skills.rest
organvm-i-theoria
organvm-i-theoriaOFFICIAL
Explore all skills by this author →
GitHub

microsoft-foundry

Deploy, evaluate, and manage Microsoft Foundry agents and model deployments end-to-end.

Updated May 16, 2026
Search Tags:#evaluation#rbac#model deployment#agent deployment#quota management#azure ai#microsoft foundry
One-click install
npx skills add https://github.com/organvm-i-theoria/_agent-ontology --skill microsoft-foundry-organvm-i-theoria
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: microsoft-foundry
Source: https://github.com/organvm-i-theoria/_agent-ontology/tree/main/.agents/skills/microsoft-foundry
Command: npx skills add https://github.com/organvm-i-theoria/_agent-ontology --skill microsoft-foundry-organvm-i-theoria

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Managing the full lifecycle of Azure AI Foundry agents and models requires juggling many disconnected operations: provisioning resources, deploying models, containerizing agents, running evaluations, managing quotas, and configuring RBAC. This Skill unifies those workflows into guided, validated procedures. ## Core Features & Use Cases - Agent Lifecycle Management: Create, containerize, deploy to ACR, invoke, troubleshoot, and update hosted or prompt agents through Azure MCP tools and CLI workflows. - Evaluation & Observability: Run batch and continuous evaluations, optimize prompts, query traces via Application Insights, and build versioned datasets from production traces. - Infrastructure Provisioning: Create Foundry projects and AI Services resources, deploy models with preset/custom/capacity-discovery routing, and configure private networking. - Governance Operations: Manage RBAC role assignments, service principals, quotas, and capacity planning across regions. - Use Case: A developer asks to deploy a new support agent: the Skill provisions a Foundry project, deploys gpt-4o after checking regional quota, containerizes and deploys the agent, then sets up continuous evaluation with a trace-derived dataset. ## Quick Start Ask the assistant to deploy your agent to Microsoft Foundry and set up continuous evaluation for it.

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 Microsoft Foundry?▼

Use the deploy sub-skill, which containerizes your agent code, builds and pushes the image to Azure Container Registry, and creates or updates the hosted agent deployment. The Skill resolves project endpoint and registry settings from .foundry/agent-metadata.yaml automatically.

How do I deploy an Azure OpenAI model with specific capacity?▼

Use the models/deploy-model sub-skill, which routes your request to preset, customize, or capacity-discovery mode. It validates that the model supports your chosen SKU and that your subscription has available quota before presenting deployment options.

Can I create evaluation datasets from production traces?▼

Yes, the eval-datasets sub-skill harvests production traces into versioned evaluation datasets with train/test splits. It tracks evaluation metrics over time, detects regressions, and maintains lineage from trace to deployment.

What permissions do I need to create a Foundry project?▼

You need Owner, Contributor, or Azure AI Owner role on the target subscription or resource group. The Skill verifies your role assignments with az role assignment list before provisioning and stops if permissions are insufficient.

Why does my model deployment fail with QuotaExceeded?▼

QuotaExceeded means your subscription has no available TPM or PTU capacity in that region for the model. Use the quota sub-skill to check regional usage, delete unused deployments to free quota, or request an increase through the Azure Portal.

When should I not use this Skill for Azure tasks?▼

Do not use it for Azure Functions, App Service, or general Azure deployments, which belong to the azure-deploy skill. It is scoped specifically to Microsoft Foundry resources, agents, models, evaluations, quotas, and RBAC.

Related Skills

Explore More Software Engineering Skills→
pascalvanderheidenpascalvanderheiden

azd-deployment

Automate Azure deployments and infrastructure provisioning with azd and Bicep.

Community
Advanced
Aradhya0510Aradhya0510
3

databricks-mlflow-evaluation

Evaluate Generative AI agents with MLflow 3 GenAI APIs and custom scorers.

Community
Advanced
davidrrowleydavidrrowley

azure-ai-projects-py

Manage Azure Foundry AI agents and project resources with the azure-ai-projects Python SDK.

Community
Advanced
DauQuangThanhDauQuangThanh
14

azure-cloud

Guide Azure infrastructure design and deployment using Terraform, Bicep, and ARM templates.

Community
Advanced