skills.rest
mordechai30
mordechai30COMMUNITY
Explore all skills by this author →
GitHub

deploy-model

Automate Azure OpenAI model deployments with capacity discovery and region selection.

Updated Aug 27, 2026
Search Tags:#automation#deployment#azure#cloud#openai#capacity
One-click install
npx skills add https://github.com/mordechai30/.agents --skill deploy-model-mordechai30
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/mordechai30/.agents/tree/main/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/mordechai30/.agents --skill deploy-model-mordechai30

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill removes the complexity and guesswork from deploying Azure OpenAI models by automating capacity discovery, region selection, and configuration, preventing common deployment failures.

Core Features & Use Cases

  • Intelligent Routing: Automatically detects whether you need a quick preset deployment, a fully customized configuration, or capacity discovery.
  • Capacity Discovery: Scans all available regions to find where your required model and capacity are actually available before you attempt to deploy.
  • Guided Customization: Provides a step-by-step flow for complex requirements like PTU (Provisioned Throughput Units), specific RAI policies, and spillover configurations.

Quick Start

Use the deploy-model skill to find the best region for a gpt-4o deployment with 10K capacity and then proceed with the setup.

Frequently Asked Questions about deploy-model

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

FAQPage Schema
How do I check Azure OpenAI model capacity before deploying to a specific region?▼

Azure OpenAI deployment requires checking capacity first to prevent failures. This skill scans all available regions to find where your required model and capacity are actually available before attempting any deployment operations.

How do I automate Azure OpenAI model deployment across multiple regions?▼

Automating Azure OpenAI deployment across multiple regions is handled by this skill via Azure CLI and ARM REST APIs. It validates subscription quotas, model availability, and project resource constraints before executing the end-to-end resource configuration.

Does this Azure OpenAI deployment skill support PTU based provisioned throughput setups?▼

PTU based provisioned throughput setups are fully supported for complex production requirements. The skill provides a guided step-by-step customization flow for configuring PTU capacity, specific RAI policies, and spillover configurations across multiple Azure regions.

What is the best way to deploy a gpt-4o model with a 10K capacity quota in Azure?▼

The best way to deploy a gpt-4o model with 10K capacity is using the quick preset deployment mode. The skill intelligently routes your request to discover the best region with available quota and then proceeds with the automated setup.

Do I need the Azure CLI installed to automate OpenAI model deployment?▼

Yes, the Azure CLI is required to automate OpenAI model deployment operations. The skill depends on the az command line tool, along with jq and openssl, to validate quotas and execute resource configuration via ARM REST APIs.

Related Skills

Explore More Software Engineering Skills→
jorgeasaurusjorgeasaurus
12

capacity

Discover Azure OpenAI model capacity across regions and rank deployment options.

Community
Advanced
andersnygaardandersnygaard
5

azure-setup-guide

Generate an Azure deployment guide for EasyAuth and CosmosDB.

Community
Basic
p-potvinp-potvin
1

capacity

Discover Azure OpenAI model capacity across regions and projects with quota validation.

Community
Advanced
microsoftmicrosoft
242

microsoft-foundry

Discover, deploy, and manage Microsoft Foundry AI resources with Python SDK and MCP tools.

Official
Advanced