ralplan

Orchestrate iterative planning with Planner, Architect, and Critic to reach consensus.

2|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/chanhee-kang/oh-my-gemini --skill ralplan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralplan
Source: https://github.com/chanhee-kang/oh-my-gemini/tree/main/skills/ralplan
Command: npx skills add https://github.com/chanhee-kang/oh-my-gemini --skill ralplan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ralplan provides orchestrated iterative planning by coordinating Planner, Architect, and Critic to reach a consensus on a comprehensive work plan.

Core Features & Use Cases

  • Iterative consensus planning across Planner, Architect, and Critic to refine a plan.
  • Invokes the base plan skill in consensus mode to drive architecture decisions and critiques.
  • Stops after a maximum of five iterations or when Critic approves.
  • Ideal for system design, project scoping, and complex task decomposition.

Quick Start

Use the ralplan skill to trigger consensus planning. Example: /oh-my-gemini:ralplan [task]

Frequently Asked Questions about ralplan

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

FAQPage Schema
How do I use multi-agent iteration to reach consensus on a system design plan?

Iterative consensus planning coordinates Planner, Architect, and Critic agents to refine a comprehensive work plan through repeated feedback cycles. It drives architecture decisions and stops when the Critic approves or after a maximum of five iterations.

What is the best way to handle complex task decomposition for feature roadmaps?

Complex task decomposition is handled by applying iterative consensus planning across Planner, Architect, and Critic agents. This mechanism uses critique cycles to refine architecture decisions and project scoping until a comprehensive work plan is reached.

How do I trigger consensus mode for project scoping and architecture decisions?

You trigger consensus mode by invoking the skill with your specific task. This orchestrates the base plan skill in consensus mode, coordinating Planner, Architect, and Critic agents to drive architecture decisions and repeated agent feedback up to five iterations.

How many iterations does the planning cycle run before stopping?

The planning cycle runs a maximum of five iterations before stopping. It terminates earlier if the Critic agent approves the comprehensive work plan generated by the Planner and Architect during the iterative consensus cycle.

Do I need any specific dependencies to run multi-agent iterative planning?

You do not need specific dependencies to run multi-agent iterative planning as it operates with no external requirements. It autonomously orchestrates the Planner, Architect, and Critic agents to reach consensus on your architecture decisions and project scoping.