Vue, Angular, React Native, Flutter, or Android.

Analyze and optimize Azure cloud costs with FinOps Toolkit: generate optimization reports from Advisor and KQL queries, perform month-over-month analysis with anomaly detection and forecasting, deploy and manage FinOps Hubs, query Data Explorer databases, and consult specialized agents for strategy and best practices.

Guide cloud services to FedRAMP ATO with readiness assessments, SSP and POA&M authoring, NIST 800-53 Rev 5 control mapping, gap analysis, architecture reviews, and continuous monitoring setup on AWS, GCP, or Azure.

Connect Claude to Google Cloud Observability via local MCP to query and analyze metrics, logs, traces. Automatically setup GCloud CLI with authentication, project config, and installation checks. Apply best practices for structured logging, query filters, alerts, and log cost optimization.

Interactively select architecture paradigms for software systems via scenario matching, compare trade-offs for team size and complexity, generate ADRs, and receive tailored implementation plans with steps, deliverables, risks, and mitigations for client-server, CQRS, event-driven, hexagonal, microservices, and more.

Set up SAP BTP accounts with entitlements and quotas, deploy multi-target applications to Cloud Foundry or Kyma environments, develop ABAP apps using RAP and CDS models, configure XSUAA identity providers and connectivity via destinations or Cloud Connector, operate with btp or CF CLI, and implement CI/CD pipelines for SAP solutions.

Automate DevOps tasks with an AI agent that configures CI/CD pipelines for testing and deployment, provisions scalable cloud infrastructure using Terraform with auto-scaling, orchestrates containers via Docker and Kubernetes, and sets up monitoring and alerting systems.

Delegate infrastructure maintenance for studio apps: perform health checks, diagnose performance bottlenecks, optimize scaling, audit costs, set up monitoring and alerting, and prevent disasters to ensure reliability and smooth operation.