microsoft-foundry:microsoft-foundry

Manage Azure AI Foundry agents, models, quotas, and RBAC via Azure CLI.

10|2|Updated Mar 8, 2026

Search Tags:#troubleshooting #azure #agent #model deployment #capacity management #ai foundry

Ready to run

npx skills add https://github.com/mahmoud20138/Claude-Skills-Collection --skill microsoft-foundry-microsoft-foundry

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: microsoft-foundry:microsoft-foundry
Source: https://github.com/mahmoud20138/Claude-Skills-Collection/tree/main/02-Azure-Skills/skills/microsoft-foundry
Command: npx skills add https://github.com/mahmoud20138/Claude-Skills-Collection --skill microsoft-foundry-microsoft-foundry

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the management of Azure AI Foundry agents and models, simplifying complex deployment, invocation, and troubleshooting tasks.

Core Features & Use Cases

Agent Lifecycle Management: Create, deploy, invoke, and troubleshoot both prompt-based and hosted agents.
Model Deployment: Deploy AI models with full control over versions, SKUs, capacity, and Responsible AI policies.
Capacity & Quota Management: Discover available capacity, optimize quota usage, and manage deployment limits.
Use Case: Deploy a new hosted agent for customer support, configure its environment variables, test its responses, and monitor its performance in production.

Quick Start

Use the microsoft-foundry skill to deploy the 'support-agent' hosted agent.

Frequently Asked Questions about microsoft-foundry:microsoft-foundry

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

FAQPage Schema

How do I deploy and troubleshoot Azure AI Foundry agents?▼

Azure AI Foundry agent deployment and troubleshooting are managed through a comprehensive suite of tools that handle the complete agent lifecycle, including creation, deployment, invocation, and issue resolution for both prompt-based and hosted agents.

What is the best way to manage Azure AI Foundry model capacity and quotas?▼

Managing Azure AI Foundry model capacity and quotas involves discovering available capacity, optimizing quota usage, and handling deployment limits to ensure efficient resource allocation for your hosted AI models.

Can I deploy custom AI models with specific versions and SKUs in Azure AI Foundry?▼

Yes, you can deploy custom AI models in Azure AI Foundry with full control over versions, SKUs, capacity discovery, and Responsible AI policies using deterministic operations orchestrated via Azure CLI and MCP tools.

Do I need Azure CLI to configure RBAC for AI Foundry resources?▼

Yes, Azure CLI is required to configure RBAC for AI Foundry resources, as the Skill orchestrates complex workflows for capacity management, model deployment, and access control using Azure CLI and MCP tools.

Why does my Azure AI Foundry hosted agent invocation fail?▼

Azure AI Foundry hosted agent invocation failures can be diagnosed using the Skill's built-in troubleshooting and observability features, which help identify issues across the agent lifecycle, environment variables, and deployment configurations.

Does this approach work for configuring environment variables and monitoring production AI agents?▼

Yes, this approach works for configuring environment variables and monitoring production AI agents by providing observability features that allow you to test agent responses and monitor their performance in a production environment.