kimchi:refine

What problem does it solve?

This Skill addresses the challenge of refining AI-generated plans to meet quality thresholds, ensuring they are complete, clear, testable, independent, and appropriately sized before execution.

Core Features & Use Cases

• Automated Plan Evaluation: Scores plans based on five key criteria (Completeness, Clarity, Testability, Independence, Size).
• Iterative Improvement: Automatically applies targeted fixes to the lowest-scoring criteria in a loop.
• Exit Condition Management: Stops refinement when a quality threshold is met, diminishing returns are observed, a regression occurs, or maximum loops are reached.
• Use Case: After an initial plan is generated, use this Skill to automatically polish it, ensuring it's robust and actionable for multi-agent execution.

Quick Start

Use the kimchi:refine skill to improve the plan, allowing up to 5 refinement loops.