Flujo interactivo guiado para desplegar modelos de Azure OpenAI con control total: versión, SKU (GlobalStandard/Standard/ProvisionedManaged), capacidad, política RAI y opciones avanzadas.
Reemplaza a: `preset`, la variante rápida que elige región y SKU automáticamente
en todo el repo
0–100, la ruta de este skill
último commit aquí
últimos 90 días
149 tok en reposo
30 KB
Funciona con cualquier agente que lea SKILL.md
npx -y skills add microsoft/azure-skills --skill customize --agent claude-codeSe instala solo en este repositorio.
Di cualquiera de estas frases y el agente debería cargar este skill.
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 |
| 4. Get Model | List models via az cognitiveservices account list-models |
User selects from available or enters custom name |
| 5. Select Version | Query versions for chosen model | Recommend latest; user picks from list |
| 6. Select SKU | Query model catalog + subscription quota, show only deployable SKUs | ⚠️ Never hardcode SKU lists — always query live data |
| 7. Configure Capacity | Query capacity API, validate min/max/step, user enters value | Cross-region fallback if no capacity in current region |
| 8. Select RAI Policy | Present content filter options | Default: Microsoft.DefaultV2 |
| 9. Advanced Options | Dynamic quota (GlobalStandard), priority processing (PTU), spillover | SKU-dependent availability |
| 10. Upgrade Policy | Choose: OnceNewDefaultVersionAvailable / OnceCurrentVersionExpired / NoAutoUpgrade | Default: auto-upgrade on new default |
| 11. Deployment Name | Auto-generate unique name, allow custom override | Validates format: ^[\w.-]{2,64}$ |
| 12. Review | Display full config summary, confirm before proceeding | User approves or cancels |
| 13. Deploy & Monitor | az cognitiveservices account deployment create, poll status |
Timeout after 5 min; show endpoint + portal link |
| Error | Cause | Resolution |
|---|---|---|
| Model not found | Invalid model name | List available models with az cognitiveservices account list-models |
| Version not available | Version not supported for SKU | Select different version or SKU |
| Insufficient quota | Capacity > available quota | Skill auto-searches all regions; fails only if no region has quota |
| SKU not supported | SKU not available in region | Cross-region fallback searches other regions automatically |
| Capacity out of range | Invalid capacity value | PREVENTED: Skill validates min/max/step at input (Phase 7) |
| Deployment name exists | Name conflict | Auto-incremented name generation |
| Authentication failed | Not logged in | Run az login |
| Permission denied | Insufficient permissions | Assign Cognitive Services Contributor role |
| Capacity query fails | API/permissions/network error | DEPLOYMENT BLOCKED: Will not proceed without valid quota data |
# Check deployment status
az cognitiveservices account deployment show --name <account> --resource-group <rg> --deployment-name <name>
# List all deployments
az cognitiveservices account deployment list --name <account> --resource-group <rg> -o table
# Check quota usage
az cognitiveservices usage list --name <account> --resource-group <rg>
# Delete failed deployment
az cognitiveservices account deployment delete --name <account> --resource-group <rg> --deployment-name <name>
For SKU comparison tables, PTU sizing formulas, and advanced option details, load references/customize-guides.md.
SKU selection: GlobalStandard (production/HA) → Standard (dev/test) → ProvisionedManaged (high-volume/guaranteed throughput) → DataZoneStandard (data residency).
Capacity: TPM-based SKUs range from 1K (dev) to 100K+ (large production). PTU-based use formula: (Input TPM × 0.001) + (Output TPM × 0.002) + (Requests/min × 0.1).
Advanced options: Dynamic quota (GlobalStandard only), priority processing (PTU only, extra cost), spillover (overflow to backup deployment).
PROJECT_RESOURCE_ID environment variable to skip promptReproducido de microsoft/azure-skills bajo licencia MIT. Leer esta página en markdown.
4 archivos en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.
Es un flujo interactivo: va pidiendo cada decisión de configuración al usuario.
Necesita en el PATH:az
Este repo incluye 41 skills. Si instalas uno, normalmente ya tienes los demás.
Despliega, evalúa, ajusta y gestiona agentes de Foundry de punta a punta con azd: agentes hospedados, evaluación por lotes y continua, optimizador de prompts y fine-tuning (SFT/DPO/RFT).
Prepara proyectos Azure basados en azd para desplegar: genera azure.yaml, la infraestructura (Bicep o Terraform) y los Dockerfiles del flujo del Azure Developer CLI.
Depura incidencias de producción en Azure con AppLens, Azure Monitor, resource health y triaje seguro. Cubre App Service, Container Apps, Functions, AKS, VMs y mensajería.
Validación previa al despliegue en Azure. Comprueba en profundidad la configuración, la infraestructura (Bicep o Terraform), los roles RBAC, los permisos de identidad administrada y los prerrequisitos.
Skill unificado de despliegue de modelos de Azure OpenAI con enrutado por intención: despliegues rápidos con preset, despliegues personalizados y descubrimiento de capacidad entre regiones y proyectos.
Orquestador de punta a punta: de una idea o una app existente hasta un despliegue en Azure, con estimación de costes y aprobación previa. Analiza tu app y detecta los servicios adecuados.
Fase 2 del pipeline azure-app-onboard: mapea los componentes de la app a servicios de Azure con estimación de costes y validación de cuota. No es invocable directamente.
Despliega una app web o API existente en un clúster AKS ya en marcha: detecta el framework, genera Dockerfile y manifiestos, valida contra los Deployment Safeguards y despliega con verificación.
Fase 4 del pipeline azure-app-onboard: ejecuta la IaC validada contra Azure y verifica la salud de los recursos desplegados. No es invocable directamente.
