$ loading_
Quickly deploy Azure OpenAI to the best available region automatically.
This skill appears to be an open-source prompt-style deployment aid, with no built-in secrets, standalone remote endpoints, or arbitrary local execution shown in the materials. It guides standard Azure CLI operations for querying capacity and creating deployments, so overall risk is low to moderate caution.
The material says the skill itself requires no extra secret, but it depends on an existing Azure CLI login and a subscription with Cognitive Services read/create permissions. In shared terminals or highly privileged subscriptions, this creates the usual risk of cloud-resource misuse through reused credentials.
No separate third-party remote endpoint is declared, but the README clearly uses Azure CLI/REST against Azure management and Cognitive Services APIs to query regional capacity, list models, and create deployments. This is normal network communication consistent with the stated function.
The README shows commands such as `az account show`, `az rest`, and `az cognitiveservices ... create`, meaning the expected capability is to drive the local Azure CLI to perform cloud-management actions. Such local process invocation is a normal capability for tools/skills, and no excessive system privilege request is evident.
The material indicates access to Azure CLI auth state, subscription context, and `PROJECT_RESOURCE_ID`, along with cloud metadata for projects/accounts/model capacity; it may also create projects or deployments. There is no indication of reading sensitive local files or broad local writes, but it does have real mutation capability over Azure resources, so least privilege is advisable.
The source is a Microsoft-related open-source GitHub repository, and the system flags it as prompt-only and open-source, with some community adoption (222 stars). Although the license is unspecified and maintenance status is unknown, it remains auditable from the material provided, with no obvious supply-chain red flags.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "preset" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/plugin/skills/microsoft-foundry/models/deploy-model/preset/SKILL.md 2. Save it as ~/.claude/skills/preset/SKILL.md 3. Reload skills and tell me it's ready
Use preset to deploy an Azure OpenAI model for me. Check capacity in the current region first, and if it is unavailable, recommend the best available alternative region.
Returns the best selected deployment region and completes or prepares the quick deployment steps.
Use preset to check Azure OpenAI capacity across all available regions. Prioritize the current region, and if it is not available, provide several best fallback regions.
Outputs whether the current region is available and provides prioritized alternative region recommendations.
I want to launch an Azure OpenAI service quickly. Use preset to automatically choose a region with sufficient capacity that suits high-availability deployment.
Provides a region choice suitable for rapid launch and high availability, with deployment-ready guidance.
Automates intelligent Azure OpenAI model deployment by checking capacity across regions and deploying to the best available option.
PROJECT_RESOURCE_ID env var or provided interactively)
/subscriptions/{sub-id}/resourceGroups/{rg}/providers/Microsoft.CognitiveServices/accounts/{account}/projects/{project}1. Check authentication → 2. Get project → 3. Check current region capacity
→ 4. Deploy immediately
1. Check authentication → 2. Get project → 3. Check current region (no capacity)
→ 4. Query all regions → 5. Show alternatives → 6. Select region + project
→ 7. Deploy
| Phase | Action | Key Commands |
|---|---|---|
| 1. Verify Auth | Check Azure CLI login and subscription | az account show, az login |
| 2. Get Project | Parse PROJECT_RESOURCE_ID ARM ID, verify exists | az cognitiveservices account show |
| 3. Get Model | List available models, user selects model + version | az cognitiveservices account list-models |
| 4. Check Current Region | Query capacity using GlobalStandard SKU | az rest --method GET .../modelCapacities |
| 5. Multi-Region Query | If no local capacity, query all regions | Same capacity API without location filter |
| 6. Select Region + Project | User picks region; find or create project | az cognitiveservices account list, az cognitiveservices account create |
| 7. Deploy | Generate unique name, calculate capacity (50% available, min 50 TPM), create deployment | az cognitiveservices account deployment create |
For detailed step-by-step instructions, see workflow reference.
| Error | Symptom | Resolution |
|---|---|---|
| Auth failure | az account show returns error | Run az login then az account set --subscription <id> |
| No quota | All regions show 0 capacity | Defer to the quota skill for increase requests and troubleshooting; check existing deployments; try alternative models |
| Model not found | Empty capacity list | Verify model name with az cognitiveservices account list-models; check case sensitivity |
| Name conflict | "deployment already exists" | Append suffix to deployment name (handled automatically by generate_deployment_name script) |
| Region unavailable | Region doesn't support model | Select a different region from the available list |
| Permission denied | "Forbidden" or "Unauthorized" | Verify Cognitive Services Contributor role: az role assignment list --assignee <user> |
# Custom capacity
az cognitiveservices account deployment create ... --sku-capacity <value>
# Check deployment status
az cognitiveservices account deployment show --name <acct> --resource-group <rg> --deployment-name <name> --query "{Status:properties.provisioningState}"
# Delete deployment
az cognitiveservices account deployment delete --name <acct> --resource-group <rg> --deployment-name <name>
…
Set up Entra ID app registration, OAuth, permissions, and MSAL integration.
Set up Azure Application Insights telemetry for web apps with best practices.
Troubleshoot Azure Event Hubs and Service Bus SDK connection and messaging issues.
Find, list, and inspect Azure resources across subscriptions and resource groups.
Deploy, evaluate, fine-tune, and optimize Microsoft Foundry agents and models.
Deploy prepared Azure apps with built-in recovery for common release errors.
Guide custom Azure OpenAI deployments with detailed model and capacity settings.
Deploy Azure OpenAI models and find regional capacity intelligently.
Discover Azure OpenAI capacity, quotas, and best regions for deployment.
Use Azure AI for search, speech, transcription, and OCR tasks.
Search Azure service updates, retirements, and feature announcements in natural language.
Fine-tune, deploy, and evaluate models in Azure AI Foundry.