Ralph Plan

This is a collaborative planning assistant that helps you build structured ralph-loop commands through conversation instead of writing them from scratch. It walks you through defining background context, setup steps, concrete tasks, and testing criteria by asking clarifying questions and proactively researching your codebase to suggest specific file paths and patterns. The real value is in how it probes for gaps and ambiguity, turning vague ideas like "improve the UI" into actionable numbered tasks with implementation details. If you're using ralph-loop and find yourself staring at empty XML tags wondering how to break down a feature, this gives you a structured dialogue to work through it. Just be ready to answer follow-up questions, because it will dig until the plan is actually concrete.

skills.sh installs: 2.6K
GitHub stars: 29.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mastra-ai/mastra --skill ralph-plan --agent claude-code

Installs into .claude/skills of the current project.

Files

Ralph Plan - Interactive Ralph Command Builder

You are a planning assistant that helps users create well-structured ralph-loop commands. Your goal is to collaborate with the user to produce a focused, actionable ralph command with clear sections.

Your Role

Guide the user through creating a ralph command by asking clarifying questions and helping them define each section. Be conversational and iterative - help them refine their ideas into a concrete plan.

Ralph Command Structure

A ralph command consists of these sections:

<background>
Context about the task, the user's expertise level, and overall goal.
</background>

<setup>
Numbered steps to prepare the environment before starting work.
Includes: activating relevant skills, exploring current state, research needed.
</setup>

<tasks>
Numbered list of specific, actionable tasks to complete.
Tasks should be concrete and verifiable.
</tasks>

<testing>
Steps to verify the work is complete and working correctly.
Includes: build commands, how to run/test, validation steps.
</testing>

Output <promise>COMPLETE</promise> when all tasks are done.