anti-slop

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Anti-Slop Skill

Anti-Slop 工具集

Detect and eliminate generic AI-generated patterns ("slop") across natural language, code, and design.

检测并消除自然语言、代码和设计中由AI生成的通用模式（即「AI Slop」）。

What is AI Slop?

什么是AI Slop？

AI slop refers to telltale patterns that signal low-quality, generic AI-generated content:

Text: Overused phrases like "delve into," excessive buzzwords, meta-commentary
Code: Generic variable names, obvious comments, unnecessary abstraction
Design: Cookie-cutter layouts, generic gradients, overused visual patterns

This skill helps identify and remove these patterns to create authentic, high-quality content.

AI Slop指的是那些表明内容由低质量、通用AI生成的典型模式：

文本：过度使用的短语（如「深入探讨」）、过多的行业黑话、元评论
代码：通用变量名、冗余注释、不必要的抽象
设计：千篇一律的布局、通用渐变效果、过度使用的视觉模式

本工具集可帮助识别并移除这些模式，以创建真实、高质量的内容。

When to Use This Skill

何时使用本工具集

Apply anti-slop techniques when:

Reviewing AI-generated content before delivery
Creating original content and want to avoid generic patterns
Cleaning up existing content that feels generic
Establishing quality standards for a project
User explicitly requests slop detection or cleanup
Content has telltale signs of generic AI generation

在以下场景中应用反AI Slop技术：

交付前审核AI生成的内容
创作原创内容时，希望避免通用模式
清理看起来千篇一律的现有内容
为项目制定质量标准
用户明确要求检测或清理AI Slop
内容带有明显的通用AI生成特征

Core Workflow

核心工作流程

1. Detect Slop

1. 检测AI Slop

For text files:

bash

python scripts/detect_slop.py <file> [--verbose]

This analyzes text and provides:

Slop score (0-100, higher is worse)
Specific pattern findings
Actionable recommendations

Manual detection: Read the appropriate reference file for detailed patterns:

```
references/text-patterns.md
```
- Natural language slop patterns
```
references/code-patterns.md
```
- Programming slop patterns
```
references/design-patterns.md
```
- Visual/UX design slop patterns

针对文本文件：

bash

python scripts/detect_slop.py <file> [--verbose]

该脚本会分析文本并提供以下信息：

Slop评分（0-100分，分数越高情况越糟）
具体的模式检测结果
可执行的改进建议

手动检测： 阅读对应的参考文件以了解详细模式：

```
references/text-patterns.md
```
- 自然语言Slop模式
```
references/code-patterns.md
```
- 编程Slop模式
```
references/design-patterns.md
```
- 视觉/UX设计Slop模式

2. Clean Slop

2. 清理AI Slop

Automated cleanup (text only):

bash

undefined

自动清理（仅支持文本）：

bash

undefined

Preview changes

预览更改

python scripts/clean_slop.py <file>

Apply changes (creates backup)

应用更改（会创建备份）

python scripts/clean_slop.py <file> --save

Aggressive mode (may slightly change meaning)

激进模式（可能会略微改变原意）

python scripts/clean_slop.py <file> --save --aggressive


**Manual cleanup:**
Apply strategies from the reference files based on detected patterns.

python scripts/clean_slop.py <file> --save --aggressive


**手动清理：**
根据检测到的模式，应用参考文件中的对应策略进行清理。

Text Slop Detection & Cleanup

文本Slop检测与清理

High-Priority Targets

高优先级清理目标

Remove immediately:

"delve into" → delete or replace with "examine"
"navigate the complexities" → "handle" or delete
"in today's fast-paced world" → delete
"it's important to note that" → delete
Meta-commentary about the document itself

Simplify wordy phrases:

"in order to" → "to"
"due to the fact that" → "because"
"has the ability to" → "can"

Replace buzzwords:

"leverage" → "use"
"synergistic" → "cooperative"
"paradigm shift" → "major change"

