Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/ag2ai/resource-hub --skill ag2-importsThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
REST and WebSocket endpoint patterns, error handling, and Pydantic schema conventions for the backend
Architecture, directory layout, communication protocol, and conventions for the full-stack multi-agent application
Step-by-step guide to add a new REST or WebSocket endpoint to the backend
Based on SOC occupation classification
Showing SKILL.md
| name | ag2-imports |
| description | Correct import paths and module structure for the AG2 framework |
| license | Apache-2.0 |
The package name is ag2, not autogen. All imports use the ag2 namespace.
from ag2.agentchat import AssistantAgent, UserProxyAgent, ConversableAgent
AssistantAgent -- LLM-powered agent that generates replies.UserProxyAgent -- Proxy for human input; can also execute code.ConversableAgent -- Base class for all conversable agents.from ag2 import LLMConfig
Use LLMConfig as a context manager to bind a model configuration to agents created within its scope:
with LLMConfig(api_type="openai", model="gpt-4o"):
agent = AssistantAgent(name="assistant")
from ag2.agentchat.group import run_group_chat
from ag2.agentchat.group import DefaultPattern, AutoPattern, RoundRobinPattern
run_group_chat -- Orchestrates a multi-agent conversation.DefaultPattern -- LLM-based speaker selection with optional handoffs.AutoPattern -- Automatic orchestration; the LLM decides flow.RoundRobinPattern -- Agents speak in fixed round-robin order.from ag2.tools import tool
The @tool decorator converts a plain function into a tool that agents can call.
from ag2.agentchat import initiate_chats # Sequential multi-conversation
from ag2.agentchat import register_hand_off # Handoff registration
from ag2.agentchat.group import Handoff # Explicit handoff target
import autogen -- the package was renamed to ag2.GroupChat or GroupChatManager -- use run_group_chat with a pattern instead.config_list dicts -- use LLMConfig objects.