Back to Details

solo-humanize

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/humanize

/humanize

Strip AI writing patterns from user-facing text. Takes a file or pasted text and rewrites it to read like a human wrote it, without losing meaning or structure.
去除面向用户文本中的AI写作模式。支持读取文件或粘贴的文本，在保留原意和结构的前提下，将其改写为更符合人类写作风格的内容。

Why this exists

设计初衷

LLM output has recognizable tells — em dashes, stock phrases, promotional inflation, performed authenticity. Readers (and Google) notice. This skill catches those patterns and rewrites them.
大语言模型（LLM）生成的内容有明显的特征——比如滥用破折号、使用陈词滥调、夸大宣传、刻意营造真诚感等。读者（甚至谷歌算法）都能察觉到这些痕迹。本功能可以识别这些模式并进行改写。

When to use

使用场景

  • After 
    /content-gen
    , 
    /landing-gen
    , 
    /video-promo
    — polish the output
  • Before publishing any user-facing prose (blog posts, landing pages, emails)
  • When editing CLAUDE.md or docs that will be read by humans
  • Standalone: 
    /humanize path/to/file.md
  • 在使用
    /content-gen
    、
    /landing-gen
    、
    /video-promo
    生成内容后，优化输出结果
  • 在发布任何面向用户的文案前（如博客文章、着陆页、邮件）
  • 编辑CLAUDE.md或其他供人类阅读的文档时
  • 独立使用：
    /humanize path/to/file.md

Input

输入方式

  • File path from 
    $ARGUMENTS
    — reads and rewrites in place
  • No argument — asks to paste text, outputs cleaned version
  • Works on 
    .md
    , 
    .txt
    , and text content in 
    .tsx
    /
    .html
    (string literals only)
  • 文件路径（通过
    $ARGUMENTS
    传入）——读取文件并原地改写
  • 无参数——提示用户粘贴文本，输出优化后的版本
  • 支持
    .md
    、
    .txt
    格式，以及
    .tsx
    /
    .html
    中的字符串文本（仅字符串字面量）

Pattern Catalog

识别的AI写作模式

1. Em Dash Overuse (—)

1. 破折号滥用（—）

The most obvious AI tell. Replace with commas, periods, colons, or restructure the sentence.
BeforeAfter
"The tool — which is free — works great""The tool (which is free) works great"
"Three features — speed, security, simplicity""Three features: speed, security, simplicity"
"We built this — and it changed everything""We built this. It changed everything."
Rule: Max 1 em dash per 500 words. Zero is better.
这是最明显的AI写作特征。将其替换为逗号、句号、冒号，或重构句子。
原句改写后
"这款工具——完全免费——用起来很棒""这款工具（完全免费）用起来很棒"
"三大特色——速度快、安全性高、操作简便""三大特色：速度快、安全性高、操作简便"
"我们打造了这款工具——它彻底改变了一切""我们打造了这款工具，它彻底改变了一切。"
**规则：**每500字最多使用1个破折号，完全不用更佳。

2. Stock Phrases

2. 陈词滥调

Phrases that signal "AI wrote this." Remove or replace with specific language.
Filler phrases (delete entirely):
  • "it's worth noting that" → (just state the thing)
  • "at the end of the day" → (cut)
  • "in today's world" / "in the modern landscape" → (cut)
  • "without further ado" → (cut)
  • "let's dive in" / "let's explore" → (cut)
Promotional inflation (replace with specifics):
  • "game-changer" → what specifically changed?
  • "revolutionary" → what's actually new?
  • "cutting-edge" → describe the technology
  • "seamless" → "works without configuration" (or whatever it actually does)
  • "leverage" → "use"
  • "robust" → "handles X edge cases" (specific)
  • "streamline" → "cut steps from N to M"
  • "empower" → what can the user now do?
  • "unlock" → what's the actual capability?
Performed authenticity (rewrite):
  • "to be honest" → (if you need to say this, the rest wasn't honest?)
  • "let me be frank" → (just be frank)
  • "I have to say" → (just say it)
  • "honestly" → (cut)
  • "the truth is" → (cut, state the truth directly)
这些短语会暴露“AI生成”的痕迹，需要删除或替换为具体表述。
冗余填充语（直接删除）：
  • "值得注意的是" → 直接陈述内容
  • "归根结底" → 删除
  • "在当今世界" / "在现代环境下" → 删除
  • "话不多说" → 删除
  • "让我们深入探讨" / "让我们一起来看看" → 删除
夸大宣传（替换为具体描述）：
  • "改变游戏规则的产品" → 具体说明改变了什么
  • "革命性的突破" → 说明实际创新点
  • "前沿技术" → 描述具体技术细节
  • "无缝体验" → "无需额外配置即可使用"（或其他实际功能）
  • "充分利用" → "使用"
  • "功能强大" → "可处理X类边缘情况"（具体表述）
  • "简化流程" → "将步骤从N步减少到M步"
  • "赋能用户" → 说明用户现在可以完成什么操作
  • "解锁潜能" → 说明实际获得的能力
刻意真诚（改写）：
  • "说实话" → 如果需要这么说，说明之前的内容不够直接
  • "坦白说" → 直接说出观点
  • "我不得不说" → 直接陈述
  • "老实说" → 删除
  • "事实是" → 删除，直接陈述事实

