agent-builder

Overview

Build high-performing OpenClaw agents end-to-end with this skill. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.

Key Features

• Design and generate a complete OpenClaw agent workspace with strong defaults and advanced-user-oriented clarifying questions.
• Iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
• Ask clarifying questions to ensure a clear understanding of the agent’s mission, autonomy level, and safety boundaries.
• Generate workspace files, including IDENTITY.md, SOUL.md, AGENTS.md, USER.md, and HEARTBEAT.md.
• Provide acceptance tests to validate the agent’s behavior.

How It Works

The skill guides you through four phases: interview, generate workspace files, guardrails checklist, and acceptance tests. You can also iterate on an existing agent by asking targeted questions and proposing minimal and surgical changes.

Use Cases

• Design a new OpenClaw agent from scratch.
• Iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
• Ensure a clear understanding of the agent’s mission, autonomy level, and safety boundaries.