ralph

Iteratively execute tasks until all user stories are verified true.

Updated May 31, 2026
One-click install
npx skills add https://github.com/Ewallyw/claude-config-public --skill ralph-ewallyw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph
Source: https://github.com/Ewallyw/claude-config-public/tree/main/claude-config-master/claude-config-master/skills/ralph
Command: npx skills add https://github.com/Ewallyw/claude-config-public --skill ralph-ewallyw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a persistent loop that ensures task completion, with configurable verification steps, for thorough execution and quality assurance.

Core Features & Use Cases

  • Task Persistence: Continuously works on tasks until all user stories are verified.
  • Verification Options: Allows selection of a reviewer for verification tasks.
  • Use Case: Ideal for complex projects where task completion and thorough verification are crucial, such as large-scale software development or complex report writing.

Quick Start

Start Ralph for a task by saying "ralph [task description]".

Frequently Asked Questions about ralph

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I ensure task completion for complex software development with verification?

PRD-driven task completion uses structured execution to break down project requirements into verifiable user stories. The mechanism works by continuously processing tasks within a persistent loop until every story passes verification.

Can I configure a specific reviewer for verification tasks during software development?

Yes, you can configure verification options for software development tasks. This allows you to select a specific reviewer to handle the verification steps, ensuring quality assurance meets your project's mandatory review requirements.

How do I start a PRD-driven execution loop for my project?

To start a PRD-driven execution loop, initiate the process by providing a task description. The system will then continuously work on the task, processing iteratively until all defined user stories are verified true.

What is the best way to handle persistent iteration for large-scale software tasks?

The best way to handle persistent iteration for large-scale software tasks is to use a structured execution loop with configurable verification. This ensures continuous task progression until all project user stories are verified complete.

Does PRD-driven task execution work for complex report writing?

Yes, PRD-driven task execution works for complex report writing. It provides a persistent loop that continuously works on tasks, ensuring thorough execution and quality assurance through mandatory verification steps until completion.