AgentTeams Migration Skill

This skill guides you through migrating your current OpenClaw instance into a AgentTeams managed Worker. You need to understand AgentTeams's architecture to produce a correct migration package.

AgentTeams Worker Architecture (Read This First)

AgentTeams is a multi-agent system where a Manager orchestrates multiple Workers:

• Workers run in Docker containers based on agentteams/worker-agent image (Ubuntu 22.04 + Node.js 22 + OpenClaw + mcporter + mc)
• Workers communicate via Matrix (not Discord/Slack), each Worker has a dedicated 3-party room (Human + Manager + Worker)
• All configuration is stored in MinIO (S3-compatible), not local filesystem
• Workers are stateless, containers can be recreated at any time, all state lives in MinIO
• The Manager controls Worker skills, Workers cannot modify their own skills/ directory

AGENTS.md Builtin-Merge System

AgentTeams uses a marker system in AGENTS.md to separate managed content from user content:

<!-- agentteams-builtin-start -->
> ⚠️ **DO NOT EDIT** this section. It is managed by AgentTeams and will be automatically
> replaced on upgrade.

(AgentTeams's Worker workspace rules, communication protocol, task execution rules, etc.)

<!-- agentteams-builtin-end -->

(Your custom content goes here, this part survives upgrades)

The builtin section (between the markers) is injected by the import script and contains:

• Workspace layout and file sync instructions
• Matrix @mention communication protocol
• Task execution workflow
• Memory and session management rules

Your migrated AGENTS.md content must go AFTER the <!-- agentteams-builtin-end --> marker. The import script handles the marker injection, you only need to produce the user content portion.

What the Worker Base Image Already Has