Skip to content
Azure AI Services

Azure AI Services Skill

Microsoft's official skill for building and troubleshooting Azure AI Search, Speech, Document Intelligence, Content Understanding, Translator, Content Safety and Azure OpenAI apps, with per-service preflight and diagnostics guides.

GitHub Docs

Install

Install with the skills CLI

One command for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf and dozens of other agents. Needs Node.js; the skill is fetched straight from microsoft/azure-skills.

$ npx skills add microsoft/azure-skills --skill azure-ai

Run it in a terminal. The CLI finds the agents installed on your machine, asks which ones to add the skill to, and whether to install it into the folder you ran it from or for all your projects.

Other ways to install

Copy the whole skill folder — SKILL.md and any scripts or references beside it — into ~/.claude/skills/azure-ai/, where Claude Code picks it up in every project. Only git is needed.

tmp=$(mktemp -d) && \
  git clone --depth 1 --branch main https://github.com/microsoft/azure-skills.git "$tmp" && \
  mkdir -p ~/.claude/skills && \
  cp -R "$tmp"/skills/azure-ai ~/.claude/skills/azure-ai

No scripts or references next to it? Saving the SKILL.md alone as ~/.claude/skills/azure-ai/SKILL.md works too.

Using another agent? Its personal skills folder
Codex
~/.agents/skills/
Cursor
~/.cursor/skills/
GitHub Copilot
~/.copilot/skills/
Gemini CLI
~/.gemini/skills/
Windsurf
~/.codeium/windsurf/skills/
OpenCode
~/.config/opencode/skills/

About

  • Routes Foundry and AI gateway requests to the dedicated Azure skills
  • AI Search: vector, hybrid and semantic queries, indexers and skillsets
  • Speech, Document Intelligence v4.0, Content Understanding, Translator and Content Safety
  • Per-service preflight and diagnostics references before troubleshooting
  • Azure MCP tools first, az CLI fallback, SDK guides for Python, TypeScript, .NET and Java

Azure AI is the skill in Microsoft's microsoft/azure-skills repository that covers the classic Azure AI services, as opposed to Microsoft Foundry projects and agents. It opens with a routing table: Foundry projects, agents, model deployments and fine-tuning go to the microsoft-foundry skill, API Management AI gateway policies go to azure-aigateway, and everything else in its scope stays here.

That scope is AI Search (classic indexes, vector, hybrid and semantic queries, indexers and skillsets), Speech (speech-to-text, text-to-speech, fast and batch transcription, SDK logs), Document Intelligence v4.0 (layout, OCR, custom extraction models and classifiers), Content Understanding analyzers, Translator with document translation and glossaries, standalone Content Safety, and direct Azure OpenAI SDK use. For each service the skill names the Azure MCP tools or az commands to use and points to a reference with preflight checks and diagnostic steps, so the agent reads the right guide before validating inputs or chasing an error. It also covers roles, private endpoints and data handling for Document Intelligence and Content Understanding, and keyless authentication across the SDKs.

SDK quick references are included for Python, TypeScript, .NET and Java depending on the service. The skill prefers the Azure MCP server and tells the user how to enable it in Claude Code or Copilot CLI when it is missing. MIT licensed; version 1.2.6 at the time of listing.

SKILL.md

The instructions your agent loads, as published by Microsoft.

SKILL.md
name
azure-ai
description
Build and troubleshoot Azure AI Search, Speech, Document Intelligence, Content Understanding, Translator, Content Safety, and OpenAI apps. WHEN: AI Search, vector search, hybrid search, semantic search, indexer, speech-to-text, text-to-speech, fast or batch transcription, Speech SDK logs, session ID, result ID, OCR, document translation, glossary.
license
MIT
metadata
author: Microsoft version: "1.2.6"

Azure AI Services

Scope and Handoffs
Request ScopeRoute To
Foundry projects, agents (Prompt/Hosted/Voice), model deployments, fine-tuning, quota, project RBAC, Foundry VNetmicrosoft-foundry
Foundry IQ knowledge bases and connectorsfoundry-iq (separate foundry-iq-skills plugin; if absent, say so)
Azure API Management AI Gateway policies (llm-content-safety, semantic cache, token limits)azure-aigateway
Classic AI Search, Speech SDK/REST/batch, Document Intelligence, Content Understanding, Translator, standalone Content Safety, OpenAI SDKStay in azure-ai
Roles, private endpoints, Studio storage or data handling for Document Intelligence or Content Understanding calls (including CU in the Foundry portal)Stay in azure-ai
Services and Diagnostic Workflows

