Developer Tools

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities. Helps identify relevant skills by domain and task when users ask "how do I do X" or "find a skill for X" Integrates with the Skills CLI ( npx skills find , npx skills add ) to search, verify, and install packages from the skills.sh directory Recommends skills based on install count, source reputation, and GitHub stars to ensure quality before suggesting installation Presents skill options with install commands and links to skills.sh for user review and one-click installation

React and Next.js performance optimization guide with 64 prioritized rules across 8 categories. Organized by impact level, from critical waterfalls and bundle optimization down to advanced patterns, each rule includes incorrect/correct code examples and explanations Covers eight domains: async patterns, bundle size, server-side caching, client-side data fetching, re-render optimization, rendering performance, JavaScript efficiency, and advanced patterns Designed for use during component writing, code review, refactoring, and performance audits on React and Next.js applications Each rule has a prefix code (e.g., async-parallel , bundle-barrel-imports ) for easy reference in automated tooling and documentation

Pre-deployment validation for Azure infrastructure, configuration, and permissions before deployment. Requires .azure/plan.md from a prior azure-prepare run; stops immediately if the plan is missing Executes recipe-specific validation commands (azd provision, bicep build, terraform validate) and records proof in the plan document Performs build verification, configuration checks, and permission validation; blocks deployment if any check fails Only authorized method to set plan status to Validated ; must be followed by azure-deploy skill to execute the actual deployment

Guidance and reference material for instrumenting webapps with Azure Application Insights. Covers SDK setup, telemetry patterns, and configuration for ASP.NET Core and Node.js applications hosted in Azure Distinguishes between this skill (reference and guidance) and azure-prepare (actual implementation); invoke azure-prepare when the user wants to add instrumentation to their project Provides auto-instrumentation guidance for C# ASP.NET Core apps in Azure App Service, plus manual instrumentation paths for creating App Insights resources via Bicep templates or Azure CLI Includes language-specific code modification guides for ASP.NET Core, Node.js, and Python, plus quick references for OpenTelemetry SDKs and exporters

Microsoft Entra ID app registration, OAuth 2.0 configuration, and MSAL integration for secure application authentication. Covers app registration setup, authentication configuration, API permissions, and client credential management across web apps, SPAs, mobile apps, and daemon services Includes step-by-step workflows for first-time registration, console application authentication, and service-to-service credential flows Provides Azure CLI commands, MSAL library examples for .NET, JavaScript, Python, and Java, plus security best practices for secret rotation and token validation Distinguishes scope clearly: handles identity and authentication setup but excludes Azure RBAC, Key Vault secrets management, and resource security

Unified access to Azure blob storage, file shares, queues, tables, and data lake services. Supports five storage service types: Blob Storage for objects and backups, File Shares for SMB access, Queue Storage for async messaging, Table Storage for NoSQL key-value data, and Data Lake for big data analytics MCP server tools enable listing storage accounts, containers, and blobs, plus downloading and uploading blob content directly Configurable access tiers (hot, cool, cold, archive) and redundancy options (LRS, ZRS, GRS, GZRS) for cost and durability optimization CLI fallback available via az storage commands when MCP is not enabled; SDK references provided for Python, TypeScript, Java, Rust, and Go

Prepare Azure applications for deployment with infrastructure-as-code, configuration, and containerization. Generates Bicep or Terraform infrastructure code, azure.yaml configuration, and Dockerfiles based on application type and deployment target Requires mandatory plan-first workflow: analyze workspace, gather requirements, select recipe (AZD, AZCLI, Bicep, or Terraform), design architecture, then execute only after user approval Covers new app creation, modernization, and updates; routes specialized requests (copilot SDK, cloud migration, AI gateway) to dedicated skills before resuming preparation Hands off to azure-validate for infrastructure validation and azure-deploy for deployment execution; plan status must be updated to "Ready for Validation" before validation begins

Transform Azure resource groups into detailed architecture diagrams showing resource relationships and configurations. Discovers all resources within a resource group and analyzes their configurations, dependencies, and interconnections Generates Mermaid diagrams organized by logical layers (Network, Compute, Data, Security, Monitoring) with SKU details and connection labels Maps relationships including network connections, data flows, identity bindings, and configuration dependencies across resources Creates comprehensive markdown documentation with resource inventory tables, architecture diagrams, and relationship explanations

Fast discovery and inventory of Azure resources across subscriptions using Resource Graph queries. Queries any Azure resource type (VMs, storage accounts, web apps, container apps, Key Vaults, etc.) across subscriptions and resource groups in a single command Supports cross-cutting searches for orphaned resources, missing tags, unhealthy states, and resource inventory counts Routes single-resource-type queries to dedicated MCP tools when available; falls back to Azure Resource Graph for broader or unsupported resource types Uses KQL (Kusto Query Language) for flexible filtering, with built-in error handling for authorization, syntax, and scope issues

