preset

Automate Azure OpenAI model deployment to optimal regions via ARM REST API.

Updated Feb 10, 2026
One-click install
npx skills add https://github.com/ammonfife/sakima.co --skill preset-ammonfife
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: preset
Source: https://github.com/ammonfife/sakima.co/tree/main/.claude/skills/microsoft-foundry/models/deploy-model/preset
Command: npx skills add https://github.com/ammonfife/sakima.co --skill preset-ammonfife

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the deployment of Azure OpenAI models, intelligently selecting the optimal region based on capacity, and simplifying the deployment process.

Core Features & Use Cases

  • Intelligent Deployment: Analyzes capacity across all regions and deploys to the best available option.
  • Optimal Region Selection: Automatically checks current region first and shows alternatives if needed.
  • Use Case: Deploy a model quickly and efficiently without worrying about region capacity or configuration.

Quick Start

Use the preset skill to deploy the latest OpenAI model to the optimal region for your project.

Frequently Asked Questions about preset

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

FAQPage Schema
How do I automate Azure OpenAI model deployment to avoid region capacity issues?

Azure OpenAI model deployment can be automated by analyzing region capacity and deploying to the best available option, checking your current region first and showing alternatives if needed.

Can I deploy Anthropic models on Azure using the ARM REST API?

Yes, Anthropic models are supported for deployment on Azure using the ARM REST API, allowing you to provision multiple models and formats alongside OpenAI deployments.

What permissions are required to deploy Azure OpenAI models across regions?

Deploying Azure OpenAI models across regions requires Azure CLI installed and Cognitive Services permissions to execute capacity analysis and provision resources in optimal regions.

What is the best way to analyze Azure OpenAI capacity before deploying a model?

The best way to analyze Azure OpenAI capacity is to automate checks across all regions, evaluating availability to automatically select and deploy to the optimal region for your model.

Why does my Azure OpenAI model deployment fail due to region capacity?

Azure OpenAI model deployment fails when the target region lacks capacity; automating capacity analysis across all regions prevents this by deploying to the best available alternative.