PluginBench
Skill
Official
Pass
Audit score 90

azure-ai

microsoft/azure-skills

Azure AI services skill for Search, Speech, OpenAI, and Document Intelligence in coding agents

What is azure-ai?

This skill equips coding agents with knowledge and tooling to work with Azure AI services including AI Search (full-text, vector, hybrid, semantic), Speech (speech-to-text, text-to-speech), OpenAI (GPT, embeddings, DALL-E), and Document Intelligence (OCR, form extraction). It surfaces MCP tool commands for Search and Speech when Azure MCP is enabled, and provides SDK quick-reference guides for Python, TypeScript, .NET, Java, and more.

  • Enables AI Search queries including full-text, vector, hybrid, and semantic search via MCP tools or SDK
  • Supports speech-to-text transcription and text-to-speech synthesis via MCP tools or SDK
  • Provides SDK reference guides for AI Search, OpenAI, Speech, Document Intelligence, Vision, Translation, and Content Safety
  • Maps each Azure AI service to its relevant MCP tool commands and Azure CLI equivalents
  • Guides setup of Azure MCP server when not already enabled
  • Covers AI enrichment features like entity extraction, OCR, and sentiment analysis

How to install azure-ai

npx skills add https://github.com/microsoft/azure-skills --skill azure-ai
Prerequisites
  • An Azure subscription with relevant AI services provisioned
  • Azure MCP server enabled (for MCP tool commands) or Azure CLI installed
  • Appropriate Azure credentials/API keys for the target services
  • npx available to install the skill via the skills CLI
Claude Code
Cursor
Windsurf
Cline

How to use azure-ai

  1. 1.Install the skill: npx skills add https://github.com/microsoft/azure-skills --skill azure-ai
  2. 2.Verify Azure MCP is enabled; if not, run /azure:setup or enable via /mcp
  3. 3.For AI Search, use the azure__search MCP tool with commands: search_index_list, search_index_get, or search_query
  4. 4.For Speech, use the azure__speech MCP tool with commands: speech_transcribe or speech_synthesize
  5. 5.For OpenAI or Document Intelligence, use the Azure CLI (az cognitiveservices) or reference the provided SDK guides
  6. 6.Select the SDK reference for your language (Python, TypeScript, .NET, Java) from the skill's references directory
  7. 7.Consult linked Microsoft Learn documentation for deep-dive indexing, query, or transcription patterns

Use cases

Good for
  • Querying an Azure AI Search index with keyword, vector, or hybrid search
  • Transcribing audio files or synthesizing speech from text
  • Extracting structured data from forms and documents using Document Intelligence
  • Building embeddings or calling GPT models via Azure OpenAI
  • Integrating content safety checks or image analysis into an application
Who it's for
  • Developers building search features on top of Azure AI Search
  • Engineers implementing speech interfaces (voice input/output) in applications
  • Developers working with Azure OpenAI for GPT or embedding workflows
  • Teams doing document processing, OCR, or form extraction on Azure
  • Coding agent users who want guided Azure AI SDK usage across Python, TypeScript, .NET, and Java

azure-ai FAQ

Do I need Azure MCP enabled to use this skill?

MCP tools (azure__search, azure__speech) require Azure MCP to be enabled. If it is not, the skill instructs you to run /azure:setup or enable it via /mcp. SDK-based access works independently of MCP.

Which Azure AI services are covered?

AI Search, Speech (speech-to-text and text-to-speech), Azure OpenAI (GPT, embeddings, DALL-E), Document Intelligence (OCR, form extraction), Vision, Translation, and Content Safety.

Which programming languages have SDK references?

Python, TypeScript, .NET (C#), and Java are covered, though not every service has a reference for every language.

Can I do vector or hybrid search with this skill?

Yes. The skill covers full-text, vector, hybrid, and semantic search capabilities in Azure AI Search, accessible via the azure__search MCP tool or the AI Search SDK.

Does this skill provision Azure resources for me?

No. The skill assumes Azure AI services are already provisioned. It provides tooling and guidance for interacting with existing resources.

Full instructions (SKILL.md)

Source of truth, from microsoft/azure-skills.


name: azure-ai description: "Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech." license: MIT metadata: author: Microsoft version: "1.1.1"

Azure AI Services

Services

ServiceUse WhenMCP ToolsCLI
AI SearchFull-text, vector, hybrid searchazure__searchaz search
SpeechSpeech-to-text, text-to-speechazure__speech-
OpenAIGPT models, embeddings, DALL-E-az cognitiveservices
Document IntelligenceForm extraction, OCR--

MCP Server (Preferred)

When Azure MCP is enabled:

AI Search

  • azure__search with command search_index_list - List search indexes
  • azure__search with command search_index_get - Get index details
  • azure__search with command search_query - Query search index

Speech

  • azure__speech with command speech_transcribe - Speech to text
  • azure__speech with command speech_synthesize - Text to speech

If Azure MCP is not enabled: Run /azure:setup or enable via /mcp.

AI Search Capabilities

FeatureDescription
Full-text searchLinguistic analysis, stemming
Vector searchSemantic similarity with embeddings
Hybrid searchCombined keyword + vector
AI enrichmentEntity extraction, OCR, sentiment

Speech Capabilities

FeatureDescription
Speech-to-textReal-time and batch transcription
Text-to-speechNeural voices, SSML support
Speaker diarizationIdentify who spoke when
Custom modelsDomain-specific vocabulary

SDK Quick References

For programmatic access to these services, see the condensed SDK guides:

Service Details

For deep documentation on specific services: