$ loading_
Guide custom Azure OpenAI deployments with detailed model and capacity settings.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "customize" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/plugin/skills/microsoft-foundry/models/deploy-model/customize/SKILL.md 2. Save it as ~/.claude/skills/customize/SKILL.md 3. Reload skills and tell me it's ready
Guide me through deploying an Azure OpenAI model for production. I want to choose the model version, SKU, capacity, content filter policy, and review advanced options like dynamic quota, priority processing, and spillover.
A step-by-step deployment flow that helps the user confirm model version, SKU, capacity, RAI policy, and advanced settings.
I need to create a Provisioned Managed deployment. Walk me through selecting the right model version, PTU capacity, and related advanced settings, and explain the impact of each option.
An interactive deployment flow tailored to PTU scenarios, including how capacity and advanced options affect throughput and cost.
Help me customize an Azure OpenAI deployment with a focus on choosing the right content filter policy, SKU, and capacity settings to meet safety requirements while maintaining performance.
A customized deployment guide centered on safety policy, SKU, and capacity so the user can balance compliance and performance.
Interactive guided workflow for deploying Azure OpenAI models with full customization control over version, SKU, capacity, content filtering, and advanced options.
| Property | Description |
|---|---|
| Flow | Interactive step-by-step guided deployment |
| Customization | Version, SKU, Capacity, RAI Policy, Advanced Options |
| SKU Support | GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard |
| Best For | Precise control over deployment configuration |
| Authentication | Azure CLI (az login) |
| Tools | Azure CLI, MCP tools (optional) |
Use this skill when you need precise control over deployment configuration:
Alternative: Use preset for quick deployment to the best available region with automatic configuration.
| Feature | customize | preset |
|---|---|---|
| Focus | Full customization control | Optimal region selection |
| Version Selection | User chooses from available | Uses latest automatically |
| SKU Selection | User chooses (GlobalStandard/Standard/PTU) | GlobalStandard only |
| Capacity | User specifies exact value | Auto-calculated (50% of available) |
| RAI Policy | User selects from options | Default policy only |
| Region | Current region first, falls back to all regions if no capacity | Checks capacity across all regions upfront |
| Use Case | Precise deployment requirements | Quick deployment to best region |
/subscriptions/{sub}/resourceGroups/{rg}/providers/Microsoft.CognitiveServices/accounts/{account}/projects/{project})az login)PROJECT_RESOURCE_ID environment variable1. Verify Authentication
2. Get Project Resource ID
3. Verify Project Exists
4. Get Model Name (if not provided)
5. List Model Versions → User Selects
6. List SKUs for Version → User Selects
7. Get Capacity Range → User Configures
7b. If no capacity: Cross-Region Fallback → Query all regions → User selects region/project
8. List RAI Policies → User Selects
9. Configure Advanced Options (if applicable)
10. Configure Version Upgrade Policy
11. Generate Deployment Name
12. Review Configuration
13. Execute Deployment & Monitor
If user accepts all defaults (latest version, GlobalStandard SKU, recommended capacity, default RAI policy, standard upgrade policy), deployment completes in ~5 interactions.
⚠️ MUST READ: Before executing any phase, load references/customize-workflow.md for the full scripts and implementation details. The summaries below describe what each phase does — the reference file contains the how (CLI commands, quota patterns, capacity formulas, cross-region fallback logic).
| Phase | Action | Key Details |
|---|---|---|
| 1. Verify Auth | Check az account show; prompt az login if needed | Verify correct subscription is active |
| 2. Get Project ID | Read PROJECT_RESOURCE_ID env var or prompt user | ARM resource ID format required |
| 3. Verify Project | Parse resource ID, call az cognitiveservices account show | Extracts subscription, RG, account, project, region |
…
Analyze and compress Markdown to reduce tokens and improve AI efficiency.
Write, review, and standardize Agent Skills to match agentskills.io requirements.
Discover Azure OpenAI capacity, quotas, and best regions for deployment.
Create, validate, and run eval.yaml suites for agent skill evaluation.
Query and analyze logs, telemetry, and time-series data in Azure Data Explorer.
Assess AKS Automatic readiness and generate fixes for migration blockers.
Quickly deploy Azure OpenAI to the best available region automatically.
Deploy Azure OpenAI models and find regional capacity intelligently.
Fine-tune, deploy, and evaluate models in Azure AI Foundry.
Deploy, evaluate, fine-tune, and optimize Microsoft Foundry agents and models.
Check Azure quotas and usage for capacity planning and region selection.
Use Azure AI for search, speech, transcription, and OCR tasks.