立即移除：

"delve into" → 删除或替换为「研究」
"navigate the complexities" → 「处理」或删除
"in today's fast-paced world" → 删除
"it's important to note that" → 删除
关于文档本身的元评论

简化冗长表述：

"in order to" → 「为了」或简化为「要」
"due to the fact that" → 「因为」
"has the ability to" → 「能够」

替换行业黑话：

"leverage" → 「使用」
"synergistic" → 「协作的」
"paradigm shift" → 「重大变革」

Quality Principles

质量原则

Be direct:

Skip preambles and meta-commentary
Lead with the actual point
Cut transition words that don't add meaning

Be specific:

Replace generic terms with concrete examples
Name specific things instead of "items," "things," "data"
Use precise verbs instead of vague action words

Be authentic:

Vary sentence structure and length
Use active voice predominantly
Write in a voice appropriate to context, not corporate-generic

直接明了：

跳过开场白和元评论
开门见山，直接表达核心观点
删除无意义的过渡词

具体明确：

用具体示例替代通用术语
明确指代事物名称，而非使用「项目」「事物」「数据」等模糊词汇
使用精准动词，避免模糊的动作表述

真实自然：

变换句子结构和长度
优先使用主动语态
根据上下文选择合适的语气，避免使用千篇一律的企业式套话

Code Slop Detection & Cleanup

代码Slop检测与清理

High-Priority Targets

高优先级清理目标

Rename generic variables:

```
data
```
→ name what data it represents
```
result
```
→ name what the result contains
```
temp
```
→ name what you're temporarily storing
```
item
```
→ name what kind of item

Remove obvious comments:

python

undefined

重命名通用变量：

```
data
```
→ 明确变量代表的数据类型
```
result
```
→ 明确结果的具体内容
```
temp
```
→ 明确临时存储的内容
```
item
```
→ 明确项目的具体类型

移除冗余注释：

python

undefined

Bad

不良示例

Create a user

创建用户

user = User()

Better - let code speak

优化后——让代码自我说明

user = User()


**Simplify over-engineered code:**
- Remove unnecessary abstraction layers
- Replace design patterns used without purpose
- Simplify complex implementations of simple tasks

**Improve function names:**
- `handleData()` → what are you doing with data?
- `processItems()` → what processing specifically?
- `manageUsers()` → what management action?

user = User()


**简化过度设计的代码：**
- 移除不必要的抽象层
- 替换无意义的设计模式
- 简化简单任务的复杂实现

**优化函数名称：**
- `handleData()` → 明确对数据执行的操作
- `processItems()` → 明确具体的处理内容
- `manageUsers()` → 明确具体的管理动作

Quality Principles

质量原则

Clarity over cleverness:

Write code that's easy to understand
Optimize only when profiling shows need
Prefer simple solutions to complex ones

Meaningful names:

Variable names should describe content
Function names should describe action + object
Class names should describe responsibility

Appropriate documentation:

Document why, not what
Skip documentation for self-evident code
Focus documentation on public APIs and complex logic

清晰优先于技巧：

编写易于理解的代码
仅在性能分析显示需要时才进行优化
优先选择简单解决方案而非复杂实现

有意义的命名：

变量名应描述其存储的内容
函数名应明确动作+对象
类名应描述其职责

恰当的文档：

记录原因而非内容
无需对自明的代码添加注释
重点为公共API和复杂逻辑编写文档

Design Slop Detection & Cleanup

设计Slop检测与清理

High-Priority Targets

高优先级清理目标

Visual slop:

Generic gradient backgrounds (purple/pink/cyan)
Overuse of glassmorphism or neumorphism
Floating 3D shapes without purpose
Every element using same design treatment

Layout slop:

Template-driven layouts ignoring content needs
Everything in cards regardless of content type
Excessive whitespace without hierarchy
Center-alignment of all elements

Copy slop:

