OpenClaw Templates: Build Your Agent Fast

OpenClaw runs on markdown files. No dashboards. No drag-and-drop builders. Just a handful of .md files that tell your agent who it is, what it knows, and how it should behave. These files are your templates. Get them right, and you have a personal AI employee. Get them wrong, and you have a confused chatbot.

I run 13 agents on a single Mac Mini. Every one of them started from a template. Here is exactly which files you need, what goes in each one, and where to find ready-made templates you can copy-paste today.

The 7 Workspace Files Every OpenClaw Agent Needs

When you install OpenClaw, it creates a workspace folder at ~/.openclaw/workspace/. This is home base. Everything your agent knows lives here in plain markdown files.

Here are the core files:

The beauty of this approach: everything is version-controllable. You can git commit your entire agent setup, share it with your team, or roll back to yesterday's version if something breaks.

SOUL.md: Your Agent's Personality Template

SOUL.md is the most important file. It defines who your agent is. Not what it does. Who it is.

A good SOUL.md covers four things:

1. Core truths. How the agent should think and act. "Be genuinely helpful, not performatively helpful." "Have opinions." "Be resourceful before asking."
2. Boundaries. What it should never do. Private things stay private. No half-baked replies. No pretending to be you in group chats.
3. Writing rules. Specific style constraints. No em dashes. Short paragraphs. Real numbers.
4. Vibe. The overall feel. "Be the assistant you'd actually want to talk to."

Here is a minimal SOUL.md you can start with:

# SOUL.md - Who You Are

## Core Truths
- Be helpful. Skip the "Great question!" filler.
- Have opinions. Disagree when it matters.
- Try to figure things out before asking.
- Earn trust through competence.

## Boundaries
- Private things stay private.
- Ask before sending emails, tweets, or public posts.
- Never send half-baked replies.

## Vibe
Concise when needed. Thorough when it matters.
Not a corporate drone. Not a sycophant. Just good.

SOUL.md Deep Dive: What Actually Makes a Difference

After running agents for months, here is what separates a good SOUL.md from a great one:

Specific negatives beat vague positives. "Don't say 'Great question!'" is more useful than "Be authentic." Your agent encounters thousands of moments where it could add filler. Specific prohibitions catch the worst offenses. Vague aspirations do nothing.

Writing rules matter more than personality rules. Your agent's tone comes mostly from how it writes, not from how you describe its vibe. Rules like "Use periods instead of em dashes" and "Keep paragraphs under 3 sentences" do more heavy lifting than "Be witty and concise."

Boundary examples prevent disasters. Instead of "be careful with external actions," specify exactly what needs permission: "Never send an email without showing me the draft first. Never post to X without my approval. Reading files and searching the web is always fine."

Add rules reactively, not proactively. Start with 5 rules. Every time your agent does something wrong, add a rule. After a month, you will have 15-20 battle-tested rules that address real problems. Pre-writing 50 rules on day one leads to bloat and contradictions.

Here is an example of a more evolved SOUL.md section from a real production setup:

## Writing Rules
- NEVER use em dashes. Use periods, colons, commas instead.
- Short paragraphs. 3 sentences max per paragraph.
- No "Great question!" or "I'd be happy to help!" filler.
- When writing as me (tweets, outreach): match my voice exactly.
- No AI cliches: "dive into", "leverage", "streamline", "game-changer".
- Use concrete numbers over vague descriptions.
- If you don't have real data, say so. Don't fabricate stats.

AGENTS.md: The Operating Manual

If SOUL.md is who your agent is, AGENTS.md is how it operates. Think of it as the employee handbook.

A solid AGENTS.md template covers:

• Session startup sequence. Which files to read, in what order. SOUL.md first, then USER.md, then daily memory files.
• Memory system. How to use daily notes (memory/YYYY-MM-DD.md) vs long-term memory (MEMORY.md). When to write things down. When to archive.
• Safety rules. No destructive commands without asking. Use trash instead of rm. When in doubt, ask.
• External vs internal actions. What the agent can do freely (read files, search the web) vs what needs permission (sending emails, posting publicly).
• Group chat behavior. When to speak. When to stay silent. How to react.

The official AGENTS.md template from OpenClaw docs is solid. I took it, then added my own rules over time: specific SOPs for each agent, a meta-learning architecture with regression tracking, and a "write it down immediately" hard rule because compaction summaries lose details.

You do not need all of that on day one. Start with the official template. Add rules as you learn what your agent gets wrong.

