ralph

Persistently execute tasks with mandatory architect verification and parallel agent calls.

6|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/Weihong-Liu/GenericAgent_project --skill ralph-weihong-liu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph
Source: https://github.com/Weihong-Liu/GenericAgent_project/tree/main/.codex/skills/ralph
Command: npx skills add https://github.com/Weihong-Liu/GenericAgent_project --skill ralph-weihong-liu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Ralph Skill addresses the challenge of ensuring tasks are fully completed and architect-verified, providing persistence across retries and parallel execution with mandatory verification.

Core Features & Use Cases

  • Task Persistence: Continuously works on a task until it is fully complete.
  • Parallel Execution: Executes independent agent calls simultaneously.
  • Verification: Requires fresh verification evidence before allowing completion.
  • Use Case: Ideal for complex tasks that require repeated work and verification, such as software development, where every aspect must be confirmed by an architect.

Quick Start

Use the ralph skill to ensure a task is fully completed and architect-verified.

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 with mandatory verification in complex software development?

Parallel execution in task completion allows independent agent calls to run simultaneously while maintaining persistence across retries. This mechanism ensures complex tasks continuously work until fully complete, with mandatory architect verification required before finalizing any results.

What is the best way to manage persistent task completion across automatic retries?

Session persistence in iterative task workflows allows tasks to continuously resume across retries until fully complete. This mechanism maintains state across failures, enabling parallel execution and mandatory architect verification to confirm every aspect is thoroughly completed.

Does parallel execution support independent agent calls with architect review?

Yes, parallel execution supports independent agent calls with architect review by running them simultaneously while requiring fresh verification evidence before allowing completion. This approach is specifically designed for complex tasks needing iterative work and strict architectural confirmation.

When do I need iterative task verification and loop until done mechanisms?

You need iterative task verification and loop until done mechanisms for complex tasks requiring repeated work and review, such as software development. These mechanisms ensure every aspect is confirmed by an architect through persistent task completion and mandatory verification evidence.

Can I use session persistence for complex tasks requiring repeated work and verification?

Yes, you can use session persistence for complex tasks requiring repeated work and verification. It enables persistent task completion with automatic retries, allowing tasks to continuously work until fully complete and architect-verified with fresh verification evidence.