deploy-model

Deploy Azure OpenAI models with preset or customized configurations.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The deploy-model skill streamlines the process of deploying Azure OpenAI models, providing intelligent routing, full customization, and capacity discovery across regions and projects.

Core Features & Use Cases

  • Intelligent Intent-Based Routing: Analyzes user intent and routes to the appropriate deployment mode (preset, customize, or capacity discovery).
  • Customization: Offers full control over deployment configurations, including version, SKU, capacity, and RAI policy.
  • Capacity Discovery: Identifies available capacity across regions and projects, enabling informed deployment decisions.
  • Use Case: A developer wants to deploy a GPT-4o model for a chatbot application. The skill will analyze the developer's intent, route to the appropriate deployment mode, and enable customization based on the developer's requirements.

Quick Start

Use the deploy-model skill to deploy a GPT-4o model with custom settings in the "westus2" region.

Frequently Asked Questions about deploy-model

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

FAQPage Schema
How do I deploy Azure OpenAI models with custom settings for SKU and capacity?

You can deploy Azure OpenAI models with custom settings by using an automated skill that routes your intent to a customization mode, allowing full control over version, SKU, capacity, and RAI policy configurations.

Do I need the Azure CLI to deploy OpenAI models?

Yes, you need the Azure CLI installed and an active Azure subscription with sufficient deployment permissions to automate the provisioning and routing of your OpenAI models.

What is capacity discovery for Azure OpenAI deployments?

Capacity discovery is the process of identifying available Azure OpenAI resources across different regions and projects, enabling developers to make informed decisions before executing model deployments.

Can I deploy a GPT-4o model quickly using presets?

Yes, you can deploy a GPT-4o model using quick preset deployments through intent-based routing, which analyzes your requirements and automatically applies standard configurations for rapid provisioning.

How does intelligent routing work for Azure OpenAI model provisioning?

Intelligent routing analyzes your deployment intent and automatically directs the process to the appropriate mode, whether you need quick presets, full customization, or regional capacity discovery across projects.

What are the limitations when customizing Azure OpenAI RAI policies during deployment?

Customization allows control over Responsible AI policies, but you are constrained by the available capacity across regions and the deployment permissions granted by your specific Azure subscription.