Find minimal Azure RBAC roles, generate assignment commands, and provide Bicep infrastructure code. Identifies built-in roles matching desired permissions using Azure documentation, or creates custom role definitions when no built-in role fits Generates Azure CLI commands and Bicep code snippets for assigning roles to identities, service principals, and managed identities Clarifies prerequisites for granting roles, including which permissions ( Microsoft.Authorization/roleAssignments/write ) are required and recommends least-privilege options like User Access Administrator Supports least-privilege access patterns by matching specific permission requirements rather than defaulting to broad roles

Diagnose and resolve Azure Event Hubs and Service Bus SDK issues with structured troubleshooting workflows. Covers connection failures, authentication errors, AMQP link issues, message lock timeouts, and event processor stalls across Python, Java, JavaScript, and .NET SDKs Includes language-specific troubleshooting guides for Event Hubs and Service Bus, plus connectivity diagnostics for ports, WebSocket fallback, IP firewalls, and private endpoints Provides MCP tools to query resource health, list namespaces/hubs/queues/topics, and search Microsoft Learn documentation for error resolution Structured diagnosis workflow: identify SDK version, check resource health, match error messages, look up docs, verify configuration, and apply fixes

Execute Azure deployments for prepared applications with built-in error recovery and validation. Requires .azure/plan.md with Validated status from azure-validate and azure-prepare skills; will not proceed without both prerequisites Executes azd up , azd deploy , terraform apply , and az deployment commands with error handling and post-deployment verification Includes pre-deploy checklist, recipe-based deployment workflows, and post-deploy configuration for SQL managed identity and Entity Framework migrations Supports applications with API Management gateway infrastructure created during preparation phase

Systematic diagnosis and remediation for Azure production issues using AppLens, Monitor, and resource health. Covers Container Apps, Function Apps, and AKS troubleshooting with service-specific guides for image pulls, cold starts, health probes, invocation failures, and node/pod issues Integrates AppLens (MCP) for AI-powered root cause analysis and Azure Monitor (MCP) for KQL-based log and metric queries Provides a five-step diagnostic flow: identify symptoms, check resource health, review logs, analyze metrics, and investigate recent changes Includes quick reference commands for activity logs, container logs, and App Insights queries, plus routing guidance for AKS-specific incidents

Fast, persistent browser automation with session continuity across sequential agent commands. Supports three browser modes: headless Chromium, real Chrome with profile support, and cloud-hosted remote browsers with proxy configuration Includes 15+ command categories covering navigation, page inspection, interactions, data extraction, cookie management, and JavaScript execution Offers cloud session management, local server tunneling via Cloudflare, and parallel subagent execution through remote sessions Built-in Python integration for setting variables, accessing the browser object, and running scripts within the automation context

Recommend Azure VM sizes, scale sets, and configurations based on workload requirements and budget. Analyzes workload type, performance needs, scaling requirements, and cost to suggest 2–3 VM or VMSS options with trade-offs Verifies recommendations against live Microsoft documentation; falls back to reference files if fetch fails Queries the unauthenticated Azure Retail Prices API for current pricing without requiring an Azure subscription Guides VM vs VMSS decision through a decision tree covering autoscaling, instance count, availability, and statefulness Covers all VM families (general purpose, compute/memory optimized, GPU, confidential computing) and VMSS orchestration modes (Flexible vs Uniform)

Assess and migrate cloud workloads from AWS, GCP, and other providers to Azure services. Supports Lambda-to-Azure Functions migration with dedicated scenario reference and best practices Generates assessment reports mapping source services to Azure equivalents before any code conversion Converts source code to target Azure runtime models, with output isolated in a separate <source-folder>-azure/ directory Requires sequential phase execution: assessment first, then migration, with user confirmation before destructive actions Hands off to azure-prepare skill for infrastructure provisioning, local testing, and deployment workflows

Create, test, and iteratively improve AI agent skills with structured evaluation and benchmarking. Guides you through the full skill development lifecycle: intent capture, drafting, test case creation, evaluation, and iteration based on user feedback Runs parallel test cases with and without the skill to measure impact, capturing timing and token usage for quantitative comparison Generates an interactive browser-based reviewer showing outputs, qualitative feedback, and benchmark metrics (pass rates, latency, token efficiency) across iterations Includes description optimization to improve skill triggering accuracy by testing 20 realistic trigger/non-trigger queries and iterating the description through up to 5 rounds

Check and manage Azure quotas and usage across regions for deployment planning and capacity validation. Azure CLI ( az quota ) is the only reliable method for checking quotas; REST API and Portal are unreliable and may show misleading "No Limit" values that do not indicate unlimited capacity Supports four core workflows: checking specific resource quotas, comparing capacity across regions, requesting quota increases, and listing all quotas for a provider Quota resource names do not map 1:1 to ARM resource types; use az quota list to discover correct names by matching localizedValue descriptions Covers Microsoft.Compute, Microsoft.Network, Microsoft.App, Microsoft.Storage, and Microsoft.MachineLearningServices; some providers like Cosmos DB are unsupported and require Portal or documentation