USER.md Deep Dive: The Context File Most People Skip

USER.md is the most underrated file in the OpenClaw workspace. It tells your agent who you are. Without it, your agent starts every conversation from zero context.

A good USER.md includes:

• Basics: Name, timezone, pronouns, location. Your agent needs this for scheduling, weather, and local context.
• Work context: What you do, what you are building, your current projects, your goals. This prevents the agent from giving generic advice.
• Communication style: Do you prefer bullet points or paragraphs? Detailed explanations or just the answer? Quick Telegram messages or formatted reports?
• Current priorities: What are you working on this quarter? What are your top 3 goals? This helps the agent prioritize tasks and suggestions.
• Personal details (optional): Hobbies, preferences, dietary restrictions, travel plans. The more context your agent has, the more relevant its suggestions become.

Here is a minimal USER.md template you can start with:

# USER.md - About Me
- **Name:** [Your name]
- **Timezone:** [Your timezone]
- **What I do:** [One sentence about your work]
- **Current project:** [What you are focused on right now]
- **Communication style:** Direct, concise. Prefer bullet points.
- **Top priority this month:** [One clear goal]

Update this file every month or when your priorities shift. An outdated USER.md is worse than no USER.md because it gives your agent wrong context.

SKILL.md: Teaching Your Agent New Tools

Skills are how you extend what your agent can do. Each skill is a folder with a SKILL.md file inside it. The file has two parts: YAML frontmatter for metadata, and markdown instructions below.

Here is the basic structure:

---
name: my-custom-skill
description: What this skill does in one sentence.
version: 1.0.0
---

# My Custom Skill

## When to Use
Describe the trigger conditions.

## How to Use
Step-by-step instructions for the agent.

## Examples
Concrete examples of inputs and outputs.

Skills live in two places:

• ~/.openclaw/skills/ for global skills (available to all agents)
• ~/.openclaw/workspace/skills/ for workspace-specific skills

OpenClaw automatically detects skills by scanning for SKILL.md files. No registration needed. Drop the folder in, restart, and your agent can use it.

You can also install community skills from ClawHub with a single command: clawhub install skill-name. There are over 5,400 skills catalogued in community lists like the awesome-openclaw-skills collection on GitHub.

For a deeper dive on finding and installing skills, check out the OpenClaw Skills Marketplace guide.

65+ Community Templates You Can Copy Right Now

You do not have to start from scratch. The OpenClaw community has built dozens of ready-to-use agent templates.

The best collection right now is awesome-openclaw-agents on GitHub. It has 65 production-ready SOUL.md templates across 13 categories:

• Productivity: Task coordinators, inbox managers, meeting note takers, daily standup collectors
• Development: Code reviewers, documentation generators, PR analyzers
• Marketing & Content: Social media managers, SEO writers, newsletter drafters
• Business: Sales pipeline trackers, competitor analyzers, financial reporters
• Personal: Health trackers, learning assistants, travel planners

Each template is a copy-paste SOUL.md file. Clone the repo, pick an agent, drop the file in your workspace. Done.

I also share my exact agent configurations (all 13 of them) inside OpenClaw Lab. The SOPs, the cron schedules, the skill files. Everything you need to replicate the system.

How to Build Your Own Template From Scratch

Community templates are great starting points. But the best agent is the one built for your specific workflow. Here is how I approach it:

Step 1: Start with USER.md. Tell the agent about yourself. Timezone, communication style, what you are working on, what you care about. The more context here, the less you have to repeat yourself in every conversation.

Step 2: Write a minimal SOUL.md. Three to five core rules. Do not overthink it. You will add more rules as you go. Every time your agent does something wrong, add a rule. That is how good templates evolve.

Step 3: Set up AGENTS.md with the official template. The default template handles session startup, memory, and safety. You can customize later.

Step 4: Add skills as needed. Do not install 50 skills on day one. Start with what you actually use. Gmail skill if you want email access. GitHub skill if you code. Calendar skill if you want scheduling. Add more when you need them.

Step 5: Iterate relentlessly. The template you have after one week will look nothing like the template you have after one month. That is the point. Every correction you give your agent, every rule you add to AGENTS.md, every boundary you set in SOUL.md: that is your template getting sharper.

If you want to get started with OpenClaw from zero, the beginner guide walks through the full install and first agent setup. And if you want to see a multi-agent system in action (13 agents, each with its own template), check the multiple agents setup guide.

Get OpenClaw installed in minutes at installopenclawnow.com.