mirror of https://github.com/magnus919/agent-skills.git synced 2026-09-16 05:56:30 +03:00

Files

T

Magnus Hedemark 5428b18ddd feat: add autogen — expert skill for conversational multi-agent AI

Greenfield SkillOpt: 3 epochs for Microsoft AutoGen skill.
Conversational agent model, GroupChat patterns, code execution,
nested chats, cancellation tokens, MCP integration.

All API surfaces validated against microsoft.github.io/autogen docs.

2026-07-09 14:57:27 -04:00

1.1 KiB

Raw Blame History

AutoGen Code Execution

Docker (Recommended)

Safe execution of LLM-generated code in isolated containers:

from autogen_ext.code_executors.docker import DockerCommandLineCodeExecutor

executor = DockerCommandLineCodeExecutor(work_dir="coding")
async with executor:
    # Use within GroupChat
    proxy = UserProxyAgent(
        name="proxy",
        code_executor=executor,
        human_input_mode="NEVER",
    )

Local (Development Only)

Runs generated code on your machine — use only for trusted environments:

from autogen_ext.code_executors.local import LocalCommandLineCodeExecutor

executor = LocalCommandLineCodeExecutor(work_dir="coding")

Cancellation

from autogen_core import CancellationToken

token = CancellationToken()
result = await executor.execute_code_blocks(code_blocks, cancellation_token=token)
# Cancel via: token.cancel()

Best Practices

Use Docker for any untrusted code execution
Set a work_dir to isolate generated files
Always pass a CancellationToken for long-running tasks
Monitor max_turns to prevent runaway code generation

1.1 KiB Raw Blame History