"Empower your business" type headlines
Generic CTAs like "Get Started" without context
Buzzword-heavy descriptions
Stock photo aesthetics

视觉层面Slop：

通用渐变背景（紫/粉/青色调）
过度使用毛玻璃或拟物化设计
无意义的悬浮3D图形
所有元素使用相同的设计风格

布局层面Slop：

忽略内容需求的模板化布局
无论内容类型都使用卡片式设计
无层级的过多留白
所有元素居中对齐

文案层面Slop：

类似「赋能您的业务」的标题
无上下文的通用CTA（如「立即开始」）
充满行业黑话的描述
库存照片式的视觉风格

Quality Principles

质量原则

Content-first design:

Design around actual content needs
Create hierarchy based on importance
Let content determine layout, not templates

Intentional choices:

Every design decision should be justifiable
Use patterns because they serve users, not because they're trendy
Vary visual treatment based on element importance

Authentic voice:

Copy should reflect brand personality
Avoid generic marketing speak
Be specific about value proposition

内容优先的设计：

根据实际内容需求进行设计
基于重要性建立视觉层级
让内容决定布局，而非模板

有意图的选择：

每个设计决策都应有合理依据
使用设计模式是为了服务用户，而非追逐潮流
根据元素的重要性采用不同的视觉处理方式

真实的品牌语气：

文案应体现品牌个性
避免使用通用的营销套话
明确具体的价值主张

Reference Files

参考文件

Consult these comprehensive guides when working on specific domains:

text-patterns.md - Complete catalog of natural language slop patterns with detection rules and cleanup strategies
code-patterns.md - Programming antipatterns across languages with refactoring guidance
design-patterns.md - Visual and UX design slop patterns with improvement strategies

Each reference includes:

Pattern definitions and examples
Detection signals (high/medium confidence)
Context where patterns are acceptable
Specific cleanup strategies

处理特定领域内容时，可参考以下综合指南：

text-patterns.md - 完整的自然语言Slop模式目录，包含检测规则和清理策略
code-patterns.md - 多语言编程反模式，包含重构指导
design-patterns.md - 视觉与UX设计Slop模式，包含改进策略

每份参考文件都包含：

模式定义与示例
检测信号（高/中置信度）
模式可接受的场景
具体的清理策略

Scripts

脚本说明

detect_slop.py

Analyzes text files for AI slop patterns.

Usage:

bash

python scripts/detect_slop.py <file> [--verbose]

Output:

Overall slop score (0-100)
Category-specific findings
Line numbers and examples
Actionable recommendations

Scoring:

0-20: Low slop (authentic writing)
20-40: Moderate slop (some patterns)
40-60: High slop (many patterns)
60+: Severe slop (heavily generic)

分析文本文件中的AI Slop模式。

使用方式：

bash

python scripts/detect_slop.py <file> [--verbose]

输出内容：

整体Slop评分（0-100）
按类别划分的检测结果
问题所在行号与示例
可执行的改进建议

评分标准：

0-20：低Slop（内容真实自然）
20-40：中度Slop（存在部分模式）
40-60：高度Slop（存在大量模式）
60+：重度Slop（内容高度通用化）

clean_slop.py

Automatically removes common slop patterns from text files.

Usage:

bash

undefined

自动移除文本文件中的常见Slop模式。

使用方式：

bash

undefined

Preview changes

预览更改

python scripts/clean_slop.py <file>

Save changes (creates backup)

保存更改（会创建备份）

python scripts/clean_slop.py <file> --save

Save to different file

保存到指定文件

python scripts/clean_slop.py <file> --output clean_file.txt

Aggressive mode

激进模式

python scripts/clean_slop.py <file> --save --aggressive


**What it cleans:**
- High-risk phrases
- Wordy constructions
- Meta-commentary
- Excessive hedging
- Buzzwords
- Redundant qualifiers
- Empty intensifiers

