skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
magnus919/agent-skills111 installs

autogen

Build conversational multi-agent systems with Microsoft AutoGen. AssistantAgent, UserProxyAgent, GroupChat, code execution, nested chats, cancellation tokens, tool integration, and MCP support. Use when building conversation-driven multi-agent systems or comparing agent frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.

How do I install this agent skill?

npx skills add https://github.com/magnus919/agent-skills --skill autogen
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides documentation and templates for the Microsoft AutoGen multi-agent framework. It demonstrates security best practices by explicitly warning against local code execution for untrusted tasks and recommending Docker-based isolation. No malicious code or exfiltration patterns were detected.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

AutoGen Expert Skill

This skill targets the AutoGen AgentChat 0.7.5 API on Python 3.10+. AutoGen (by Microsoft Research) is a framework for conversational multi-agent AI. Unlike LangGraph's explicit graph topology or CrewAI's role-based crews, AutoGen uses agent-to-agent conversations as the orchestration primitive. Agents communicate through structured chat, with built-in patterns for group chat routing, human input, and code execution.

Core Paradigm

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

model_client = OpenAIChatCompletionClient(model="gpt-4o-mini")

assistant = AssistantAgent(
    name="assistant",
    system_message="You are a helpful assistant.",
    model_client=model_client,
)

Role split in AgentChat 0.7.5: UserProxyAgent represents a human and obtains replies through input_func. CodeExecutorAgent executes code blocks using a CodeExecutor. They are separate agents; neither accepts the legacy human_input_mode option.

Core Principles

  1. Conversations are the orchestration primitive. Agents send messages, receive replies, and the conversation structure determines the workflow.
  2. Keep human input and code execution separate. Use UserProxyAgent for a human participant; use CodeExecutorAgent with a CodeExecutor for code.
  3. GroupChat routes between agents. RoundRobinGroupChat cycles fixed-order. SelectorGroupChat uses an LLM to pick the next speaker.
  4. Nested chats delegate work. An agent can spawn a sub-conversation between specialist agents and return the result.
  5. Docker is the safe code execution mode. Local code execution (LocalCommandLineCodeExecutor) runs LLM-generated code on your machine — use Docker in production.
  6. Cancellation tokens stop runaway agents. Always pass CancellationToken for long-running tasks.

Where to Start

You already have...Start here
Nothing — exploring AutoGenCreate an assistant chat or a team with a human UserProxyAgent
Agents that need to coordinateBuild a GroupChat with multiple agents
Agents that need code executionConfigure Docker code executor
A complex multi-step taskUse nested chats for sub-tasks

Quick Reference

TaskApproachReference
Human-in-the-loop chatAssistantAgent + UserProxyAgentreferences/agent-types.md
Multi-agent groupGroupChat with RoundRobinGroupChatreferences/group-chat.md
Code executionDockerCommandLineCodeExecutorreferences/code-execution.md
Tool integrationregister_function() or @toolreferences/tool-integration.md
Nested chatAgentTool or a team run from a toolreferences/conversation-patterns.md
CancellationCancellationTokenreferences/conversation-patterns.md
MCP toolsMcpWorkbenchreferences/tool-integration.md

Framework Routing Guide

ScenarioReach forWhy
Conversation-driven multi-agentAutoGenNative agent-to-agent chat as orchestration
Role-based multi-agent teamsCrewAIRole/Goal/Backstory is the native abstraction
State-machine multi-agentLangGraphGraph topology, subgraphs, human-in-the-loop
Chain/agent compositionLangChainLCEL pipe operator for general chains

Reference Files

ReferenceLoad whenFile
Agent TypesAssistantAgent, UserProxyAgentreferences/agent-types.md
Conversation PatternsSend/receive, nested chats, cancellationreferences/conversation-patterns.md
Group ChatRoundRobin, Selector, MagenticOnereferences/group-chat.md
Code ExecutionDocker, local, cancellation tokensreferences/code-execution.md
Tool Integrationregister_function, @tool, MCP integrationreferences/tool-integration.md
v0.4 Migrationv0.2->v0.4 migration, AgentTool, streaming, terminationreferences/v04-migration.md
Validation AuditResearch validation of all API claimsreferences/validation-audit.md
FAQ & TroubleshootingCommon errors and fixesreferences/faq-and-troubleshooting.md

Install the exact package versions used by the templates with python -m pip install -r requirements.txt from this skill directory. The code-execution example uses Docker and requires a working Docker daemon.

Templates

TemplateWhen to useFile
Two-Agent ChatAssistant + human inputtemplates/two-agent-chat.py
Group ChatMulti-agent team with speaker routingtemplates/group-chat.py
Code Execution AgentAssistant + Docker-backed code executortemplates/code-execution.py

Troubleshooting

SymptomLikely causeFixReference
Agent loops foreverNo team termination conditionAdd a TerminationCondition such as MaxMessageTerminationreferences/conversation-patterns.md
Code execution failsDocker not runningStart Docker or use LocalCommandLineCodeExecutorreferences/code-execution.md
Nested chat never returnsCancellation token not passedPass CancellationToken with timeoutreferences/conversation-patterns.md
v0.2 code doesn't workv0.4 API changedFollow migration guidereferences/faq-and-troubleshooting.md
GroupChat speaker selection loopsSelectorGroupChat with no clear nextUse RoundRobinGroupChat for fixed orderreferences/group-chat.md
UserProxyAgent waits for inputIt is a human participant and its input_func is waitingSupply an appropriate input function or use an automated agentreferences/agent-types.md

When NOT to Use AutoGen

  • Simple single-agent task — overkill, use direct API call
  • Need fine-grained graph control — use LangGraph
  • Need role-based teams with fixed processes — use CrewAI
  • Need chain composition — use LangChain LCEL

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/magnus919/agent-skills/autogen">View autogen on skillZs</a>