Azure Master
PluginComplete Azure cloud expertise covering 2025-2026 features. This plugin should be used for ANY Azure resource provisioning, AKS Automatic, Container Apps GPU, Azure OpenAI (GPT-5, reasoning models), Deployment Stacks, Azure ML workspaces, AI Foundry, compute clusters, endpoints, Terraform, networking, private endpoints, managed identities, debugging, and cost optimization.
This plugin acts as an expert system for Azure cloud services, providing detailed information and operational guidance for a vast range of resources including Kubernetes, Container Apps, Azure OpenAI, and infrastructure-as-code tools like Bicep and Terraform. It aims to cover the latest 2025-2026 features and best practices, including GPU support for AI workloads and network isolation patterns.
Scope
- warning:Single responsibility principleThe plugin attempts to cover an extremely broad scope, including almost all major Azure services, AI/ML, networking, security, and DevOps tools, which could lead to trigger bloat and reduced precision for specific tasks.
- info:Tool namingThe exposed slash commands `/azure-master:az-cli` and `/azure-master:azure-deploy` are descriptive but are broad entry points rather than specific tool names.
- warning:Minimal I/O surfaceThe broad nature of the `/azure-master:az-cli` and `/azure-master:azure-deploy` commands, which accept free-form natural language commands, implies a large and potentially unconstrained I/O surface.
- warning:Tool surface sizeThe plugin exposes two very broad slash commands that act as general entry points, rather than a precise set of 3-10 specialized tools.
Invocation
- warning:Scoped toolsThe plugin exposes two broad slash commands (`/azure-master:az-cli` and `/azure-master:azure-deploy`) which act as general-purpose execution interfaces rather than narrow verb-noun tools, potentially increasing the risk of model misselection.
- warning:Overlapping near-synonym toolsThe plugin exposes two broad commands (`az-cli`, `azure-deploy`) that cover a vast and overlapping set of Azure operations, forcing the model to disambiguate on every call.
Security
- info:Unguarded Destructive OperationsWhile Azure CLI and Bicep can perform destructive operations, the plugin relies on the user to provide and confirm commands, and the README indicates confirmation prompts for certain operations.
インストール
まずマーケットプレイスを追加
/plugin marketplace add josiahsiegel/claude-plugin-marketplace/plugin install azure-master@claude-plugin-marketplace類似の拡張機能
HashiCorp Agent Skills
98Terraform module generation and refactoring skills including module design and Terraform Stacks.
Terraform Master Plugin
95Complete Terraform expertise system for all cloud providers (Azure, AWS, Google Cloud) and platforms. PROACTIVELY activate for: (1) ANY Terraform task (init/plan/apply/validate), (2) Infrastructure-as-code design, (3) Resource import and state management, (4) Multi-environment architectures, (5) CI/CD pipeline integration, (6) Security scanning and best practices, (7) Version-aware code generation, (8) CLI mastery with -chdir and all flags. Provides: comprehensive provider knowledge (AzureRM/AWS/GCP/community), version-aware implementations, state operations (mv/rm/import), bulk import strategies (Terraformer/aztfexport), security scanning (tfsec/Checkov), enterprise architecture patterns, complete CLI reference, and platform-specific guidance (Windows/Linux/macOS).
Railway Tools
95Railway tools for Claude Code - manage projects, services, deployments
HCP Packer Registry Integration
95HCP Packer registry integration for tracking and managing image metadata.
Azure Skills Plugin
Microsoft Azure MCP integration for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Claude Code.
Modal Master Plugin
95Expert Modal.com serverless cloud platform system with comprehensive Modal 1.0 SDK (May 2025) features, GPU functions (T4/L4/A10G/L40S/A100/H100/H200/B200), autoscaler configuration, @modal.concurrent/@modal.batched decorators, Sandboxes for isolated code execution, CloudBucketMount for S3/GCS, and production deployment patterns. PROACTIVELY activate for: (1) ANY Modal.com task, (2) GPU configuration with fallbacks and multi-GPU, (3) Autoscaler settings (min/max/buffer containers, scaledown_window), (4) Web endpoints (FastAPI, ASGI, WSGI, custom servers), (5) @modal.concurrent for request concurrency, (6) @modal.batched for dynamic batching, (7) Sandboxes for untrusted code execution, (8) Scheduling (Cron with timezone, Period), (9) Storage (Volumes with commit(), Dict with TTL, Queue, CloudBucketMount), (10) Parallel processing (.map(), .starmap(), .spawn(), .for_each()), (11) Container lifecycle (@modal.enter, @modal.method, @modal.exit), (12) Image building (uv_pip_install, run_function for model downloads), (13) Secrets and environment management, (14) Deployment and CI/CD with GitHub Actions, (15) Cost optimization and 2025 pricing. Provides: Modal 1.0 stable API patterns, GPU selection guide with per-second pricing, autoscaler tuning strategies, concurrency and batching for ML inference, Sandbox security patterns, CloudBucketMount for external data, complete CLI reference, debugging workflows, and production-ready configurations.