customize

Configure Azure OpenAI deployments through an interactive workflow with validation.

Updated May 25, 2026
One-click install
npx skills add https://github.com/AcendWay/ai-skills-library --skill customize-acendway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: customize
Source: https://github.com/AcendWay/ai-skills-library/tree/main/skill-folders/microsoft-foundry/models/deploy-model/customize
Command: npx skills add https://github.com/AcendWay/ai-skills-library --skill customize-acendway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the guesswork of configuring Azure OpenAI deployments by guiding you through exact model version, SKU, capacity, and content filtering choices.

Core Features & Use Cases

  • Interactive end-to-end deployment configuration that walks you through selecting model name and version, choosing a deployable SKU, and setting capacity within allowed min/max/step limits.
  • Production-ready options including RAI (content filtering) policy selection for OpenAI models, version upgrade policy, and advanced deployment behaviors like dynamic quota, priority processing, and spillover.
  • Robust validation and fallback logic that checks authentication, verifies the project resource, filters SKUs by available quota, and falls back across regions when capacity is missing.

Quick Start

Tell the Skill: "Customize an Azure OpenAI deployment for gpt-4o by selecting the latest available version, GlobalStandard SKU, a capacity I specify, and the Microsoft.DefaultV2 RAI policy, then create and monitor the deployment."

Frequently Asked Questions about customize

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

FAQPage Schema
How do I configure an Azure OpenAI deployment with specific capacity and SKU settings?

Yes, you can apply a Microsoft.DefaultV2 RAI content-filter policy to your Azure OpenAI deployment. The interactive workflow allows you to select the appropriate RAI policy for OpenAI models to ensure production-ready content filtering compliance.

What happens if the requested SKU quota is unavailable during Azure OpenAI model configuration?

If the requested SKU quota is unavailable, the deployment workflow filters SKUs by available quota and falls back across regions when capacity is missing. This ensures successful deployment creation even when primary region resources are exhausted.

Can I deploy Anthropic MaaS models using the Azure OpenAI deployment configuration workflow?

Yes, the Azure OpenAI deployment workflow supports both OpenAI TPM-based and Anthropic MaaS model formats. It handles deterministic CLI and REST requirements for model format, ensuring correct deployment creation and upgrade policies for each format type.

How do I set up dynamic quota and priority processing for an Azure OpenAI model deployment?

You can set up dynamic quota, priority processing, and spillover by selecting advanced deployment behaviors in the interactive workflow. This configures the Azure OpenAI model deployment with production-ready options beyond standard SKU and capacity settings.

Does the Azure OpenAI deployment workflow validate authentication and project resources before creating a model?

Yes, the workflow includes robust validation logic that checks authentication and verifies the project resource before deployment creation. This prevents errors by ensuring correct ARM resource targeting and SKU availability prior to execution.