agent-builder

Generate OpenClaw agent workspace files and define agent personas and guardrails.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/dsactivi-2/Mujo-Team --skill agent-builder-dsactivi-2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-builder
Source: https://github.com/dsactivi-2/Mujo-Team/tree/main/skills/agent-builder
Command: npx skills add https://github.com/dsactivi-2/Mujo-Team --skill agent-builder-dsactivi-2

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the creation and iteration of OpenClaw agents, automating the generation of essential workspace files and ensuring adherence to best practices.

Core Features & Use Cases

  • End-to-End Agent Creation: Design and generate a complete OpenClaw agent workspace from scratch, including IDENTITY.md, SOUL.md, AGENTS.md, USER.md, and HEARTBEAT.md.
  • Iterative Agent Improvement: Refine existing agents by targeting specific failure modes, autonomy changes, or safety boundaries.
  • Use Case: A product manager needs to quickly spin up a new customer support agent. They use this Skill to define the agent's persona, operating rules, and communication channels, receiving a fully configured workspace in minutes.

Quick Start

Use the agent-builder skill to create a new agent for managing customer feedback, starting with a job statement and desired autonomy level.

Frequently Asked Questions about agent-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an OpenClaw agent from scratch?

To build an OpenClaw agent, define a job statement and autonomy level to generate essential workspace files like IDENTITY.md, SOUL.md, and AGENTS.md for a complete persona and operating rules configuration.

What files are required for an OpenClaw agent workspace?

An OpenClaw agent workspace requires IDENTITY.md, SOUL.md, AGENTS.md, USER.md, and HEARTBEAT.md files to define agent personas, operating rules, safety guardrails, and communication channels.

How do I refine an existing OpenClaw agent's safety boundaries?

Refine an existing OpenClaw agent by targeting specific failure modes or autonomy changes to update its safety guardrails, operating rules, and workspace files iteratively.

Do I need to understand OpenClaw workspace structure to create an agent?

Yes, understanding OpenClaw workspace structure and agent behavior principles is required to effectively define agent personas, operating rules, and autonomy levels during generation and iteration.

Can I generate an OpenClaw customer support agent automatically?

Yes, you can automatically generate a fully configured OpenClaw customer support agent workspace by providing a job statement and desired autonomy level to define its persona and communication channels.

What's the best way to define agent operating rules in OpenClaw?

The best way to define OpenClaw agent operating rules is using the agent-builder to configure AGENTS.md and SOUL.md files, ensuring adherence to best practices for safety guardrails and autonomy.