Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Guides users through creating Ralph hat collection preset files via structured conversation. Asks questions about workflow purpose, agent roles, and event routing, then validates the design against schema constraints before writing a production-ready YAML file to the presets/ directory.
The guided conversation catches schema violations and routing ambiguities before you run the preset, avoiding trial-and-error YAML editing.
When to use it
- Building a multi-agent code review workflow from scratch
- Converting a workflow idea into a structured Ralph preset
- Designing a pipeline for sequential document processing agents
- Setting up a supervisor-worker agent coordination pattern
- Creating a scientific-method debugging workflow with event routing
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: I want a preset for a security-focused code review with an analyst, reviewer, and summarizer.
- 1Asks clarifying questions about review depth, roles, and whether issues should be fixed or just reported
- 2Maps the workflow as an event chain: task.start → Security Analyst → security.complete → Code Reviewer → review.complete → Summarizer → LOOP_COMPLETE
- 3Validates that each trigger maps to exactly one hat and no reserved events are used as triggers
- 4Generates a YAML file with three hats, each with name, description, triggers, publishes, and instructions fields
- 5Saves the completed file to presets/security-code-review.yml
A complete presets/security-code-review.yml file with three configured hats and validated event routing