**Safety:**
- Always creates `.backup` file when overwriting
- Preview mode shows changes before applying
- Preserves content meaning (non-aggressive mode)

python scripts/clean_slop.py <file> --save --aggressive


**清理范围：**
- 高风险短语
- 冗长表述
- 元评论
- 过度模糊的表述
- 行业黑话
- 冗余限定词
- 空洞的强调词

**安全性说明：**
- 覆盖文件时始终会创建`.backup`备份文件
- 预览模式可在应用更改前查看修改内容
- 非激进模式下会保留内容原意

Best Practices

最佳实践

Prevention Over Cure

预防胜于补救

When creating content:

Write with specific audience in mind
Use concrete examples over abstractions
Lead with the point, skip preambles
Choose words for precision, not impression
Review before considering it complete

创作内容时：

明确目标受众
使用具体示例而非抽象表述
开门见山，跳过开场白
选择精准词汇而非刻意营造印象
完成后进行自我审核

Context-Aware Cleanup

基于上下文的清理

Not all patterns are always slop:

Acceptable contexts:

Academic writing may need more hedging
Legal documents require specific phrasing
Internal documentation can use shortcuts
Technical docs have domain-specific conventions

Always consider:

Who is the audience?
What is the purpose?
Does this pattern serve a function?
Is there a better alternative?

并非所有模式都是Slop：

可接受的场景：

学术写作可能需要更多的严谨表述
法律文件需要特定的措辞
内部文档可使用简化表述
技术文档有特定的领域惯例

始终考虑：

受众是谁？
内容的目的是什么？
该模式是否有实际作用？
是否有更好的替代方案？

Iterative Improvement

迭代式改进

Detect - Run detection scripts or manual review
Analyze - Understand which patterns are truly problems
Clean - Apply automated cleanup where safe
Review - Manually verify changes maintain meaning
Refine - Fix remaining issues by hand

检测 - 运行检测脚本或进行手动审核
分析 - 确定哪些模式确实存在问题
清理 - 在安全场景下应用自动清理
审核 - 手动验证更改是否保留原意
优化 - 手动修复剩余问题

Quality Over Automation

质量优先于自动化

The scripts are tools, not replacements for judgment:

Use automated detection to find candidates
Apply automated cleanup to obvious patterns
Manually review anything that changes meaning
Exercise discretion based on context

脚本是工具，无法替代人工判断：

使用自动检测来定位问题候选
对明显的模式应用自动清理
手动审核所有可能改变原意的内容
根据上下文灵活判断

Integration Patterns

集成模式

Code Review

代码审核

bash

undefined

bash

undefined

Check files before committing

提交前检查文件

python scripts/detect_slop.py src/documentation.md --verbose

Clean up automatically

自动清理

python scripts/clean_slop.py src/documentation.md --save

undefined

python scripts/clean_slop.py src/documentation.md --save

undefined

Content Pipeline

内容流水线

Create initial content
Run slop detection
Apply automated cleanup
Manual review and refinement
Final quality check

创建初始内容
运行Slop检测
应用自动清理
手动审核与优化
最终质量检查

Standards Enforcement

标准执行

Create project-specific thresholds:

Max acceptable slop score: 30
Required manual review for scores > 20
Auto-reject submissions with scores > 50

制定项目特定的阈值：

可接受的最高Slop评分：30
评分超过20需手动审核
评分超过50自动拒绝提交

Limitations

局限性

Scripts only handle text:

Code slop detection is manual (use code-patterns.md)
Design slop detection is manual (use design-patterns.md)

Context sensitivity:

Scripts can't understand all contexts
Some "slop" may be appropriate in certain domains
Always review automated changes

Language coverage:

Detection patterns optimized for English
Code patterns focus on common languages (Python, JS, Java)
Design patterns are platform-agnostic

脚本仅支持文本处理：

代码Slop检测需手动完成（参考code-patterns.md）
设计Slop检测需手动完成（参考design-patterns.md）

上下文敏感性：

脚本无法理解所有上下文
某些「Slop」在特定领域可能是合适的
始终需要手动审核自动更改

语言覆盖范围：

检测模式针对英语优化
代码模式聚焦于常用语言（Python、JS、Java）
设计模式与平台无关

Common Scenarios

常见场景

Scenario 1: Review AI-Generated Content

场景1：审核AI生成的内容

bash

undefined

bash

undefined

User asks: "Can you review this article for AI slop?"

