skills.rest
anishi1222
anishi1222COMMUNITY
Explore all skills by this author →
WebsiteGitHub

microsoft-foundry

Manage Foundry agent lifecycle including deployment, evaluation, fine-tuning, and monitoring.

Updated Feb 20, 2026
Search Tags:#monitoring#deployment#evaluation#fine-tuning#agent management#foundry
One-click install
npx skills add https://github.com/anishi1222/multi-agent-code-reviewer --skill microsoft-foundry-anishi1222
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: microsoft-foundry
Source: https://github.com/anishi1222/multi-agent-code-reviewer/tree/main/.agents/skills/microsoft-foundry
Command: npx skills add https://github.com/anishi1222/multi-agent-code-reviewer --skill microsoft-foundry-anishi1222

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires az, github-copilot, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the management of Foundry agents, including deployment, evaluation, fine-tuning, and monitoring, providing a comprehensive solution for AI agent lifecycle management.

Core Features & Use Cases

  • End-to-End Foundry Agent Management: Covers the entire lifecycle of Foundry agents, from deployment and evaluation to fine-tuning and monitoring.
  • Deploy Agents: Containerize, build, push to ACR, create/update/clone agent deployments.
  • Evaluate Agents: Run batch evals, analyze failures, optimize prompts, improve agent instructions, compare versions, set up CI/CD monitoring, and enable continuous production evaluation.
  • Fine-Tune Agents: Fine-tune models on Azure AI Foundry using SFT, DPO, or RFT, including dataset preparation, training job submission, deployment, and evaluation.
  • Monitor Agents: Continuously monitor agent performance and troubleshoot issues.

Quick Start

Use the microsoft-foundry skill to deploy a Foundry agent by running the following command: microsoft-foundry deploy-agent <agent-name> <model-name>.

Frequently Asked Questions about microsoft-foundry

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

FAQPage Schema
How do I deploy a Foundry agent to Azure Container Registry?▼

To deploy a Foundry agent, you containerize it by building a Docker image and pushing it to Azure Container Registry. You can then create, update, or clone the agent deployment using the Azure CLI and Copilot CLI.

Can I run batch evaluations on Foundry agents?▼

Yes, you can run batch evaluations on Foundry agents to analyze failures and optimize prompts. The Skill supports comparing agent versions and setting up continuous production evaluation to monitor performance.

Does Foundry agent management support LangGraph and custom Python frameworks?▼

Yes, Foundry agent management supports the Microsoft Agent Framework, LangGraph, and custom frameworks. You can manage agents implemented in either Python or C#.

What's the best way to fine-tune models on Azure AI Foundry?▼

The best way to fine-tune models on Azure AI Foundry is using SFT, DPO, or RFT methods. This process includes dataset preparation, submitting the training job, deploying the fine-tuned model, and evaluating its performance.

Do I need Azure CLI and Copilot CLI to manage Foundry agents?▼

Yes, you need both the Azure CLI and GitHub Copilot CLI installed to manage Foundry agents. These dependencies are required for automating Docker builds, ACR pushes, and agent lifecycle management tasks.

Related Skills

Explore More Software Engineering Skills→
jrojas-pijrojas-pi

pi-acr-manager

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

Community
Advanced
microsoftmicrosoft
2.9k

finetuning

Fine-tune AI models on Azure AI Foundry using SFT, DPO, or RFT.

Official
Advanced
mattmacleod16-svgmattmacleod16-svg
1

agentic-eval

Automate iterative evaluation and refinement of AI agent outputs with structured JSON results.

Community
Advanced
microsoftmicrosoft
2.9k

agent-framework-azure-ai-py

Build persistent Python agents for Azure AI Foundry with hosted tools and MCP integration.

Official
Advanced