evaluator-optimizer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Evaluator-Optimizer

Iterative refinement workflow that takes existing code, documentation, or designs and polishes them through rigorous cycles of evaluation and improvement until they meet production-grade quality standards.

通过严格的评估与改进循环，对现有代码、文档或设计进行打磨，直至达到生产级质量标准的迭代优化工作流。

When to Use This Skill

何时使用该技能

Refining a rough draft of code into production quality
Polishing documentation for clarity, completeness, and accuracy
Iteratively improving a design or architecture proposal
Systematic quality improvement where "good enough" is not sufficient
When you need to converge on high quality through structured iteration

将代码草稿完善至生产质量
打磨文档以提升清晰度、完整性与准确性
迭代改进设计或架构提案
对质量要求较高，“足够好”无法满足需求的系统性质量提升场景
需要通过结构化迭代逐步实现高质量成果时

Quick Reference

快速参考

Task	Load reference
Evaluation criteria and quality rubrics	`skills/evaluator-optimizer/references/evaluation-criteria.md`

任务	参考资料路径
评估标准与质量准则	`skills/evaluator-optimizer/references/evaluation-criteria.md`

Workflow: The Loop

工作流：循环机制

For any given artifact (code, text, design):

Accept: Take the current version of the artifact.
Evaluate: Act as a harsh critic. Rate the artifact on correctness, clarity, efficiency, style, and safety. Assign a score out of 100.
Decide:
- Score >= 90: Stop and present the result.
- Score < 90: Refine.
Refine: Rewrite the artifact, specifically addressing the critique from step 2. List what changed and why.
Repeat: Return to step 2 with the new version.

针对任意工件（代码、文本、设计）：

接收：获取工件的当前版本。
评估：以严苛的视角进行评判。从正确性、清晰度、效率、风格与安全性五个维度为工件评分，满分100分。
决策：
- 评分≥90：停止并呈现结果。
- 评分<90：优化。
优化：重写工件，针对性解决步骤2中提出的问题。列出具体修改内容及原因。
重复：使用新版本回到步骤2。

Behavioral Rules

行为规则

Do not settle: "Good enough" is not good enough. You are here to polish.
Be explicit: When evaluating, list specific flaws. "The function
```
process_data
```
is O(n^2) but could be O(n)."
Show your work: Summarize changes in each iteration.
Self-correct: If a refinement breaks something, revert and try a different approach.
Converge: Each iteration must improve the score. If two consecutive iterations do not improve the score, stop and present the best version.

绝不妥协：“足够好”是远远不够的，你的目标是精益求精。
表述明确：评估时需列出具体问题，例如“函数
```
process_data
```
的时间复杂度为O(n²)，可优化至O(n)。”
展示过程：总结每次迭代中的修改内容。
自我修正：若某次优化引入问题，需回退并尝试其他方案。
逐步收敛：每次迭代必须提升评分。若连续两次迭代评分未提升，停止并呈现最优版本。

Iteration Output Template

迭代输出模板

markdown

undefined

markdown

undefined

Iteration [N] Evaluation

第[N]次迭代评估

Criterion	Score (1-10)	Notes
Correctness
Clarity
Efficiency
Style
Safety
Total	/50	[x100/50]

评估维度	得分（1-10）	备注
正确性
清晰度
效率
风格
安全性
总分	/50	[x100/50]

Issues Found

发现的问题

[Specific issue with location]
[Specific issue with location]

[具体问题及位置]
[具体问题及位置]

Refinements Applied

已应用的优化

[Change 1 and rationale]
[Change 2 and rationale]

undefined

[修改内容1及理由]
[修改内容2及理由]

undefined

Example Interaction

示例交互

Input: "Refine this Python script."

Iteration 1 Evaluation:

Functionality: Good
Efficiency: Poor - uses nested loops for matching
Style: Variable names
```
a
```
and
```
b
```
are unclear
Score: 60/100

Refinements applied:

Flattened loops using a set lookup (O(n))
Renamed
```
a
```
to
```
users
```
,
```
b
```
to
```
active_ids
```
Added type hints

Iteration 2 Evaluation:

Functionality: Good
Efficiency: Excellent
Style: Good
Score: 95/100

Result: Present the refined script.

输入：“优化这段Python脚本。”

第1次迭代评估：

功能：良好
效率：较差 - 使用嵌套循环进行匹配
风格：变量名
```
a
```
和
```
b
```
含义模糊
评分：60/100

已应用的优化：

使用集合查找（O(n)）替代嵌套循环
将
```
a
```
重命名为
```
users
```
，
```
b
```
重命名为
```
active_ids
```
添加类型提示

第2次迭代评估：

功能：良好
效率：优秀
风格：良好
评分：95/100

结果：呈现优化后的脚本。