MCPInstall

openclaw-agent-builder

by irangareddy

Build specialized openclaw agents with proper workspace structure, identity, and skills

Installs
93
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/irangareddy/openclaw-essentials --skill openclaw-agent-builder
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads openclaw-agent-builder automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

OpenClaw Agent Builder

Create specialized openclaw agents with complete workspace structure, identity files, and skills.

When to Use

When building a new openclaw agent for a specific purpose:

  • Domain-specific agents (Android dev, SEO, content writing, etc.)
  • Multi-agent routing scenarios
  • Isolated agent personalities
  • Workspace-based AI assistants

Core Concepts

OpenClaw Agent Structure

Each agent = isolated brain with:

  • Workspace: Files (AGENTS.md, SOUL.md, USER.md, IDENTITY.md, TOOLS.md, etc.)
  • State dir: ~/.openclaw/agents/<agentId>/agent (auth, config)
  • Sessions: ~/.openclaw/agents/<agentId>/sessions (chat history)

Workspace Files

Required:

  • AGENTS.md - Operating instructions, memory management, behavior rules
  • SOUL.md - Persona, tone, communication style
  • USER.md - User context and how to address them
  • IDENTITY.md - Agent name, emoji, role, mission
  • TOOLS.md - Tool notes and conventions

Optional:

  • HEARTBEAT.md - Heartbeat checklist (keep short)
  • BOOT.md - Startup checklist when gateway restarts
  • memory/ - Daily memory logs (YYYY-MM-DD.md)
  • MEMORY.md - Curated long-term memory
  • skills/ - Workspace-specific skills

Agent Builder Workflow

1. Ask Questions First

Before building, clarify:

  • Agent purpose: What problem does this agent solve?
  • Domain expertise: What specialized knowledge needed?
  • Communication style: Professional? Casual? Technical?
  • Tools/integrations: APIs, databases, external systems?
  • Skills needed: Custom capabilities or workflows?

2. Create Workspace Structure

# Create agent workspace
mkdir -p ~/.openclaw/workspace-<agent-name>
cd ~/.openclaw/workspace-<agent-name>

# Initialize git (recommended)
git init

3. Build Core Files

IDENTITY.md - Who the agent is:

# IDENTITY.md

## Name
[Agent Name]

## Emoji
[1-2 relevant emojis]

## Role
[Short role description - e.g., "Android spec writer", "SEO optimizer"]

## Mission
[Concise mission statement - what the agent does and why]

SOUL.md - Personality and tone:

# SOUL.md - [Agent Name]

## Who You Are

[Description of expertise, background, strengths]

## Your Expertise

### [Domain 1]
- [Specific skill or knowledge area]
- [Another capability]

### [Domain 2]
- [Capability]

## Your Approach

### [Trait 1 - e.g., Analytical, Pragmatic]
- [How this manifests]

### [Trait 2]
- [Behavior pattern]

## Your Tone

[Communication style - concise/verbose, formal/casual, technical level]

## Your Values

1. **[Value 1]** - [Why it matters]
2. **[Value 2]** - [Explanation]

AGENTS.md - Operating instructions:

# AGENTS.md - [Agent Name]

[Brief agent description and primary role]

## Primary Responsibilities

1. **[Task 1]** - [Description]
2. **[Task 2]** - [Description]

## Workflow

### On User Request: "[Trigger Pattern]"

1. **[Step 1]** [Action description]
   [Details, commands, or sub-steps]

2. **[Step 2]** [Next action]

### On User Request: "[Another Pattern]"

[Workflow steps]

## [Domain-Specific Section - e.g., "iOS Codebase Structure"]

[Relevant context, file paths, patterns]

## [Another Section - e.g., "Translation Guidelines"]

[Reference tables, mappings, rules]

## Memory

- Log [what to track] in `memory/YYYY-MM-DD.md`
- [Memory strategy specific to agent purpose]

## Tools

See `TOOLS.md` for [domain-specific tools or integrations]

## Skills

- **[skill-name]** - [Purpose]
- **[another-skill]** - [Purpose]

USER.md - User context:

# USER.md

## Who You Are

[User description, preferences, context]

## Your Goals

[What user wants to achieve with this agent]

## Communication Preferences

[How user prefers to interact]

TOOLS.md - Tool conventions:

# TOOLS.md

## [Domain] Tools

- **[Tool/API name]**: [Purpose and usage notes]
- **[Another tool]**: [Notes]

## Authentication

[If agent needs API keys, credentials, etc.]

