# Deploy Azure AI Models with Capacity Checks

Azure model deployment requires current availability, quota, region, and SKU data. This skill guides deployment choices, confirmation, execution, and status checks.

## Install

```bash
npx skillstore add microsoft/deploy-model
```

## Metadata

- Status: approved
- Slug: microsoft-deploy-model
- Version: 1.0.0
- Author version: 1.0.0
- Skillstore revision: r2
- Version status: valid
- Tree hash: 6454a65bff32b76b6c56ebea9d7737a919ee23a36cbe94dbb867b444b756f3fb
- Author: microsoft
- GitHub username: microsoft
- License: MIT
- Repository: https://github.com/microsoft/github-copilot-for-azure/tree/main/plugin/skills/microsoft-foundry/models/deploy-model
- Ref: ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: blocked
- Manual install advisory: allowed\_with\_warning
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network, filesystem
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/microsoft-deploy-model
- Manifest: https://skillstore.pages.dev/api/skills/microsoft-deploy-model/manifest

## Capabilities

- Routes requests between preset deployment, custom deployment, and capacity discovery workflows.
- Checks Azure CLI authentication and confirms the target project before deployment.
- Queries live model availability, regional capacity, SKU support, and subscription quota.
- Guides model version, SKU, capacity, RAI policy, and upgrade option selection.
- Creates and monitors Azure AI Foundry model deployments after user confirmation.
- Generates Azure AI Foundry portal links for completed deployments.

## Use Cases

- Deploy a model quickly: Choose a model and use current Azure data to find suitable default deployment settings.
- Plan capacity across regions: Compare Azure regions and projects before selecting a model deployment target.
- Configure governed deployments: Select model version, SKU, capacity, RAI policy, and upgrade behavior for controlled environments.

## Prompt Templates

### Quick model deployment

```
Deploy gpt-4o-mini to my Azure AI Foundry project with recommended defaults. Confirm the target project before creating resources.
```

### Capacity discovery

```
Find regions where I can deploy gpt-4o with at least 50K TPM. Show capacity, quota, and matching projects.
```

### Custom deployment

```
Deploy gpt-4o with a selected version, GlobalStandard SKU, custom capacity, and Microsoft.DefaultV2 RAI policy. Review all settings first.
```

### Production deployment planning

```
Plan a production Azure AI Foundry deployment. Compare regions, SKU choices, quota limits, upgrade policy, and confirmation steps before deployment.
```

## Limitations

- Requires Azure CLI access and deployment permissions in the target subscription.
- Capacity, quota, pricing, and model availability depend on live Azure service data.
- Deployment actions can create billable Azure resources.
- Referenced deployment-name helpers are not included, and generated portal links may require adjustment.

## Best Practices

- Confirm subscription, project, region, SKU, and capacity before creating resources.
- Use live Azure quota and model catalog data instead of hardcoded availability lists.
- Start with conservative capacity and monitor usage before increasing throughput.

## Anti Patterns

- Deploying without showing the target project and subscription.
- Assuming a model or SKU is available without checking live Azure data.
- Selecting custom RAI policies or PTU settings without validating organizational requirements.

## Security Audit

- Audited at: 2026-07-23T19:49:49.254\+00:00
- Summary: Most static alerts are false positives from Markdown formatting, documented Azure commands, official Microsoft endpoints, and benign redirection. Confirmed risks include jq program injection through the SKU argument and a predictable temporary file. Semantic review also found local Python code injection and Azure CLI option injection.

## Stats

- Views: 199
- Downloads: 8
- Favorites: 0
- Popularity score: 0