원클릭으로
refinement-loop
// Iterative refinement through multiple passes. Use when the user asks to 'meditate on', 'distill', 'refine', or 'iterate on' something, or proactively when a problem benefits from multiple passes rather than a single attempt.
// Iterative refinement through multiple passes. Use when the user asks to 'meditate on', 'distill', 'refine', or 'iterate on' something, or proactively when a problem benefits from multiple passes rather than a single attempt.
Presents a proposed approach in progressive confirmable chunks with recommended decisions and alternatives. Use when aligning on a design, plan, or technical approach before implementation.
Iterative code refactoring through progressive lenses via a worker-reviewer agent team.
Launches agent teams with structured roles and task decomposition. Use when asked to create a team, spawn teammates, or coordinate multiple agents in parallel.
Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent design, acceptance test, component test, walking skeleton, in-memory fakes, component, contract test, adapter, fast tests, sub-second feedback. Language-agnostic (Go, Rust, Python, TypeScript, Java, C#).
Writes Claude Code status line scripts. Use when creating, customizing, or debugging statusline configurations.
Creates process files - text as code instructions for reliable AI workflows. Use when creating new process files.
| name | refinement-loop |
| description | Iterative refinement through multiple passes. Use when the user asks to 'meditate on', 'distill', 'refine', or 'iterate on' something, or proactively when a problem benefits from multiple passes rather than a single attempt. |
STARTER_CHARACTER = 🔄
Iterative refinement through file artifacts. Each pass removes one layer of noise, revealing the next.
Ensure playground/ exists and is in .gitignore. All iteration files go there.
Ask the user:
{goal}-{subject} (e.g., gist-nullables, simplify-api, distill-auth-docs)Write original to: playground/{goal}-{subject}-0.md
Loop:
playground/{goal}-{subject}-{N+1}.md, then loop againWhen you think you're done, you're probably not. Run through this:
Only stop when you've gone through this checklist extensively multiple times and genuinely found nothing. There is no "good enough" - someone will use this later and shouldn't waste time on mediocre results.
Show the user the final version with a brief summary of the refinement journey and number of iterations you used. If deeper issues or questions surfaced, present them to the user as well.