skills.rest
azaslonov
azaslonovCOMMUNITY
Explore all skills by this author →
Website𝕏@azaslonovGitHub

plugins/azure/skills/microsoft-foundry

Manage Azure AI Foundry environments from resource setup to agent deployment and troubleshooting.

1|Updated Mar 4, 2026
Search Tags:#azure#evaluation#resource management#quota#agent deployment#foundry#model orchestration
One-click install
npx skills add https://github.com/azaslonov/apic-tools-demos --skill plugins-azure-skills-microsoft-foundry
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: plugins/azure/skills/microsoft-foundry
Source: https://github.com/azaslonov/apic-tools-demos/tree/main/plugins/azure/skills/microsoft-foundry
Command: npx skills add https://github.com/azaslonov/apic-tools-demos --skill plugins-azure-skills-microsoft-foundry

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires azd, az cli, bicep, azurerm, foundry-sdk, and includes references (resource) and scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a comprehensive framework for deploying, managing, and troubleshooting Azure AI Foundry resources and agents, simplifying the onboarding and operational processes for AI projects.

Core Features & Use Cases

  • Resource Provisioning: Create and configure Azure AI Foundry projects, resources, and networks via Bicep templates and CLI.
  • Agent Management: Deploy, update, and troubleshoot both prompt and hosted agents using MCP tools and SDKs.
  • Model Deployment: Deploy models with capacity planning, optimal region selection, and SKU configuration, including PTU and Dynamic Quota.
  • Evaluation & Monitoring: Auto-create evaluators, run batch evaluations, analyze failures, and set up continuous evaluation workflows.
  • Quota & Capacity: Monitor quotas, request increases, and optimize deployment locations to ensure resource availability.
  • Networking & Private VNet: Configure private network segmentation for secure deployments.
  • Troubleshooting & Telemetry: Use Application Insights and trace analysis for diagnostic insights into agent failures and latency issues.

Quick Start

To set up a new Foundry project, first create the resource with resource/create, then deploy an agent with agent/deploy, and finally run evaluation via observe. Manage quotas with quota. Troubleshoot issues using troubleshoot.

Frequently Asked Questions about plugins/azure/skills/microsoft-foundry

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

FAQPage Schema
How do I deploy AI agents and models in Azure AI Foundry?▼

Azure AI Foundry agent deployment uses the Foundry SDK and MCP tools to configure and launch prompt or hosted agents. You manage the deployment lifecycle including updates and troubleshooting within your provisioned environment.

Can I use Bicep and Azure CLI to automate Foundry resource provisioning?▼

Yes, Bicep templates and Azure CLI automate Azure AI Foundry resource provisioning. You create and configure projects, resources, and networks, including private VNet segmentation, establishing secure infrastructure for your AI workloads.

How do I monitor Azure AI Foundry quotas and request capacity increases?▼

You monitor Azure AI Foundry quotas and request capacity increases through dedicated quota management commands. This involves tracking PTU and Dynamic Quota utilization and optimizing deployment locations to ensure resource availability for model orchestration.

Does Azure AI Foundry support batch evaluation and continuous monitoring?▼

Azure AI Foundry supports batch evaluation and continuous monitoring by auto-creating evaluators and setting up evaluation workflows. You analyze failures and operational metrics to maintain agent performance and reliability.

Why is my Azure AI Foundry agent deployment failing or experiencing latency?▼

Azure AI Foundry agent deployment failures and latency issues are diagnosed using Application Insights and trace analysis. This troubleshooting mechanism provides diagnostic insights into agent errors, helping you identify and resolve operational bottlenecks.

Do I need azd and foundry-sdk to manage Foundry environments end-to-end?▼

Yes, azd and foundry-sdk are required dependencies to manage Foundry environments end-to-end. They provide the necessary CLI commands and programmatic interfaces for resource setup, agent deployment, model orchestration, and operational troubleshooting.

Related Skills

Explore More Software Engineering Skills→
andres-vvandres-vv
3

azure-infra-deploy

Deploy Azure infrastructure with azd and Bicep files.

Community
Intermediate
crytligcrytlig

appinsights-instrumentation

Integrate Azure Application Insights into web applications with setup and configuration guidance.

Community
Intermediate
markus41markus41
12

Azure Storage

Provision Azure Storage resources with Bicep templates and RBAC access controls.

Community
Advanced
nesihaver-ILnesihaver-IL

azure-ai-foundry

Build and orchestrate AI agents on Azure AI Foundry with Python SDKs.

Community
Advanced