de-slopify
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDe-Slopify
De-Slopify
Overview
概述
De-slopify is a methodology for removing telltale signs of AI-generated content from documentation, prose, and code. LLMs produce statistically regular output with characteristic vocabulary, punctuation habits, and structural patterns that make text and code feel inauthentic. Some patterns appear over 1,000x more frequently in LLM output than human writing.
When to use: Before publishing READMEs, after AI-assisted writing sessions, during documentation reviews, when reviewing AI-generated code for over-engineering, before committing prose or code that an LLM touched.
When NOT to use: On code logic or algorithms where correctness matters more than style. On technical specifications where precision outweighs voice. On content that was already human-written and reads naturally.
De-slopify是一种移除文档、散文和代码中AI生成内容典型痕迹的方法。LLM生成的输出具有统计规律性，带有独特的词汇、标点习惯和结构模式，会让文本和代码显得不够真实。有些模式在LLM输出中的出现频率是人类写作的1000倍以上。
适用场景：发布README之前、AI辅助写作之后、文档审核过程中、审核AI生成的代码是否过度设计时、提交LLM处理过的散文或代码之前。
不适用场景：在正确性优先于风格的代码逻辑或算法中；在精度比表达更重要的技术规范中；在已经由人类撰写、读起来自然的内容中。
Quick Reference
快速参考
| Category | Pattern | Fix |
|---|---|---|
| Punctuation | Emdash overuse | Semicolons, commas, colons, or split into two sentences |
| Phrase | "Here's why" / "Here's why it matters" | Explain why directly without the lead-in |
| Phrase | "It's not X, it's Y" | "This is Y" or restate the distinction |
| Phrase | "Let's dive in" / "Let's get started" | Delete; just start the content |
| Phrase | "It's worth noting" / "Keep in mind" | Delete the hedge; state the fact |
| Phrase | "At its core" / "In essence" / "Fundamentally" | Delete; say the thing directly |
| Vocabulary | "delve", "tapestry", "landscape", "nuanced" | Replace with plain, specific language |
| Vocabulary | "revolutionize", "cutting-edge", "game-changer" | Replace with concrete claims or delete |
| Structure | Uniform sentence length throughout | Mix short (5-word) and long (20+ word) sentences |
| Structure | Perfectly balanced lists of exactly 3 items | Vary list length; humans use 2, 4, or odd counts |
| Structure | Generic claims without specifics | Add names, dates, numbers, or first-person detail |
| Sycophancy | "Great question!" / "Absolutely!" | Delete; answer the question directly |
| Meta | "Let me break this down..." / "Let me explain" | Delete the preamble; just break it down |
| Structure | Numbered lists where a sentence suffices | Use a sentence; reserve lists for genuinely parallel items |
| Closer | "In conclusion" / "To summarize" | Delete or replace with a specific takeaway |
| Code | Over-commented trivial functions | Remove comments that restate the code |
| Code | Unnecessary abstractions and design patterns | Flatten to the simplest working solution |
| Code | Verbose or overly descriptive variable names | Use domain-appropriate concise names |
| Code | Defensive error handling on every operation | Handle errors only where failure is realistic |
| 类别 | 典型问题 | 修复方案 |
|---|---|---|
| 标点符号 | 破折号过度使用 | 改用分号、逗号、冒号，或拆分为两个句子 |
| 短语表达 | "Here's why" / "Here's why it matters"（“原因如下”类表述） | 直接解释原因，去掉引导语 |
| 短语表达 | "It's not X, it's Y"（“不是X，而是Y”类表述） | 改为“这是Y”或重新表述两者的区别 |
| 短语表达 | "Let's dive in" / "Let's get started"（“让我们开始”类表述） | 删除该表述，直接切入内容 |
