skills.rest
merceralex397-collab
merceralex397-collabCOMMUNITY
Explore all skills by this author →
GitHub

azure-ai

Implements Azure AI Search, Speech, OpenAI, and Document Intelligence workflows via MCP tools and SDK references.

Updated Jul 20, 2026
Search Tags:#ocr#azure#vector search#openai#speech-to-text#ai search#document intelligence
One-click install
npx skills add https://github.com/merceralex397-collab/alex-stack --skill azure-ai-merceralex397-collab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: azure-ai
Source: https://github.com/merceralex397-collab/alex-stack/tree/main/dev/azure-profile/azure-skills-main/azure-skills-main/.github/plugins/azure-skills/skills/azure-ai
Command: npx skills add https://github.com/merceralex397-collab/alex-stack --skill azure-ai-merceralex397-collab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Working with Azure AI services requires knowing which tools, SDKs, and authentication patterns apply to each service. This Skill provides a single entry point for Azure AI Search, Speech, OpenAI, and Document Intelligence tasks, with MCP tool mappings and condensed SDK quick references in Python, TypeScript, .NET, and Java. ## Core Features & Use Cases - AI Search Operations: List indexes, get index details, and run full-text, vector, hybrid, and semantic queries through the azure__search MCP tools or az search CLI. - Speech Services: Perform speech-to-text transcription and text-to-speech synthesis via azure__speech MCP commands, with support for diarization and custom models. - SDK Quick References: Condensed guides for Azure Search Documents, OpenAI, Vision Image Analysis, Transcription, Translation, Document Intelligence, and Content Safety across multiple languages. - Use Case: You need to add hybrid vector search to an application. Use this Skill to query the search index via MCP, then follow the Python or TypeScript SDK reference to implement VectorizedQuery with semantic ranking in your code. ## Quick Start Ask the AI to list your Azure AI Search indexes and run a hybrid vector query against one of them using the azure-ai skill.

Frequently Asked Questions about azure-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a vector or hybrid search query on Azure AI Search?▼

Use the azure__search MCP tool with the search_query command, or the Azure.Search.Documents SDK with VectorizedQuery set in SearchOptions.VectorSearch.Queries. Combining vector and keyword search with semantic ranking gives the best relevance for natural language queries.

How do I transcribe audio to text with Azure Speech?▼

Use the azure__speech MCP tool with the speech_transcribe command for speech-to-text. For programmatic access, the azure-ai-transcription Python SDK supports batch transcription with diarization and real-time streaming via begin_stream_transcription.

What MCP tools are available for Azure AI services?▼

The azure__search server provides search_index_list, search_index_get, and search_query commands. The azure__speech server provides speech_transcribe and speech_synthesize. If Azure MCP is not enabled, run /azure:setup or enable it via /mcp.

Should I use DefaultAzureCredential in production for Azure AI SDKs?▼

No. DefaultAzureCredential is intended for local development only, where it picks up Azure CLI or VS Code credentials. In production, use ManagedIdentityCredential for deterministic, secret-free authentication, as detailed in the auth-best-practices reference.

Which SDK languages are covered for Azure AI services?▼

Quick references cover Python, TypeScript, .NET, and Java depending on the service. AI Search has Python, TypeScript, and .NET guides; Content Safety adds Java; Document Intelligence and OpenAI cover .NET and TypeScript.

Why does Azure Document Intelligence analysis require polling?▼

Document analysis is a long-running operation, so the SDK returns an operation that must be polled until completion. In TypeScript use getLongRunningPoller and pollUntilDone; in .NET pass WaitUntil.Completed to AnalyzeDocumentAsync.

Related Skills

Explore More Software Engineering Skills→
microsoftmicrosoft
242

azure-role-selector

Identify least-privilege Azure RBAC roles and generate CLI and Bicep assignment snippets.

Official
Intermediate
davidrrowleydavidrrowley

azure-ai-contentunderstanding-py

Extract multimodal semantic content from documents, images, audio, and video via Python SDK.

Community
Intermediate
MicrosoftDocsMicrosoftDocs
686

azure-ai-services

Provide expert guidance for developing with Azure AI services.

Official
Advanced
orqesaorqesa

build_vs_buy

Evaluate build versus buy options for software capabilities.

Official
Intermediate