by softaworks
代码库自然会随着时间累积复杂性,导致更多的错误和维护负担。这个技能提供了一个评估框架,基于每个变更是否能减少最终代码库中的总代码量来评估。
1. 打开 Claude 聊天界面
2. 点击下方 "📋 复制" 按钮
3. 粘贴到 Claude 聊天框中并发送
4. 输入 "使用 reducing-entropy 技能" 开始使用
=== reducing-entropy 技能 === 作者: softaworks 描述: 代码库自然会随着时间累积复杂性,导致更多的错误和维护负担。这个技能提供了一个评估框架,基于每个变更是否能减少最终代码库中的总代码量来评估。 使用方法: 1. 调用技能: "使用 reducing-entropy 技能" 2. 提供相关信息: 根据技能要求提供必要参数 3. 查看结果: 技能会返回处理结果 示例: "使用 reducing-entropy 技能,帮我分析一下这段代码"
这种方法适用于所有 Claude 用户,不需要安装额外工具。
productivity
safe
A manual-only skill for minimizing total codebase size by measuring success through final code amount, not effort. Biases toward deletion and aggressive simplification.
This skill exists to counter the natural tendency of codebases to grow over time. It provides a framework for evaluating changes based on whether they reduce the total amount of code in the final codebase, not just minimize the work required now.
More code creates more entropy. More entropy means more bugs, more maintenance, more cognitive load. This skill fights that trend.
Use this skill when:
Do NOT use automatically. This is a manual-only skill that requires explicit user request.
Measure the end state, not the effort.
Every change must answer:
What's the smallest codebase that solves this?
Does this result in less total code?
What can we delete?
Before starting, you must load at least one mindset from the references/ directory. These provide philosophical grounding for radical simplification:
references/Do not proceed without loading a mindset.
This skill actively rejects these common arguments:
| Argument | Why It's Rejected |
|---|---|
| "Keep what exists" | Status quo bias. The question is total code, not churn. |
| "This adds flexibility" | Flexibility for what? YAGNI. |
| "Better separation of concerns" | More files/functions = more code. Separation isn't free. |
| "Type safety" | Worth how many lines? Sometimes runtime checks win. |
| "Easier to understand" | 14 things are not easier than 2 things. |
Don't use this skill when:
User: "I need to add validation to these 5 forms"
Standard approach:
- Create validation schema for each form (5 files)
- Add validation helper functions (1 file)
- Update each form component (5 files modified)
- Total: +6 files, ~300 lines added
Reducing Entropy approach:
1. Load mindset (e.g., "worse-is-better.md")
2. Ask: What's the smallest codebase that solves this?
- Could we have 1 validation function instead of 5 schemas?
- Do all 5 forms need validation or just 2?
- Can we delete 3 forms and merge functionality?
3. Count before/after:
- Before: 5 forms + 0 validation = 500 lines
- Option A: 5 forms + 6 validation files = 800 lines (reject)
- Option B: 2 forms + 1 validation function = 350 lines (accept)
4. Delete: Remove 3 forms, add 1 function
- Net result: -150 lines
references/ - Philosophical mindsets to load before startingadding-reference-mindsets.md - How to add new mindsetsYou've succeeded when:
Bias toward deletion. Measure the end state.
View Count
0
Download Count
0
Favorite Count
0
Quality Score
72