| 短语表达 | "It's worth noting" / "Keep in mind"（“值得注意”类表述） | 删除这类铺垫性表述，直接陈述事实 |
| 短语表达 | "At its core" / "In essence" / "Fundamentally"（“从本质上”类表述） | 删除该表述，直接说明核心内容 |
| 词汇选择 | "delve", "tapestry", "landscape", "nuanced"（华丽空洞词汇） | 替换为平实、具体的语言 |
| 词汇选择 | "revolutionize", "cutting-edge", "game-changer"（夸大词汇） | 替换为具体的表述或直接删除 |
| 结构模式 | 句子长度完全统一 | 混合使用短句（5词以内）和长句（20词以上） |
| 结构模式 | 完美平衡的3项式列表 | 调整列表长度；人类通常使用2、4或奇数项 |
| 结构模式 | 无具体细节的泛泛之谈 | 添加名称、日期、数字或第一人称细节 |
| 客套表述 | "Great question!" / "Absolutely!"（过度客套表述） | 删除该表述，直接回答问题 |
| 元表述 | "Let me break this down..." / "Let me explain"（“让我解释”类表述） | 删除该铺垫，直接展开说明 |
| 结构模式 | 可用单句说明却使用编号列表 | 使用单句表述；仅在内容真正平行时使用列表 |
| 结尾表述 | "In conclusion" / "To summarize"（“总结来说”类表述） | 删除该表述或替换为具体的结论要点 |
| 代码问题 | 对简单函数过度注释 | 删除重复代码含义的注释 |
| 代码问题 | 不必要的抽象和设计模式 | 简化为最简单的可行解决方案 |
| 代码问题 | 冗长或过度描述的变量名 | 使用符合领域习惯的简洁名称 |
| 代码问题 | 对每个操作都进行防御性错误处理 | 仅在可能出现实际故障的场景处理错误 |
Common Mistakes
常见错误
| Mistake | Correct Pattern |
|---|---|
| Replacing every emdash mechanically | Evaluate context; sometimes an emdash is the right choice |
| Editing code blocks for style | Focus on prose; leave code examples and technical syntax untouched |
| Removing all structure to sound casual | Keep headers, tables, and lists intact; rewrite prose only |
| Over-correcting into choppy fragments | Read aloud after editing; recombine sentences that lost flow |
| Applying fixes without defining target voice | Set persona, tone, and audience before starting edits |
| Running regex replacements instead of reading | Manual line-by-line review is required; context determines fixes |
| Ignoring AI code smells | Review AI-generated code for over-engineering, verbose names, and unnecessary abstractions |
| Removing all LLM-typical words unconditionally | Some flagged words are perfectly natural in context; use judgment |
| 错误做法 | 正确方式 |
|---|---|
| 机械替换所有破折号 | 根据上下文判断；有时破折号是合适的选择 |
| 为了风格修改代码块 | 重点优化散文内容；保留代码示例和技术语法不变 |
| 为了口语化移除所有结构 | 保留标题、表格和列表结构；仅重写散文部分 |
| 过度修改导致语句支离破碎 | 修改后朗读检查；重新组合失去流畅性的句子 |
| 未定义目标语气就开始修改 | 在开始编辑前确定内容风格、语气和受众 |
| 使用正则表达式批量替换而非逐行阅读检查 | 需要逐行人工审核；上下文决定具体修复方案 |
| 忽略AI代码异味 | 审核AI生成的代码是否存在过度设计、冗长命名和不必要的抽象 |
| 无条件移除所有LLM高频词汇 | 部分标记词汇在特定语境下完全自然；请根据实际情况判断 |
Delegation
任务委托
- Scan a repository for documentation files that need de-slopifying: Use agent
Explore - Rewrite an entire documentation site to remove AI artifacts: Use agent
Task - Plan a documentation voice guide and editorial workflow: Use agent
Plan - Review AI-generated code for slop patterns: Use agent
code-reviewer
For systematic quality auditing across 12 dimensions (architecture, security, testing, performance, etc.), use theskill.quality-auditor
- 扫描仓库中需要清理AI痕迹的文档文件：使用Agent
Explore - 重写整个文档站点以移除AI痕迹：使用Agent
Task - 制定文档语气指南和编辑工作流：使用Agent
Plan - 审核AI生成代码中的冗余模式：使用Agent
code-reviewer
如需针对12个维度（架构、安全、测试、性能等）进行系统化质量审计，请使用技能。quality-auditor
References
参考资料
- Prose patterns: emdash alternatives, phrase replacements, and voice calibration
- Before-and-after examples of common AI writing fixes
- AI slop vocabulary: words and phrases that signal LLM authorship
- Code slop: detecting and fixing AI-generated code smells
- Review workflow: prompts, checklists, and integration
- 散文模式：破折号替代方案、短语替换及语气校准
- 常见AI写作修复的前后对比示例
- AI冗余词汇：暴露LLM作者身份的词汇和短语
- 代码冗余：检测和修复AI生成的代码异味
- 审核工作流：提示词、检查清单及集成方案