‹ 首页

refinement-loop

@lexler · 收录于 昨天 · 上游提交 1 周前

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.

适合你,如果常需要反复推敲才能达到期望效果。

/ 通过 npx 安装 校验哈希
npx oh-my-skill add lexler/skill-factory/refinement-loop
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- lexler/skill-factory/refinement-loop
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify lexler/skill-factory/refinement-loop
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
223GitHub stars
~631上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 2eae60e · 表述以原文为准
它做什么

当你要改进一篇文章、代码或想法时,Claude会反复迭代:先写出初稿,然后多次阅读、批评、重写,直到彻底完善。每次保存新版本到文件,最后展示优化结果和迭代次数。

什么时候触发

当你明确要求“冥想”、“蒸馏”、“优化”或“迭代”某个内容时触发;或者当问题明显需要多轮改进时,Claude也会主动启用。

装好后可以这样说
Claude会启动迭代循环,反复改进。
Claude会逐步提炼,输出精简版本。
Claude会执行穷尽检查后停止。
技能原文 SKILL.md作者撰写 · Apache-2.0 · 2eae60e

Refinement Loop

STARTER_CHARACTER = 🔄

Iterative refinement through file artifacts. Each pass removes one layer of noise, revealing the next.

Setup

Ensure playground/ exists and is in .gitignore. All iteration files go there.

Process
1. Clarify Goal (if the user hasn't defined it for you already earlier in the conversation)

Ask the user:

  • What are you refining and what is the goal of refinement?
  • Derive a short tag that we'll use as filename for iterating: {goal}-{subject} (e.g., gist-nullables, simplify-api, distill-auth-docs)
2. Capture Starting Point

Write original to: playground/{goal}-{subject}-0.md

3. Iterate

Loop:

  1. Read back the current file (forces fresh perspective)
  2. Reflect critically: What's missing? What's weak? What could be clearer?
  3. If improvements found: Write improved version to playground/{goal}-{subject}-{N+1}.md, then loop again
Before Stopping - Exhaustive Check

When you think you're done, you're probably not. Run through this:

  1. List everything that could still be improved - even small things (formatting, word choice, structure, clarity)
  2. Consider what we haven't considered - what angles did we miss? What would someone else notice?
  3. Try improving in a new direction - not just polishing what's there, but questioning assumptions
  4. Read as if seeing it for the first time - does it immediately make sense? Is anything unclear?

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.

4. Present Final

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.

Principles
  • Read back forces fresh eyes: Reading from file breaks the "I just wrote this" blindness
  • No "good enough": Every detail matters. Formatting, word choice, structure - all of it
  • Consider the unconsidered: What angles haven't we explored? What would someone else see? Is there something that the user hasn't even considered, too? (you can surface it as questions at the end)
  • Files force iterative improvement: Writing to files prevents "pretend" iteration in conversation. Real iteration gets to much better results.
  • Earn the stop: Run the exhaustive check. If you find nothing, you've earned stopping.
按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。