ralph

Iterate over PRD user stories with parallel agent calls until reviewer verification passes.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/Jurel89/copilot-omni --skill ralph-jurel89
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph
Source: https://github.com/Jurel89/copilot-omni/tree/main/skills/ralph
Command: npx skills add https://github.com/Jurel89/copilot-omni --skill ralph-jurel89

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Ralph addresses the issue of incomplete implementations and ensures tasks are fully completed and verified by reviewers.

Core Features & Use Cases

  • PRD-Driven Persistence: Continues work until all user stories in prd.json are passed and reviewed.
  • Parallel Execution: Simultaneously processes multiple stories for faster completion.
  • Structured Tracking: Tracks progress across iterations with detailed progress files.
  • Reviewer Verification: Mandates review by specified personnel before task completion.
  • Use Case: Ideal for complex tasks that require persistent execution and thorough review.

Quick Start

Activate the ralph skill with the description of your task to start the persistent execution and reviewer verification process.

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 implementations using PRD-driven iteration?

PRD-driven persistence ensures task completion by automating an iteration loop that continuously processes user stories from prd.json until all tasks are successfully executed and verified. It mandates reviewer verification before task completion is confirmed.

Can I execute multiple user stories in parallel for faster task completion?

Yes, parallel execution simultaneously processes multiple user stories to accelerate task completion. This approach utilizes parallel agent calls to handle task-specific stories concurrently while maintaining structured tracking across iterations.

What is reviewer verification and how does it work with iteration tracking?

Reviewer verification mandates specified personnel to review and pass user stories before task completion is confirmed. Iteration tracking monitors this process by generating detailed progress files that track story status across each execution loop.

Do I need a structured PRD input format to use persistent execution loops?

Yes, a structured PRD input in the form of prd.json is required. The persistence loop depends on structured user stories defined in this file to drive parallel execution, iteration tracking, and subsequent reviewer verification.

What's the best way to track progress across parallel agent calls?

Structured tracking monitors progress across iterations by generating detailed progress files. This mechanism records the execution status of parallel agent calls, ensuring each user story is accounted for until reviewer verification is passed.