skills.rest
p-potvin
p-potvinCOMMUNITY
Explore all skills by this author →
GitHub

microsoft-foundry

Deploy and manage Azure AI Foundry agents across container build, ACR push, hosting, and monitoring.

1|Updated Apr 4, 2026
Search Tags:#prompt optimization#azure#evaluation#rbac#model deployment#agent deployment#foundry
One-click install
npx skills add https://github.com/p-potvin/vaultwares-pipelines --skill microsoft-foundry-p-potvin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: microsoft-foundry
Source: https://github.com/p-potvin/vaultwares-pipelines/tree/main/.github/agents/agents/microsoft-foundry
Command: npx skills add https://github.com/p-potvin/vaultwares-pipelines --skill microsoft-foundry-p-potvin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the full lifecycle of Azure AI Foundry agents by providing guided, production-ready workflows to containerize, deploy, invoke, evaluate, monitor, and troubleshoot agents so teams can safely ship and operate agent-based services.

Core Features & Use Cases

  • Agent lifecycle orchestration: Build Docker images, push to ACR, create or update hosted/contained agent deployments, and start/stop containers.
  • Evaluation & optimization: Run batch evaluations, harvest traces into eval datasets, analyze failures, and drive prompt optimization and instruction improvements.
  • Project and resource management: Create Foundry projects and AI Services resources, perform capacity discovery, handle RBAC/quota checks, and resolve deployment failures with diagnostics and monitoring.
  • Use Case: Onboard a new agent by creating a Foundry project, containerizing the agent, deploying to an optimal region, running CI evaluation tests, and iterating prompts based on eval results.

Quick Start

Deploy the agent in ./my-agent to Azure Foundry using the preset workflow, push the image to ACR, and monitor the deployment until the container is running.

Frequently Asked Questions about microsoft-foundry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy an agent to Azure AI Foundry?▼

To deploy an agent to Azure AI Foundry, you need to containerize the agent using Docker, push the image to Azure Container Registry, and then create or update a hosted agent deployment using the Azure CLI.

How do I evaluate Azure AI Foundry agents and optimize prompts?▼

You can evaluate Azure AI Foundry agents by running batch evaluations and harvesting traces into evaluation datasets. Analyze failures from these results to drive prompt optimization and instruction improvements.

Do I need Azure CLI authentication and a specific project resource ID to manage Foundry agents?▼

Yes, managing Azure AI Foundry agents requires Azure CLI authentication, access to a subscription, a project resource ID, and a .foundry/agent-metadata.yaml file to execute lifecycle workflows.

How do I discover capacity and handle RBAC checks when provisioning Azure AI Foundry resources?▼

Azure AI Foundry resource provisioning uses scripted capacity discovery to find optimal regions and performs RBAC and quota checks to ensure proper access before creating projects and AI Services resources.

Why is my Azure AI Foundry agent deployment failing or not starting?▼

Azure AI Foundry agent deployment failures can be diagnosed using telemetry-based troubleshooting, diagnostics, and monitoring to resolve container hosting issues, RBAC errors, or capacity constraints.

Related Skills

Explore More Software Engineering Skills→
microsoftmicrosoft
2.9k

preset

Deploy Azure OpenAI models by checking regional capacity and selecting the best option.

Official
Advanced
EntityProcessEntityProcess
15

agentv-prompt-optimizer

Iteratively refine AI prompt files against AgentV evaluation datasets.

Official
Advanced
jrojas-pijrojas-pi

pi-acr-manager

Builds Docker images, pushes them to Azure Container Registry, and updates Azure Container Apps.

Community
Advanced
jgezelscorpjgezelscorp

microsoft-foundry

Manage Azure AI Foundry agents, models, quotas, and RBAC.

Community
Advanced