---
name: "autogen-multiagent-conversational-swarm"
description: "Orchestrate collaborative multi-agent group chats with Microsoft AutoGen 0.4."
metadata:
  author: "Microsoft"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "create autogen groupchat"
  - "configure autogen assistantagent"
  - "setup autogen code execution"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# Microsoft AutoGen Conversational Agent Swarms

Builds autonomous agent swarms with AutoGen: ConversableAgent, GroupChat, GroupChatManager, custom speaker selection strategies, and Docker code execution sandboxes.

## When to Invoke
Invoke this skill whenever you need to:
- create autogen groupchat
- configure autogen assistantagent
- setup autogen code execution

## Execution SOP & Rules
1. Define focused system messages for each agent establishing specific domain ownership.
2. Set human_input_mode='TERMINATE' or 'ALWAYS' on UserProxyAgent depending on automation requirements.
3. Enclose code blocks in ```python tags with clear termination keywords (TERMINATE).
4. Execute untrusted generated code only inside isolated Docker container environments.

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.