create-hat-collection
Generates new Ralph hat collection presets through guided conversation. Asks clarifying questions, validates against schema constraints, and outputs production-ready YAML files.
Why use this skill?
Efficiently generate production-ready YAML presets for OpenClaw agents. Get guided assistance for designing multi-agent workflows and event-driven architectures.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/paulpete/create-hat-collectionWhat This Skill Does
The create-hat-collection skill is a powerful architectural assistant designed to streamline the creation of multi-agent workflows within the OpenClaw environment. Rather than manually writing complex YAML configurations, this skill acts as a bridge between your high-level conceptual vision and production-ready code. It follows a structured, three-phase guided conversation to ensure your agents are defined with precision. The skill clarifies your project purpose, maps out complex event flows, validates your architecture against critical schema constraints, and ultimately outputs a fully formatted, valid YAML preset file directly into your presets/ directory. By enforcing standard design patterns like Critic-Actor or Supervisor-Worker, it prevents common architectural pitfalls and ensures your agent swarm is robust and maintainable.
Installation
To begin building your own custom hat collections, run the following command in your terminal:
clawhub install openclaw/skills/skills/paulpete/create-hat-collection
Use Cases
This skill is perfect for developers building autonomous agent swarms. Key scenarios include:
- Rapid prototyping of complex linear pipelines (A to B to C workflows).
- Designing sophisticated "Scientific" debugging workflows that require iterative hypothesis testing and failure recovery.
- Constructing Supervisor-Worker models where a central orchestrator delegates tasks to specialized agents.
- Standardizing team-wide agent behaviors by converting ad-hoc ideas into repeatable YAML templates.
Example Prompts
- "I want to build a code review workflow where an Agent A writes code, Agent B critiques it, and Agent C rewrites it based on the feedback. Can you help me set up the hat collection?"
- "Let's create a new preset for a research assistant that starts with a search agent, moves to a summarization agent, and finally outputs to a file-writer agent. Let's use the pipeline pattern."
- "I need a supervisor hat that distributes tasks to three specific workers. Can you walk me through the design process and generate the YAML for me?"
Tips & Limitations
- Validate early: The skill includes strict schema validation. Pay close attention to the triggers and publishes lists to avoid ambiguous routing errors.
- Naming Conventions: Ensure your hat names and keys are descriptive; these become the identity of your agents at runtime.
- Constraints: Remember that
task.startandtask.resumeare reserved events—do not attempt to define these as custom triggers in your workflow. - Scope: This skill is strictly for creating new presets. If you need to edit an existing YAML file, please refer to the documentation for manual configuration updates or alternative editing tools.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-paulpete-create-hat-collection": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write
Related Skills
playwriter
Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.
code-task-generator
Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.
release-bump
Use when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish
evaluate-presets
Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.
tmux-terminal
Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.