Compétences deploy-model
📦

deploy-model

Risque faible ⚡ Contient des scripts🌐 Accès réseau⚙️ Commandes externes

نشر نماذج Azure OpenAI

نشر نماذج OpenAI في Azure Foundry مع التوجيه الذكي. يتعامل هذا المهارة مع عمليات النشر المسبقة التكوين والإعدادات المخصصة واكتشاف السعة عبر مناطق Azure.

Prend en charge: Claude Codex Code(CC)
🥉 73 Bronze
1

Télécharger le ZIP du skill

2

Importer dans Claude

Allez dans Paramètres → Capacités → Skills → Importer un skill

3

Activez et commencez à utiliser

Tester

Utilisation de "deploy-model". Deploy gpt-4o to Azure Foundry

Résultat attendu:

  • تم إنشاء النشر بنجاح
  • النموذج: gpt-4o
  • المنطقة: eastus
  • SKU: Standard
  • السعة: تلقائية
  • عنوان URL للنشر: https://portal.azure.com/...

Utilisation de "deploy-model". Find capacity for gpt-4o-mini

Résultat attendu:

  • المناطق المتاحة:
  • 1. eastus - 500 TPM متاح
  • 2. westus2 - 300 TPM متاح
  • 3. uksouth - 200 TPM متاح

Audit de sécurité

Risque faible
v1 • 2/21/2026

Static analysis flagged 475 potential issues, but evaluation confirms these are false positives or expected behavior. The skill uses shell commands to invoke Azure CLI for model deployment operations, which is legitimate for Azure tooling. Network access is to Azure API endpoints. Filesystem patterns are documentation examples, not vulnerabilities. This is an official Microsoft skill for Azure Foundry.

17
Fichiers analysés
2,443
Lignes analysées
6
résultats
1
Total des audits
Problèmes à risque faible (3)
capacity/scripts/discover_and_rank.ps1:25-33scripts/generate_deployment_url.sh:75-79
Shell Command Execution in Scripts
Scripts use shell commands to invoke Azure CLI for model deployment. This is expected behavior for an Azure deployment skill.
capacity/scripts/discover_and_rank.ps1:26-32
Network Access to Azure Endpoints
Scripts make network requests to Azure API endpoints. This is required for Azure model deployment operations.
capacity/SKILL.md:31SKILL.md:130
Documentation References to File Paths
Documentation files contain example paths. These are documentation examples, not actual filesystem vulnerabilities.

Facteurs de risque

⚡ Contient des scripts
Aucun emplacement spécifique enregistré
🌐 Accès réseau (2)
capacity/scripts/discover_and_rank.ps1:26 scripts/generate_deployment_url.ps1:59
⚙️ Commandes externes (4)
capacity/scripts/discover_and_rank.ps1:25-26 capacity/scripts/discover_and_rank.sh:17 capacity/SKILL.md:21 SKILL.md:25-47
Audité par: claude

Score de qualité

45
Architecture
100
Maintenabilité
85
Contenu
50
Communauté
84
Sécurité
91
Conformité aux spécifications

Ce que vous pouvez construire

نشر النموذج السريع

نشر نموذج OpenAI مع الإعدادات الافتراضية للنماذج الأولية السريعة

نشر المؤسسة المخصص

تكوين النشر باستخدام SKU محدد وسعة وسياسات RAI للإنتاج

اكتشاف السعة

العثور على المناطق والسعة المتاحة لأنواع نماذج محددة قبل النشر

Essayez ces prompts

النشر السريع 
Deploy gpt-4o to Azure Foundry in the eastus region
النشر المخصص 
Deploy gpt-4 with Standard SKU, 100 TPM capacity, and content filtering enabled to westus2
العثور على السعة 
Find where I can deploy gpt-4o-mini with at least 50 TPM capacity
تحليل النشر 
Show me the best regions for deploying gpt-4 with high capacity

Bonnes pratiques

  • Always verify capacity availability before deploying in production
  • Use descriptive deployment names for easier management
  • Configure RAI policies appropriate for your use case
  • Store deployment URLs securely for reference

Éviter

  • Do not use for listing existing deployments (use foundry_models_deployments_list)
  • Do not use for deleting resources (use dedicated Azure tools)
  • Do not assume all regions have equal capacity
  • Avoid deploying without checking availability first

Foire aux questions

What Azure permissions are required to use this skill?
You need Azure Foundry contributor access or higher to deploy models.
Can this skill delete existing deployments?
No, this skill is for deployment creation only. Use Azure portal or dedicated tools for management.
How do I check deployment status?
The skill returns deployment status after creation. Use Azure portal or MCP tools for ongoing monitoring.
What regions are supported?
All Azure regions that support Azure OpenAI service are supported.
Can I deploy multiple models at once?
The skill handles one deployment request at a time. Repeat the command for multiple models.
What happens if capacity is unavailable?
The skill will report unavailable regions. Use capacity discovery to find viable alternatives.

Détails du développeur

Auteur

microsoft

Licence

MIT

Dépôt

https://github.com/microsoft/github-copilot-for-azure/tree/main/plugin/skills/microsoft-foundry/models/deploy-model

Réf

main

Structure de fichiers

📁 capacity/

📁 scripts/

📄 discover_and_rank.ps1

📄 discover_and_rank.sh

📄 query_capacity.ps1

📄 query_capacity.sh

📄 SKILL.md

📁 customize/

📁 references/

📄 customize-guides.md

📄 customize-workflow.md

📄 EXAMPLES.md

📄 SKILL.md

📁 preset/

📁 references/

📄 preset-workflow.md

📄 workflow.md

📄 EXAMPLES.md

📄 SKILL.md

📁 scripts/

📄 generate_deployment_url.ps1

📄 generate_deployment_url.sh

📄 SKILL.md

📄 TEST_PROMPTS.md