3. Rule of Three

3. 三段式列举

AI loves triplets: "fast, secure, and scalable." Real writing varies list length.
BeforeAfter
"Fast, secure, and scalable""Fast and secure" (if scalable isn't proven)
"Build, deploy, and iterate""Build and ship" (if that's what you mean)
Three bullet points that all say the same thingOne clear bullet
Rule: If you find 3+ triplet lists in one document, break at least half of them.
AI偏爱三元组表述：“快速、安全、可扩展”。人类写作会灵活调整列表长度。
原句改写后
"快速、安全、可扩展""快速且安全"（如果可扩展未被验证）
"构建、部署、迭代""构建并发布"（如果这是实际意图）
三个内容重复的项目符号合并为一个清晰的项目符号
**规则：**如果文档中有3处及以上的三元组列举，至少改写其中一半。

4. Structural Patterns

4. 结构模式化

Every section has the same shape: AI tends to write: heading → one-sentence intro → 3 bullets → transition sentence. Real writing varies section length and structure.
Hedging sandwich: "While X has limitations, it offers Y, making it Z." → Pick a side. State it.
False balance: "On one hand X, on the other hand Y." → If one side is clearly better, say so.
所有章节结构一致： AI写作常遵循“标题→一句话引言→3个项目符号→过渡句”的固定结构。人类写作会灵活调整章节长度和结构。
含糊其辞的夹心结构： "虽然X存在局限性，但它具备Y特性，使其成为Z。" → 明确立场，直接陈述。
虚假平衡： "一方面X，另一方面Y。" → 如果某一方明显更优，直接表明。

5. Sycophantic Openers

5. 谄媚式开场

  • "Great question!" → (cut)
  • "That's a fantastic idea!" → (cut, or say what's specifically good about it)
  • "Absolutely!" → (cut if not genuine agreement)
  • "I'd be happy to help!" → (just help)
  • "好问题！" → 删除
  • "这是个绝妙的主意！" → 删除，或具体说明其优点
  • "完全同意！" → 如果不是真心认同，删除
  • "我很乐意帮忙！" → 直接提供帮助

6. Passive Voice / Weak Verbs

6. 被动语态/弱动词

  • "It should be noted that" → (cut, just note it)
  • "There are several factors that" → name the factors
  • "It is important to" → say why
  • "This can be achieved by" → "Do X"
  • "需要注意的是" → 删除，直接陈述
  • "存在多个影响因素" → 直接列出因素
  • "重要的是" → 说明原因
  • "可通过以下方式实现" → "执行X操作"

Process

处理流程

  1. Read the input — file path or pasted text.
  2. Scan for patterns — check each category above. Count violations per category.
  3. Rewrite — fix each violation while preserving:
    • Technical accuracy (don't change code, commands, or technical terms)
    • Structure (headings, lists, code blocks stay)
    • Tone intent (if the original was casual, keep it casual)
    • Length (aim for same or shorter, never longer)
  4. Report what changed:
    Humanized: {file or "pasted text"}

Changes:
  Em dashes:  {N} removed
  Stock phrases: {N} replaced
  Inflation: {N} deflated
  Triplets: {N} broken
  Sycophancy: {N} cut
  Total: {N} patterns fixed

Before: {word count}
After:  {word count}
  5. If file path: write the cleaned version back. Show a diff summary. If pasted text: output the cleaned version directly.
  1. 读取输入 —— 文件路径或粘贴的文本。
  2. 扫描模式 —— 检查上述所有类别，统计各类别的违规次数。
  3. 改写内容 —— 修正每一处违规，同时保留：
    • 技术准确性（不修改代码、命令或专业术语）
    • 结构（标题、列表、代码块保持不变）
    • 语气意图（如果原文是口语化风格，保留该风格）
    • 长度（尽量与原文一致或更短，避免冗长）
  4. 输出修改报告：
    Humanized: {file or "pasted text"}

Changes:
  Em dashes:  {N} removed
  Stock phrases: {N} replaced
  Inflation: {N} deflated
  Triplets: {N} broken
  Sycophancy: {N} cut
  Total: {N} patterns fixed

Before: {word count}
After:  {word count}
  5. 如果是文件路径： 将优化后的内容写回原文件，并显示差异摘要。 如果是粘贴的文本： 直接输出优化后的内容。

What NOT to change

不可修改的内容

  • Code blocks and inline code
  • Technical terms, library names, CLI commands
  • Quotes from other people (attributed quotes stay verbatim)
  • Numbers, dates, URLs
  • Headings structure (don't merge or split sections)
  • Content meaning — only rephrase, never add or remove ideas
  • 代码块和行内代码
  • 专业术语、库名称、CLI命令
  • 他人引用的内容（注明出处的引用需完全保留）
  • 数字、日期、URL
  • 标题结构（不合并或拆分章节）
  • 内容原意 —— 仅改写表述方式，绝不添加或删除核心观点

Edge Cases

边缘情况处理

  • Short text (<50 words): just apply stock phrase filter, skip structural analysis
  • Already clean: report "No AI patterns found. Text looks human."
  • Code-heavy docs: skip code blocks entirely, only process prose sections
  • Non-English text: apply em dash and structural rules (they're universal), skip English stock phrases
  • 短文本（<50词）： 仅应用陈词滥调过滤规则，跳过结构分析
  • 已符合人类写作风格： 输出报告“未检测到AI写作模式，文本符合人类写作风格。”
  • 代码密集型文档： 完全跳过代码块，仅处理文案部分
  • 非英文文本： 应用破折号和结构规则（这些是通用特征），跳过英文陈词滥调过滤