← Back to Skills Marketplace
plgonzalezrx8

Agent Builder

by Pedro Gonzalez · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
7369
Downloads
28
Stars
56
Active Installs
1
Versions
Install in OpenClaw
/install agent-builder
Description
Build high-performing OpenClaw agents end-to-end. 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.
Usage Guidance
Safe to install for building OpenClaw agents. Before using generated files, review AGENTS.md, SOUL.md, MEMORY.md, and HEARTBEAT.md; keep memory free of secrets, leave heartbeats empty until needed, and choose conservative autonomy unless broad autonomy is intentional.
Capability Analysis
Type: OpenClaw Skill Name: agent-builder Version: 1.0.0 The OpenClaw AgentSkills bundle is designed to help an AI agent build and iterate on other OpenClaw agents' configurations. The `SKILL.md` instructions guide the agent through an interview process and then to generate or modify standard OpenClaw workspace files (`SOUL.md`, `AGENTS.md`, etc.). The included reference files (`references/openclaw-workspace.md`, `references/templates.md`) explicitly promote security best practices, such as not storing secrets in the workspace and including guardrails (e.g., 'ask before destructive actions') in generated agent configurations. There is no evidence of prompt injection, data exfiltration, malicious execution, or any other harmful behavior directed at the executing agent or the user.
Capability Assessment
Purpose & Capability
The skill coherently supports its stated purpose: interviewing the user, generating OpenClaw workspace files, and iterating agent behavior. It can shape future agent autonomy, so review of generated rules is appropriate.
Instruction Scope
Instructions are scoped to workspace generation and targeted diffs, and they explicitly include guardrails such as ask-before-destructive-actions and ask-before-outbound-messages. The broad autonomy option is disclosed as higher risk.
Install Mechanism
The artifact contains only markdown instruction and reference files; there are no executable scripts, package installs, binaries, environment variables, or credential setup requirements.
Credentials
The skill itself does not request network, credential, or system access. It helps design agents that may later use tools or messaging channels depending on user choices.
Persistence & Privilege
Optional MEMORY.md, daily memory logs, and HEARTBEAT.md are purpose-aligned and disclosed. Templates advise private-session memory, empty heartbeat defaults, and no stored secrets.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install agent-builder
  3. After installation, invoke the skill by name or use /agent-builder
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of agent-builder skill. - Enables end-to-end design and generation of OpenClaw agent workspaces. - Guides users through key agent setup, including job statement, channels, autonomy, guardrails, and memory options. - Automatically creates all required OpenClaw files (IDENTITY.md, SOUL.md, AGENTS.md, USER.md, HEARTBEAT.md) with tailored content. - Supports iteration on existing agents, focusing on addressing failure modes, autonomy adjustments, and safety boundaries. - Provides checklists for guardrails and fast acceptance test scenarios to validate agent behavior.
Metadata
Slug agent-builder
Version 1.0.0
License
All-time Installs 271
Active Installs 56
Total Versions 1
Frequently Asked Questions

What is Agent Builder?

Build high-performing OpenClaw agents end-to-end. 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 7369 downloads so far.

How do I install Agent Builder?

Run "/install agent-builder" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Agent Builder free?

Yes, Agent Builder is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Agent Builder support?

Agent Builder is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Agent Builder?

It is built and maintained by Pedro Gonzalez (@plgonzalezrx8); the current version is v1.0.0.

💬 Comments