Back to Details

humanize

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Humanize

文本拟人化润色

Review and edit copy to remove signs of AI-generated writing. Based on Wikipedia's "Signs of AI writing" guide maintained by WikiProject AI Cleanup. Contains 30 rules across 6 categories.
审核并编辑文案，消除AI生成文本的特征。本工具基于维基百科AI清理项目维护的《AI生成文本识别特征》指南开发，包含6大类共30条规则。

When to Apply

适用场景

  • Editing AI-generated drafts
  • Reviewing text that sounds robotic or corporate
  • Cleaning up writing before publishing
  • Making technical content sound more natural
  • 编辑AI生成的草稿
  • 审核读起来机械生硬或过于官方的文本
  • 发布前对文案进行优化处理
  • 让技术类内容读起来更自然

Constraints (Non-Negotiable)

硬性约束条件

  • Preserve meaning, factual claims, and intent.
  • Preserve coverage: don't drop list items, options, or qualifiers (e.g., removing one option from a list) unless they're truly redundant.
  • Do not add new facts, dates, quotes, or citations that are not already present or user-provided.
  • Do not imply a source ("according to…") unless you can name it from the input.
  • Keep genre and audience intact (e.g., neutral encyclopedic tone vs. personal essay). Use 
    voice-soul
    only when that voice fits.
  • Don't rewrite quoted material unless the user asked to rewrite the quote itself.
  • Avoid em dashes (—). Replace with commas, periods, or parentheses.
  • Don't introduce new AI patterns. Your rewrite must pass the same rules you're applying. Common traps: "Here's the thing:", "It's not about X, it's about Y", formulaic hooks that try to sound casual.
  • 保留原文的含义、事实陈述和核心意图。
  • 保留完整内容：不得删除列表项、选项或限定语（例如从列表中移除某一选项），除非内容确实冗余。
  • 不得添加原文或用户未提供的新事实、日期、引用或参考文献。
  • 不得随意暗示信息来源（如“据……所述”），除非能从输入内容中明确找到对应来源。
  • 保持文本的体裁和目标受众定位（例如中立的百科语气与个人随笔的区别）。仅当风格适配时才使用
    voice-soul
    规则。
  • 不得改写引用内容，除非用户明确要求改写该引用。
  • 避免使用破折号（—），改用逗号、句号或括号替代。
  • 不得引入新的AI行文模式。 改写后的文本必须符合你所应用的规则。常见误区包括：使用“事情是这样的：”“关键不是X，而是Y”这类刻意营造口语感的模板化开头。

Rule Categories

规则分类

CategoryImpactPrefixRules
ContentHIGH
content-
6
LanguageHIGH
language-
8
StyleMEDIUM
style-
7
CommunicationHIGH
comm-
3
FillerMEDIUM
filler-
5
VoiceHIGH
voice-
1
分类影响级别前缀规则数量
内容高
content-
6
语言高
language-
8
风格中
style-
7
沟通话术高
comm-
3
冗余内容中
filler-
5
语气风格高
voice-
1

Quick Reference

速查指南

Content (HIGH)

内容类（高影响）

  • content-significance
    — Remove "pivotal moment", "testament to" inflation
  • content-notability
    — Replace media name-dropping with specific claims
  • content-ing-endings
    — Fix trailing "...highlighting growth" phrases
  • content-promotional
    — Cut "nestled", "vibrant", "breathtaking"
  • content-vague-attribution
    — Replace "experts say" with specific sources
  • content-challenges
    — Remove formulaic "Despite challenges..." sections
  • content-significance
    — 删除“关键时刻”“有力证明”这类夸大表述
  • content-notability
    — 将泛泛提及媒体名称改为具体表述
  • content-ing-endings
    — 修正以“……彰显了增长”这类现在分词结尾的冗余表述
  • content-promotional
    — 删除“坐落于”“充满活力的”“令人惊叹的”这类营销化修饰词
  • content-vague-attribution
    — 将“专家表示”这类模糊归因改为具体来源
  • content-challenges
    — 删除“尽管面临挑战……”这类模板化段落

Language (HIGH)

语言类（高影响）

  • language-ai-vocabulary
    — Replace delve, showcase, leverage, foster
  • language-dual-adjectives
    — Remove "innovative and comprehensive" padding
  • language-copula
    — Use "is" instead of "serves as", "stands as"
  • language-contractions
    — Prefer contractions when genre allows
  • language-negative-parallelism
    — Cut "It's not just X, it's Y", "It's not about X, it's about Y"
  • language-rule-of-three
    — Don't force ideas into groups of three
  • language-synonym-cycling
    — Stop cycling through synonyms
  • language-false-ranges
    — Fix fake "from X to Y" constructions
  • language-ai-vocabulary
    — 替换delve、showcase、leverage、foster这类AI常用的生硬词汇
  • language-dual-adjectives
    — 删除“创新且全面的”这类冗余的双重形容词
  • language-copula
    — 用“是”替代“充当”“作为”这类冗余表述
  • language-contractions
    — 在体裁允许的情况下，优先使用缩略形式（比如用“it's”代替“it is”）
  • language-negative-parallelism
    — 删除“这不只是X，更是Y”“关键不是X，而是Y”这类模板化句式
  • language-rule-of-three
    — 不要刻意将观点凑成三组
  • language-synonym-cycling
    — 避免反复替换同义词
  • language-false-ranges
    — 修正“从X到Y”这类虚假的范围表述

Style (MEDIUM)