Read the matching reference before diagnosing errors, validating local inputs, or collecting support evidence:

ServiceMCP / CLIPreflight & Diagnostics
AI Search (classic indexes, vector/hybrid/semantic queries, indexers/skillsets)azure__search (search_service_list, search_index_get, search_index_query), az search[Index, query, and indexer diagnostics](references/search/index-and-query-diagnostics.md)
Speech (STT, TTS, Fast/Batch Transcription, Batch Synthesis, SDK logs)azure__speech (speech_stt_recognize, speech_tts_synthesize), az cognitiveservices[Speech SDK client diagnostics](references/speech/diagnostics.md) | [Audio & REST/batch preflight](references/speech/transcription-and-audio-preflight.md)
Document Intelligence (v4.0 Analyze, layout/OCR, custom extraction, classifiers, composed models)az cognitiveservices[Input, v4 migration, and Analyze diagnostics](references/document-intelligence/preflight-and-diagnostics.md) | [Custom models, labels, and confidence](references/document-intelligence/custom-models.md)
Content Understanding (analyzers, CU Studio, model defaults, custom analyzers)az cognitiveservices[Setup, API versions, and defaults](references/content-understanding/overview-and-setup.md) | [Custom analyzers](references/content-understanding/custom-analyzers.md) | [Diagnostics](references/content-understanding/diagnostics.md)
Access, network, and data for Document Intelligence and Content Understandingazure__role (role_assignment_list), az role, az network[Roles and auth](references/foundry-tools/access-and-roles.md) | [Studio storage](references/foundry-tools/storage-and-studio.md) | [Private networking](references/foundry-tools/private-network.md) | [Data handling](references/foundry-tools/data-handling.md) | [Evidence without content](references/foundry-tools/evidence-without-content.md)
Translator (Text & Document Translation, glossaries, Blob auth)az cognitiveservices[Document Translation & glossary preflight](references/translator/document-translation-preflight.md)
Content Safety (standalone text:analyze, image:analyze, text:shieldPrompt, blocklists)az cognitiveservices[Standalone API preflight & diagnostics](references/content-safety/api-preflight-and-diagnostics.md)
OpenAI (direct SDK/API usage)az cognitiveservices[.NET SDK](references/sdk/azure-ai-openai-dotnet.md)

If Azure MCP is not enabled: In Copilot CLI or Claude Code, ask the user to run /mcp and enable Azure MCP; in other hosts, ask the user to enable Azure MCP through the host's MCP configuration. Offline local preflight scripts do not require Azure MCP or Azure sign-in.

For keyless authentication patterns across Azure AI SDKs, read [Azure Authentication Best Practices](references/auth-best-practices.md).

SDK Quick References
  • AI Search: [Python](references/sdk/azure-search-documents-py.md) | [TypeScript](references/sdk/azure-search-documents-ts.md) | [.NET](references/sdk/azure-search-documents-dotnet.md)
  • OpenAI: [.NET](references/sdk/azure-ai-openai-dotnet.md)
  • Vision: [Python](references/sdk/azure-ai-vision-imageanalysis-py.md) | [Java](references/sdk/azure-ai-vision-imageanalysis-java.md)
  • Transcription: [Python](references/sdk/azure-ai-transcription-py.md)
  • Translation: [Python](references/sdk/azure-ai-translation-text-py.md) | [TypeScript](references/sdk/azure-ai-translation-ts.md)
  • Document Intelligence: [.NET](references/sdk/azure-ai-document-intelligence-dotnet.md) | [TypeScript](references/sdk/azure-ai-document-intelligence-ts.md)
  • Content Safety: [Python](references/sdk/azure-ai-contentsafety-py.md) | [TypeScript](references/sdk/azure-ai-contentsafety-ts.md) | [Java](references/sdk/azure-ai-contentsafety-java.md)
Service Documentation
Install
New

Microsoft's official Azure skill for pre-deployment checks: validates azure.yaml, Bicep or Terraform, RBAC role assignments and managed identity permissions before an agent deploys.

New

Microsoft's official skill for Azure Blob Storage, File Shares, Queue and Table Storage and Data Lake: when to use each, access tiers, redundancy options, Azure MCP and az CLI commands, and SDK guides.

New

Microsoft's official skill for preparing apps for Azure with the Azure Developer CLI: writes a deployment plan first, then generates azure.yaml, Bicep or Terraform infrastructure and Dockerfiles before handing off to validation.

Browse all skills →