skills.rest
davidrrowley
davidrrowleyCOMMUNITY
Explore all skills by this author →
Website𝕏@davidrrowleyGitHub

deploy-model

Automates Azure OpenAI model deployment with configurable regions, quotas, and policies.

Updated Apr 12, 2026
Search Tags:#azure#openai#deploy#model-deployment#capacity-discovery#rai-policy#sku-selection
One-click install
npx skills add https://github.com/davidrrowley/CortexYouV3 --skill deploy-model-davidrrowley
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/davidrrowley/CortexYouV3/tree/main/.agents/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/davidrrowley/CortexYouV3 --skill deploy-model-davidrrowley

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires az, jq, python3, xxd, base64, openssl, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Deploying and provisioning Azure OpenAI models across regions and projects is complex and error-prone due to SKU/version compatibility, regional capacity limits, subscription quotas, and required policy configuration. This Skill unifies intent detection, capacity discovery, and deployment flows to prevent accidental deployments, surface viable regions and projects, and streamline both quick and fully customized deployments.

Core Features & Use Cases

  • Intent-based routing: Automatically routes user requests to Preset (fast deploy), Customize (full control), or Capacity Discovery (read-only) flows based on natural-language signals.
  • Capacity and quota validation: Queries region capacity and subscription quota, ranks candidate regions/projects, and annotates results so only viable options are presented.
  • Interactive customization: Guided selection of model version, SKU, capacity, RAI policy, advanced options (dynamic quota, spillover, PTU), and safe review/confirmation before execution.
  • Operational tooling: Includes scripts to discover and rank capacity, query per-region capacity, and generate portal URLs for deployments.
  • Use cases: Fast one-click deploys for staging, production-grade customized deployments with PTU sizing, and finding alternate regions when quota is exhausted.

Quick Start

Deploy gpt-4o to the best available region with default settings and confirm the target project when prompted.

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 across different regions?▼

You can deploy Azure OpenAI models across regions using intent-based routing that validates model-SKU compatibility, checks subscription quota, and routes execution to preset or customize workflows. It unifies deployment flows across regions and projects.

How do I find Azure OpenAI capacity when my subscription quota is exhausted?▼

Capacity discovery queries region capacity and subscription quota across accessible subscriptions, ranks candidate regions and projects, and annotates results so only viable options are presented for your Azure OpenAI deployment.

Can I customize Azure OpenAI model deployments with specific SKU and RAI policy configurations?▼

Yes, you can fully customize Azure OpenAI deployments with interactive selection of model version, SKU, capacity, RAI policy, and advanced options like dynamic quota, spillover, and PTU, followed by a safe review and confirmation.

What is the best way to quickly deploy an Azure OpenAI model for staging?▼

The best way to quickly deploy Azure OpenAI models for staging is using the preset deployment flow, which routes execution automatically based on natural-language signals to provide fast one-click deploys with default settings.

Do I need specific tools to validate Azure OpenAI model and SKU compatibility?▼

Yes, the operational tooling requires dependencies including az, jq, python3, xxd, base64, and openssl to validate model-SKU compatibility, query per-region capacity, and generate portal URLs for Azure OpenAI deployments.

Why does my Azure OpenAI deployment fail due to regional capacity limits?▼

Azure OpenAI deployments fail due to regional capacity limits when quota is exhausted, but this can be prevented by validating subscription quota and region capacity first, then ranking candidate regions to find viable alternatives.

Related Skills

Explore More Software Engineering Skills→
albertdobmeyeralbertdobmeyer
2

encoding-formats

Decode and convert encoded strings, tokens, and binary data.

Community
Intermediate
DigiBanks99DigiBanks99

capacity

Rank Azure OpenAI regions by capacity and quota for deployment planning.

Community
Intermediate
jaypatrickjaypatrick

deploy-model

Automate Azure OpenAI model deployment across regions with validation and routing.

Community
Advanced
crytligcrytlig

customize

Guide Azure OpenAI deployment configuration for model versions, SKUs, capacities, and policies.

Community
Advanced