Skills agent-framework
📦

agent-framework

Safe 🔑 Env variables

Build AI agents with Microsoft Agent Framework

Create AI agents and multi-agent workflows using Microsoft Agent Framework SDK. This skill scaffolds agent projects with tools, HTTP server support, and VSCode debugging configurations for enterprise AI applications.

Supports: Claude Codex Code(CC)
🥉 76 Bronze
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "agent-framework". Create a new agent called 'WeatherAgent' that can tell the weather

Expected outcome:

The skill generates: requirements.txt with pinned agent-framework versions, main.py with ChatAgent setup and weather tool, .env file template for FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL_DEPLOYMENT_NAME, .vscode/launch.json and .vscode/tasks.json for debugging

Using "agent-framework". Build a Writer-Reviewer workflow

Expected outcome:

The skill generates: A Writer executor that creates content, A Reviewer executor that provides feedback, WorkflowBuilder configuration with edges connecting the two agents, run_stream event handling for real-time output

Security Audit

Safe
v1 • 2/21/2026

This is an official Microsoft skill for creating AI agents using Microsoft Agent Framework SDK. The static scanner flagged 165 potential issues, but evaluation confirms all are false positives. The flagged backtick patterns are Markdown code fences in documentation files. The skill appropriately uses .env files for storing Azure Foundry credentials (FOUNDRY_PROJECT_ENDPOINT, FOUNDRY_MODEL_DEPLOYMENT_NAME), which is a standard and secure practice for credential management.

7
Files scanned
785
Lines analyzed
2
findings
1
Total audits
Medium Risk Issues (1)
Environment File Access
The skill creates .env files to store Azure Foundry project endpoint and model deployment name credentials.

Risk Factors

🔑 Env variables (1)
Audited by: claude

Quality Score

45
Architecture
100
Maintainability
87
Content
50
Community
100
Security
91
Spec Compliance

What You Can Build

Enterprise AI Application Development

Build production AI agents with type safety, checkpointing, and orchestration for enterprise Azure environments.

Multi-Agent Workflow Prototyping

Create and test multi-agent workflows with Writer-Reviewer patterns, loops, and human-in-the-loop interactions.

VSCode Debugging Setup

Configure local debugging with AI Toolkit Agent Inspector for interactive agent testing and troubleshooting.

Try These Prompts

Create Basic Agent
Create a new AI agent using Microsoft Agent Framework that can respond to user queries. Include HTTP server mode support.
Create Agent with Tools
Build an agent with custom tools using the function calling pattern. Add at least 2 custom tools for the agent to use.
Create Multi-Agent Workflow
Create a multi-agent workflow with a Writer agent that generates content and a Reviewer agent that provides feedback. Use the workflow builder pattern.
Create Loop Workflow
Build a multi-agent loop workflow where a Teacher agent and Student agent interact. Include turn-based control with a maximum of 5 iterations.

Best Practices

  • Always use pinned SDK versions (1.0.0b260107 for agent-framework) to avoid breaking changes from beta releases
  • Use virtual environments (.venv) to isolate dependencies and avoid conflicts
  • Configure HTTP server mode as the default entry point for better debugging and containerization support
  • Pin environment variables in .env file but remind users to update values before running

Avoid

  • Using bare 'python' or 'pip' commands without virtual environment activation
  • Skipping the server mode when the user needs HTTP endpoint access
  • Using legacy AzureAIAgentClient instead of current AzureAIClient
  • Not pinning SDK versions leading to breaking changes from beta releases

Frequently Asked Questions

What programming language does this skill support?
This skill supports Python only. The Microsoft Agent Framework SDK for JavaScript/TypeScript requires a different skill.
Do I need an Azure subscription?
Yes, you need an Azure AI Foundry project with a deployed model. The skill will help you configure the FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL_DEPLOYMENT_NAME environment variables.
Can I debug agents locally?
Yes, the skill generates .vscode configurations for debugging with AI Toolkit Agent Inspector. This provides interactive debugging and message flow visualization.
What is MCP in this context?
MCP (Model Context Protocol) is a standard for connecting AI agents to external tools. The skill supports both stdio-based and HTTP-based MCP tools.
Why pin SDK versions?
The agent-framework SDK is in preview (beta). Version 1.0.0b260107 is stable. Later versions may have breaking changes like renamed classes (AgentRunResponseUpdate vs AgentResponseUpdate).
What is Agent-as-Server pattern?
This pattern wraps your agent/workflow in an HTTP server using azure-ai-agentserver packages. It enables containerization, deployment to Azure Foundry, and integration with other services.