ralph

Execute iterative tasks with mandatory verification before completion.

6|1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/Goblin1024/oh-my-kimi --skill ralph-goblin1024
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph
Source: https://github.com/Goblin1024/oh-my-kimi/tree/main/skills/ralph
Command: npx skills add https://github.com/Goblin1024/oh-my-kimi --skill ralph-goblin1024

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Handles tasks that require repeated actions until success, ensuring no completion is claimed without verification.

Core Features & Use Cases

  • Persistent iteration loop that re-evaluates progress and repeats work until goals are met.
  • Mandatory verification phase that collects evidence (tests, builds, lint, etc.) before completion.
  • Supports multi-agent orchestration and stateful context to resume after interruptions.

Quick Start

Provide a clear task description and trigger Ralph to begin a persistent execution loop that only completes after successful verification.

Frequently Asked Questions about ralph

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

FAQPage Schema
How do I automate end-to-end task execution with mandatory verification until completion?

Automating end-to-end task execution with mandatory verification requires a persistent execution loop that re-evaluates progress, repeating work and collecting evidence like tests or builds until goals are successfully met.

What is a persistent iteration loop for workflow automation and when do I need it?

A persistent iteration loop is an automation mechanism that continuously repeats actions and progress checks until success. You need it for development or operations tasks where no completion can be claimed without passing verification milestones.

How do I orchestrate parallel task delegation via Agent in an automated workflow?

Orchestrating parallel task delegation via Agent involves using multi-agent automation to distribute work, managing stateful context so workflows can resume after interruptions and enforce verification milestones before completion.

Does multi-agent orchestration support state management to resume workflows after interruptions?

Yes, multi-agent orchestration supports stateful context management to resume after interruptions. It maintains persistent execution loops and state within the OMK context, allowing iterative workflows to continue until verification passes.

What's the best way to enforce verification milestones before task completion in development operations?

The best way to enforce verification milestones is using an automation agent that mandates an evidence collection phase—running tests, builds, and lint checks—before allowing completion, ensuring no unverified work is marked as done.

Why does my automated workflow claim task completion without running verification checks?

Automated workflows claim completion without verification if they lack a persistent execution loop enforcing mandatory evidence gathering. You need an agent that mandates verification milestones, collecting tests and builds before any completion is recognized.