Azure-Samples

Use when starting or refining a project's requirements, before any planning or coding. Supports sub-commands `sync`, `reverse`, and `validate`.

Use when local verification passed and the feature is ready to ship to Azure.

Use when a plan exists and the application source or IaC needs to be created or updated.

Use when a spec exists and an implementation or Azure deployment plan is needed, before writing code.

Use when the user wants to run the full Specify → Plan → Implement → Deploy loop end-to-end in one shot. Accepts a free-form prompt that is passed to specify.

Use when implementation exists and needs to be exercised locally against provisioned Azure dependencies, before deploying.

Create Azure architecture diagrams, flowcharts, data-flow visualizations, or illustrations as Excalidraw documents with embedded official Azure service icons, and export them as SVG and PNG. Use whenever the user wants to draw, sketch, diagram, visualize, or…

Execute pending tasks from tasks.md / tasks.json, updating both on completion.

Read-only — assemble the wider runtime picture of a deployed voice app from azd deployment artifacts and Azure Monitor (Application Insights / Log Analytics) via Azure MCP or az CLI, then render it as KQL, call timelines, latency waterfalls, and mermaid…

Service catalog and guided onboarding for the azd deployment. USE WHEN the user wants to discover, install, set up, or be walked through the deployable components (Azure OpenAI/AI Foundry, Speech, ACS/telephony, Cosmos DB, Redis, Container Apps, Key Vault,…

Agent-first, read-only diagnosis of the voice pipeline (deploy, telephony, STT, LLM, TTS, state) — gather evidence via Azure MCP / azd artifacts / CLI, probe the user for missing details, and recommend fixes without changing anything

Require relevant tests and documentation updates for any code or config change, and report what was run.

Create or update evaluation scenarios for the tests/evaluation framework, including session-based scenarios and A/B comparisons

Guide azd-based deployments, including where azure.yaml and azd hook scripts live, the current deployment flow, troubleshooting docs, and regional/model availability checks for Azure OpenAI

Add a new React component with Material UI

Add a new FastAPI endpoint to the API

Break down Azure Kubernetes Service spend by cluster, namespace, and utilization bucket. Identifies the most expensive clusters and namespaces, and how much spend sits in idle vs active workloads. WHEN: "AKS cost", "Kubernetes cost", "cluster cost",…

Current spend vs limits, end-of-month forecast, and active alerts. WHEN: "budget status", "am I over budget", "budget health", "will I exceed budget", "budget forecast". INVOKES: list_budgets, forecast_costs, query_costs, list_alerts

Create a budget with sensible default thresholds, contact emails, and an optional action group. WHEN: "create budget", "setup budget", "need a budget", "no budgets", "budget recommendations". INVOKES: list_budgets, query_costs, forecast_costs, create_budget

RI/Savings Plan utilization, coverage of compute spend, new purchase recommendations, and an optional investigation when utilization drops. WHEN: "commitment benefits", "RI utilization", "savings plan utilization", "reservation coverage", "utilization…

Check Azure Policy SKU/region restrictions, tag compliance, and budget coverage via Azure Resource Graph. WHEN: "what SKUs are allowed", "can I deploy this", "check policy", "allowed VMs", "will this be denied", "tag compliance", "budget coverage",…

Explain a cost spike or unexpected charge: when it happened, which service drove it, what changed, and who owns the resources. WHEN: "why did cost go up", "cost spike", "unexpected charge", "explain increase", "bill higher than expected", "surprise cost".…

Surface right-sizing recommendations (Azure Advisor) filtered by SKU policy and flagged against existing commitments, plus quick-win cleanup candidates. WHEN: "optimize costs", "reduce spending", "right-size", "savings opportunities", "save money",…

Look up Azure retail pricing for a service / SKU / region, compare options across regions or commitment types, estimate workload cost, and optionally retrieve negotiated prices via pricesheet download. WHEN: "how much will it cost", "estimate cost", "compare…

Reviews Azure SDK .NET code samples for best practices, credential handling, error patterns, Aspire orchestration, and documentation compliance. Trigger: "review .NET Azure SDK sample", "check dotnet sample", "Azure SDK .NET review".

Reviews Azure SDK Go code samples for best practices, credential handling, idiomatic error handling, context propagation, and documentation compliance. Trigger: "review Go Azure SDK sample", "check Go sample", "Azure SDK Go review".

Reviews Azure SDK Java code samples for best practices, credential handling, error patterns, Spring Boot integration, and documentation compliance. Trigger: "review Java Azure SDK sample", "check Java sample", "Azure SDK Java review".

Reviews Azure SDK Python code samples for best practices, credential handling, async patterns, error handling, and documentation compliance. Trigger: "review Python Azure SDK sample", "check Python sample", "Azure SDK Python review".

Reviews Azure SDK Rust code samples for best practices, credential handling, ownership patterns, async runtime usage, error propagation, and documentation compliance. Trigger: "review Rust Azure SDK sample", "check Rust sample", "Azure SDK Rust review".

Reviews Azure SDK samples for best practices, credentials, errors, and docs. Auto-detects language.

Reviews Azure SDK TypeScript code samples for best practices, credential handling, error patterns, and documentation compliance. Trigger: "review TypeScript Azure SDK sample", "check TypeScript sample", "Azure SDK TypeScript review".

