deploy-model
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).
94
92%
Does it follow best practices?
Impact
96%
2.66xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
88%
54%Automate Azure OpenAI Model Deployment to the Best Available Region
Preset deployment workflow implementation
GlobalStandard SKU only
0%
100%
API version 2024-10-01
0%
100%
50% capacity formula
0%
100%
Minimum 50 TPM
0%
100%
generate_deployment_name script
0%
0%
PROJECT_RESOURCE_ID env var check
100%
100%
Current region checked first
100%
100%
Project confirmation step
80%
100%
Deployment status monitoring
0%
100%
No hardcoded SKU lists
100%
100%
100%
73%Deploy an Anthropic Claude Model to Azure AI Foundry
Anthropic model deployment via REST API
REST API not CLI
80%
100%
modelProviderData present
0%
100%
Industry field included
0%
100%
Industry always prompted
0%
100%
countryCode field included
0%
100%
organizationName field included
0%
100%
Capacity set to 1
0%
100%
No RAI policy step
100%
100%
No version upgrade policy
100%
100%
Correct API version in URL
0%
100%
100%
51%Build an Azure OpenAI Deployment Assistant Script
Intent routing and SKU validation
PTU/provisioned routes to customize
100%
100%
Capacity query routes to capacity
100%
100%
Simple model name routes to preset
100%
100%
Default to preset when ambiguous
0%
100%
discover_and_rank script used
0%
100%
Subscription quota validated after discovery
80%
100%
Quota name pattern correct
0%
100%
No hardcoded SKU list
100%
100%
Zero-quota SKUs marked not selectable
12%
100%
Capacity discovery 4-option handoff
0%
100%
Project confirmation before deploy
0%
100%
Capacity+deploy ambiguous → discovery first
100%
100%
- Repository
- microsoft/azure-skills
- Commit
9d594ab
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.