用户需求：「能否帮我审核这篇文章中的AI Slop？」

Read references/text-patterns.md for patterns to watch
Run: python scripts/detect_slop.py article.txt --verbose
Review findings and apply manual cleanup
Optionally run: python scripts/clean_slop.py article.txt --save
Do final manual review of cleaned content

undefined

阅读references/text-patterns.md，了解需关注的模式
运行：python scripts/detect_slop.py article.txt --verbose
查看检测结果并进行手动清理
可选：运行python scripts/clean_slop.py article.txt --save
对清理后的内容进行最终手动审核

undefined

Scenario 2: Clean Up Codebase

场景2：清理代码库

bash

undefined

bash

undefined

User asks: "Help me clean up generic AI patterns in my code"

用户需求：「帮我清理代码库中的通用AI模式」

Read references/code-patterns.md
Review code files manually for patterns
Create list of generic names to rename
Refactor following principles in code-patterns.md
Remove obvious comments and over-abstractions

undefined

阅读references/code-patterns.md
手动审核代码文件以查找模式
列出需要重命名的通用变量名
按照code-patterns.md中的原则进行重构
移除冗余注释和过度抽象的代码

undefined

Scenario 3: Design Review

场景3：设计审核

bash

undefined

bash

undefined

User asks: "Does this design look too generic?"

用户需求：「这个设计看起来是不是太通用了？」

Read references/design-patterns.md
Check against high-confidence slop indicators
Identify specific issues (gradients, layouts, copy)
Provide specific recommendations from design-patterns.md
Suggest concrete alternatives

undefined

阅读references/design-patterns.md
对照高置信度Slop指标进行检查
识别具体问题（渐变、布局、文案）
根据design-patterns.md提供具体的改进建议
给出具体的替代方案

undefined

Scenario 4: Establish Quality Standards

场景4：制定质量标准

bash

undefined

bash

undefined

User asks: "Help me create quality standards for our team"

用户需求：「帮我为团队制定质量标准」

Review all three reference files
Identify patterns most relevant to user's domain
Create project-specific guidelines
Set up detection scripts in development pipeline
Document acceptable exceptions

undefined

阅读所有三份参考文件
确定与用户领域最相关的模式
制定项目特定的指南
在开发流水线中配置检测脚本
记录可接受的例外情况

undefined

Tips for Success

成功技巧

For text cleanup:

Run detection first to understand scope
Use non-aggressive mode for important content
Always review automated changes
Focus on high-risk patterns first

For code cleanup:

Start with renaming generic variables
Remove obvious comments next
Refactor over-engineered code last
Test after each significant change

For design cleanup:

Audit visual elements against patterns
Prioritize structural issues over aesthetic ones
Ensure changes serve user needs
Maintain brand consistency

General principles:

Quality > uniformity
Context > rules
Clarity > cleverness
Specificity > generality

文本清理技巧：

先运行检测以了解问题范围
对重要内容使用非激进模式
始终审核自动更改
优先处理高风险模式

代码清理技巧：

从重命名通用变量开始
接下来移除冗余注释
最后重构过度设计的代码
每次重大修改后进行测试

设计清理技巧：

对照模式审核视觉元素
优先解决结构问题而非审美问题
确保更改服务于用户需求
保持品牌一致性

通用原则：

质量 > 统一性
上下文 > 规则
清晰 > 技巧
具体 > 通用