## Conventions

[Domain-specific conventions or patterns]

4. Add Skills (Optional)

Create workspace-specific skills:

mkdir -p skills/<skill-name>

Each skill needs SKILL.md:

---
name: skill-name
description: What the skill does
---

# Skill Name

[Skill documentation following agentskills.io format]

## When to Use

[Trigger conditions]

## Steps

[Detailed workflow]

## Examples

[Usage examples]

5. Setup Memory System

mkdir -p memory
touch memory/$(date +%Y-%m-%d).md

Optional MEMORY.md for curated knowledge:

# MEMORY.md

## [Category]

- [Key fact or pattern]
- [Lesson learned]

## [Another Category]

[Organized knowledge]

6. Register Agent

# Add agent to openclaw
openclaw agents add <agent-name>

# Set workspace path
# Edit ~/.openclaw/openclaw.json:
{
  "agents": {
    "list": [
      {
        "id": "<agent-name>",
        "workspace": "~/.openclaw/workspace-<agent-name>"
      }
    ]
  }
}

7. Add Bindings (Multi-Agent Routing)

Route specific channels/users to this agent:

{
  "bindings": [
    {
      "agentId": "<agent-name>",
      "match": {
        "channel": "whatsapp",
        "peer": { "kind": "direct", "id": "+1234567890" }
      }
    }
  ]
}

Design Principles

Agent Identity

  • Clear purpose: Single, focused responsibility
  • Distinct personality: Unique tone/approach vs other agents
  • Expertise depth: Deep knowledge in specific domain

Communication Style

  • Concise: Default to brevity unless domain requires detail
  • Professional: Match industry standards
  • Actionable: Focus on what to do, not just description

Memory Strategy

  • Daily logs: Track important events/decisions
  • Curated knowledge: Extract patterns into MEMORY.md
  • Context preservation: Save state before /new or /reset

Skill Organization

  • Workspace skills: Agent-specific capabilities
  • Shared skills: Common utilities in ~/.openclaw/skills/
  • Override pattern: Workspace skills override shared/bundled

Example Agents

Android Spec Generator

Purpose: Analyze iOS features, generate Android requirement specs
Style: Concise, technical, requirement-focused
Skills: ios-analyzer, android-spec-generator, github-issue-creator

SEO Expert

Purpose: Content optimization, keyword research, SEO strategy
Style: Data-driven, analytical, actionable
Skills: keyword-research, content-analyzer, competitor-analysis

Content Writer

Purpose: Blog posts, documentation, technical writing
Style: Clear, engaging, audience-aware
Skills: content-planner, seo-writer, editor

Anti-Patterns

❌ Don't:

  • Mix multiple unrelated domains in one agent
  • Create verbose, chatty agents unless purpose requires it
  • Duplicate content across AGENTS.md, SOUL.md, TOOLS.md
  • Store secrets in workspace (use ~/.openclaw/credentials/)

✅ Do:

  • Keep single, clear focus per agent
  • Match communication style to domain norms
  • Organize by responsibility (identity/soul/operations)
  • Use git for workspace backup (private repo)

Testing Agent

# Start gateway with agent
openclaw gateway --agent <agent-name>

# Or use binding to route to agent
openclaw gateway

# Send test message via WhatsApp/Telegram/Discord
# Verify agent responds with expected personality/capability

Maintenance

Update Agent

cd ~/.openclaw/workspace-<agent-name>
git add .
git commit -m "Update [what changed]"
git push

Add New Skill

cd ~/.openclaw/workspace-<agent-name>/skills
mkdir new-skill
# Create SKILL.md

Backup Agent

# Workspace already in git
# Separately backup sessions if needed:
tar -czf sessions-backup.tar.gz ~/.openclaw/agents/<agent-name>/sessions/

Resources

Questions Before Building?

Ask user to clarify:

  1. Agent purpose and scope
  2. Communication style preferences
  3. Required integrations/APIs
  4. Routing strategy (dedicated channel vs shared)
  5. Skill requirements

FAQ

What does the openclaw-agent-builder skill do?

Build specialized openclaw agents with proper workspace structure, identity, and skills

How do I install openclaw-agent-builder?

Run npx skills add https://github.com/irangareddy/openclaw-essentials --skill openclaw-agent-builder in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/openclaw-agent-builder/ (personal) or .claude/skills/openclaw-agent-builder/ (project).

Which AI agents can use openclaw-agent-builder?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is openclaw-agent-builder safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains openclaw-agent-builder?

It is published by irangareddy in irangareddy/openclaw-essentials. It has 93 recorded installs.

More from irangareddy/openclaw-essentials

View all →

openclaw-cli

irangareddy/openclaw-essentials

Master the OpenClaw CLI - gateway, agents, channels, skills, hooks, and automation

Productivity & Automation485 installs

memory-curator

irangareddy/openclaw-essentials

Manage agent memory through daily logs, session preservation, and knowledge extraction. Use when (1) logging work at end of day, (2) preserving context before /new or /reset, (3) extracting patterns from daily logs to MEMORY.md, (4) searching past decisions and learnings, (5) organizing knowledge for long-term retention. Essential for continuous improvement and avoiding repeated mistakes.

DevOps & Cloud205 installs

Popular other skills

View category →

hyperframes-cli

heygen-com/hyperframes

The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.

1.3M installs

triage

mattpocock/skills

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

1M installs

ask-matt

mattpocock/skills

Ask which skill or flow fits your situation. A router over the skills in this repo.

778.4K installs

to-questionnaire

mattpocock/skills

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

508.9K installs

wait-what

mattpocock/skills

Stop. That last message did not land: re-pitch it.

459.7K installs

loop-me

mattpocock/skills

Grill me about specs for the workflows I want to build, within this workspace.

447.9K installs