Migrate existing Azure Durable Functions apps from existing backend storage providers (Azure Storage, Netherite, MSSQL) to the Durable Task Scheduler. Use when switching backends, converting to azureManaged storage provider, upgrading from Azure Storage…

Build durable, fault-tolerant workflows in Java using the Durable Task SDK with Azure Durable Task Scheduler. Use when creating orchestrations, activities, or implementing patterns like function chaining, fan-out/fan-in, human interaction, or monitoring.…

Build durable, fault-tolerant workflows in JavaScript/TypeScript using the Durable Task SDK with Azure Durable Task Scheduler. Use when creating orchestrations, activities, entities, or implementing patterns like function chaining, fan-out/fan-in, human…

Build durable, fault-tolerant workflows in Python using the Durable Task SDK with Azure Durable Task Scheduler. Use when creating orchestrations, activities, entities, or implementing patterns like function chaining, fan-out/fan-in, human interaction, or…

Build durable, fault-tolerant workflows using Azure Durable Functions with .NET isolated worker and Durable Task Scheduler backend. Use when creating serverless orchestrations, activities, entities, or implementing patterns like function chaining,…

Build durable, fault-tolerant workflows in .NET using the Durable Task SDK with Azure Durable Task Scheduler. Use when creating orchestrations, activities, entities, or implementing patterns like function chaining, fan-out/fan-in, human interaction, or…

Guide for creating new AI Gateway labs. Use when users want to create a new lab in the labs/ folder. This skill provides the standard lab structure, templates, and patterns used across the AI Gateway repository including Jupyter notebooks, Bicep…

Guide for creating Azure API Management (APIM) XML policies. Use when users want to create, modify, or understand APIM policies including inbound/outbound processing, authentication, rate limiting, caching, transformations, AI gateway policies, and policy…

Guide for building Bicep files for Azure API Management (APIM) and related Azure services. Use when users want to create, modify, or understand Bicep templates for APIM instances, APIs, backends, subscriptions, policies, products, loggers, diagnostics, and…

Guide for creating Kusto Query Language (KQL) queries for Azure API Management tables in Azure Monitor (Log Analytics Workspace). Use when users want to query, analyze, or monitor APIM logs including gateway logs, LLM/AI logs, MCP logs, WebSocket logs, and…

Guide for creating Terraform files for Azure API Management (APIM) and related Azure services. Use when users want to create, modify, or understand Terraform configurations for APIM instances, APIs, backends, subscriptions, policies, products, loggers,…

Reusable session pattern for modernized .NET apps that add observability, grounded search, reporting, MCP tools, and A2A agents.

Package an Aspire modernization session with docs, demo flow, and architecture notes

Keeps scenario README files and session docs aligned with the repo's documentation conventions.

Clone the closest existing eShopLite scenario baseline before adding a new modernization story.

{what this skill teaches agents}

Deprovision Azure resources for the Azure Cosmos DB NoSQL create-index samples by authenticating with azd, confirming the target subscription, and running azd down. Use when the user asks to tear down, deprovision, or remove create-index sample resources.

Provision Azure resources for the Azure Cosmos DB NoSQL create-index samples by authenticating with azd, selecting an Azure subscription, and running azd up. Use when the user asks to provision, deploy, initialize, or restore create-index sample resources.

Run and validate all five Azure Cosmos DB create-index samples after deployment. Triggers include "validate create-index samples", "run all create-index languages", "check create-index output", and "verify the final tables". Compares generated output with…

Configure or run structural validation for a manifest-defined repository sample set. Use when asked to add a reusable sample-set validator, validate final-table structure and semantic keys, test a validation manifest, or generate timestamped evidence for a…

Clean generated files from the Azure Cosmos DB NoSQL create-index samples. Use for requests to clean create-index samples, remove create-index build artifacts, delete generated create-index output, or reset create-index sample dependencies.

Correct sticky positioning with header alignment and accessible search/filter controls

Proper flex truncation for title+badge rows in Tailwind CSS

Diagnose and fix React render loops caused by unstable effect or callback dependencies

How to extend the AI Policy Engine with new features without breaking existing behavior

Provision or create an Azure AI Foundry IQ knowledge base from local files, especially VoiceAgent/samples/sample_foundry_iq_doc. Use when asked to upload documents to Foundry IQ, create a knowledge source or knowledge base, create its Foundry project MCP…

Create or provision a Microsoft Foundry Toolbox with an Azure AI Search tool over local files, especially VoiceAgent/samples/sample_foundry_iq_doc. Use when asked to create a Foundry Toolbox, index documents for a Toolbox, configure an azure_ai_search Toolbox…

Create, configure, test, and troubleshoot Azure AI Foundry voice agents in the customer private preview. Use when asked to create a basic voice agent, add an MCP or Foundry IQ knowledge tool, connect with the Voice Live SDK, diagnose preview access errors, or…

Guide for building Bicep files for Azure API Management (APIM) and related Azure services. Use when users want to create, modify, or understand Bicep templates for APIM instances, APIs, backends, subscriptions, policies, products, loggers, and diagnostics.…

Guide for creating Azure API Management (APIM) XML policies. Use when users want to create, modify, or understand APIM policies including inbound/outbound processing, authentication, rate limiting, caching, transformations, and policy expressions. This skill…

Guide for creating or scaffolding Azure API Management (APIM) usage samples with the repository's notebook/helper architecture. Use when users want a new sample under `samples/`, a sample-local helper, `samples/_TEMPLATE` scaffolding, or synchronized README,…

Review code for best practices, potential bugs, and improvements. Use when asked to review, analyze, or critique code quality.

Analyze datasets and generate statistical summaries and insights. Use when asked to analyze data, compute statistics, or identify trends.

Summarize meeting transcripts into structured notes with action items. Use when asked to process, summarize, or extract action items from meetings.