azure-ai — Claude Code skill for Azure AI Search, Speech and OCR
Wires Azure services into your agent: index queries, speech recognition and synthesis, OCR. Useful when the project already runs on Azure.
npx skills add microsoft/skills --skill azure-ai -a claude-codeWhat azure-ai does
The skill covers four Azure services and the tools that reach them. AI Search handles full-text, vector and hybrid search, plus enrichment like entity extraction, OCR and sentiment. Speech does real-time and batch transcription, neural text-to-speech with SSML, speaker diarization and custom domain vocabulary. OpenAI brings GPT models, embeddings and DALL-E, while Document Intelligence takes on form extraction and OCR.
The preferred route is Azure MCP. With it enabled the agent gets azure__search with search_index_list, search_index_get and search_query, and azure__speech with speech_transcribe and speech_synthesize. If Azure MCP is off, ask the user to run /mcp in Copilot CLI or Claude and enable it; other hosts need it turned on through their own MCP configuration. Skip that step and the skill is just a reference page.
Inside are condensed SDK guides for Python, TypeScript, .NET and Java: search, OpenAI, Vision, transcription, translation, Document Intelligence, Content Safety. The CLI side lists az search and az cognitiveservices. The skill does not provision anything in Azure, so resources and credentials have to exist first — otherwise tool calls land on an empty index list.
What it helps with
- list indexes and run a query against one
- combine keyword and vector results in hybrid search
- transcribe audio in batch or live
- synthesize speech with neural voices and SSML
- pull fields out of scanned forms via OCR
Example prompts for the agent
- list the search indexes in Azure AI Search
- query the index for documents about refunds
- transcribe this meeting recording to text
How to install azure-ai
1Skills CLI (Vercel)
npx skills add microsoft/skills --skill azure-ai -a claude-code2Manually: put the files in place
~/.claude/skills/azure-ai/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/azure-ai/
Manually: put the files in place
.agents/skills/azure-ai/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/azure-ai/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/skills azure-ai2Manually: put the files in place
.github/skills/azure-ai/SKILL.mdPlatform CLI
gemini skills install https://github.com/microsoft/skills --path .github/plugins/azure-skills/skills/azure-aiManually: put the files in place
.devin/skills/azure-ai/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about azure-ai
How do I install azure-ai in Claude?
Run npx skills add microsoft/skills --skill azure-ai -a claude-code. The skill file lands at ~/.claude/skills/azure-ai/SKILL.md.
What does azure-ai do?
It gives the agent access to Azure AI Search, Speech, OpenAI and Document Intelligence: index queries, speech-to-text and text-to-speech, OCR, form extraction. It also ships condensed SDK guides for Python, TypeScript, .NET and Java.
Does azure-ai need Azure MCP?
Yes, that is the preferred path: the azure__search and azure__speech tools only appear when Azure MCP is enabled. In Claude and Copilot CLI you turn it on with /mcp.
Source text
SKILL.md · MIT
--- 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: "1.2.2" --- # Azure AI Services ## Services | Service | Use When | MCP Tools | CLI | |---------|----------|-----------|-----| | AI Search | Full-text, vector, hybrid search | `azure__search` | `az search` | | Speech | Speech-to-text, text-to-speech | `azure__speech` | - | | OpenAI | GPT models, embeddings, DALL-E | - | `az cognitiveservices` | | Document Intelligence | Form 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:** 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. ## AI Search Capabilities | Feature | Description | |---------|-------------| | Full-text search | Linguistic analysis, stemming | | Vector search | Semantic similarity with embeddings | | Hybrid search | Combined keyword + vector | | AI enrichment | Entity extraction, OCR, sentiment | ## Speech Capabilities | Feature | Description | |---------|-------------| | Speech-to-text | Real-time and batch transcription | | Text-to-speech | Neural voices, SSML support | | Speaker diarization | Identify who spoke when | | Custom models | Domain-specific vocabulary | ## SDK Quick References For programmatic access to these services, see the condensed SDK guides: - **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 Details For deep documentation on specific services: - AI Search indexing and queries -> [Azure AI Search documentation](https://learn.microsoft.com/azure/search/search-what-is-azure-search) - Speech transcription patterns -> [Azure AI Speech documentation](https://learn.microsoft.com/azure/ai-services/speech-service/overview)
© Microsoft · MIT · microsoft/skills