风格类（中影响）

  • style-em-dash
    — Replace em dashes with commas or periods
  • style-boldface
    — Reduce mechanical bold emphasis
  • style-inline-headers
    — Avoid mechanical Header: lists; keep when they improve skimming
  • style-title-case
    — Use sentence case in headings
  • style-emojis
    — Remove decorative emojis
  • style-curly-quotes
    — Use straight quotes
  • style-rhythm
    — Vary sentence/paragraph cadence
  • style-em-dash
    — 用逗号或句号替代破折号
  • style-boldface
    — 减少机械性的粗体强调
  • style-inline-headers
    — 避免使用**标题：**这类模板化的列表格式；仅当有助于快速阅读时保留
  • style-title-case
    — 标题使用句首大写格式（而非每个单词大写）
  • style-emojis
    — 删除装饰性表情符号
  • style-curly-quotes
    — 使用直引号而非弯引号
  • style-rhythm
    — 变换句子和段落的节奏

Communication (HIGH)

沟通话术类（高影响）

  • comm-artifacts
    — Remove "I hope this helps!", "Let me know if..."
  • comm-cutoff
    — Remove "as of my last update" disclaimers
  • comm-sycophantic
    — Cut "Great question!", "You're absolutely right!"
  • comm-artifacts
    — 删除“希望这对你有帮助！”“如果……请告诉我”这类套话
  • comm-cutoff
    — 删除“截至我的最后更新”这类免责声明
  • comm-sycophantic
    — 删除“问得好！”“你完全正确！”这类奉承话术

Filler (MEDIUM)

冗余内容类（中影响）

  • filler-openings
    — Cut "In today's fast-paced world", "Here's the thing" openings
  • filler-phrases
    — Cut "in order to", "at this point in time"
  • filler-hedging
    — Reduce "could potentially possibly"
  • filler-transitions
    — Reduce moreover/furthermore signposting
  • filler-conclusions
    — Replace "the future looks bright" with specifics
  • filler-openings
    — 删除“在当今快节奏的世界里”“事情是这样的”这类套话开头
  • filler-phrases
    — 删除“为了”“在当前这个时间点”这类冗余短语
  • filler-hedging
    — 减少“可能或许大概”这类过度模糊的表述
  • filler-transitions
    — 减少“此外”“再者”这类过渡词的滥用
  • filler-conclusions
    — 将“未来前景光明”这类空泛结论替换为具体表述

Voice (HIGH)

语气风格类（高影响）

  • voice-soul
    — Add personality, opinions, varied rhythm
  • voice-soul
    — 增添个性、观点，变换节奏

Scoring

评分机制

Score text before and after rewriting to show improvement. The score measures how human the writing sounds.
对改写前后的文本进行评分，以体现优化效果。评分用于衡量文本的“拟人化程度”。

How it works

评分规则

  1. Start at 100
  2. Subtract points for each violation found
  3. HIGH impact violations (Content, Language, Communication, Voice): -3 points each
  4. MEDIUM impact violations (Style, Filler): -1 point each
  5. Minimum score is 0
  1. 初始分数为100分
  2. 每发现一处违规扣除相应分数
  3. 高影响违规项（内容、语言、沟通话术、语气风格）：每项扣3分
  4. 中影响违规项（风格、冗余内容）：每项扣1分
  5. 最低分数为0分

Score report format

评分报告格式

Category       | Before | After | Notes
---------------|--------|-------|-------------------------------
Content        |     94 |   100 | 2 violations fixed
Language       |     88 |    97 | dual-adjectives, copula
Style          |     85 |   100 | 4 em dashes, tightened headers
Communication  |    100 |   100 | —
Filler         |     95 |   100 | "Here's the thing" removed
Voice          |     91 |    94 | rhythm, contractions
---------------|--------|-------|-------------------------------
Overall        |     84 |    97 |
Category       | Before | After | Notes
---------------|--------|-------|-------------------------------
Content        |     94 |   100 | 2 violations fixed
Language       |     88 |    97 | dual-adjectives, copula
Style          |     85 |   100 | 4 em dashes, tightened headers
Communication  |    100 |   100 | —
Filler         |     95 |   100 | "Here's the thing" removed
Voice          |     91 |    94 | rhythm, contractions
---------------|--------|-------|-------------------------------
Overall        |     84 |    97 |

Interpreting scores

分数解读

  • 95-100: Clean, sounds human
  • 85-94: Minor issues, mostly fine
  • 70-84: Noticeable AI patterns
  • Below 70: Needs significant work
  • 95-100分：文本自然，完全符合人类写作特征
  • 85-94分：存在轻微问题，整体表现良好
  • 70-84分：存在明显的AI行文痕迹
  • 70分以下：需要大幅优化

Process

处理流程

  1. If 
    WRITING_STYLE_GUIDE_PATH
    is set, load the writing style guide before processing
  2. Load relevant rules from 
    references/
  3. Scan text for patterns and calculate before score
  4. Rewrite problem sections
  5. Add voice (see 
    voice-soul
    )
  6. Self-check: Scan your rewrite for the same AI patterns, calculate after score
  7. Read aloud, it should sound like a person wrote it
  1. 若已设置
    WRITING_STYLE_GUIDE_PATH
    环境变量，先加载对应的写作风格指南
  2. 从
    references/
    目录加载相关规则
  3. 扫描文本查找AI行文模式，计算改写前分数
  4. 对存在问题的部分进行改写
  5. 调整语气风格（参考
    voice-soul
    规则）
  6. 自我检查：扫描改写后的文本，确认是否存在相同的AI行文模式，计算改写后分数
  7. 朗读改写后的文本，确保读起来像是人类撰写的

Output

输出内容

Provide:
  1. Score report (before → after with category breakdown)
  2. The rewritten text
  3. Brief summary of changes
需输出以下内容：
  1. 评分报告（包含改写前后的分数及各分类明细）
  2. 改写后的文本
  3. 变更内容简要说明

Environment Variables

环境变量

VariableRequiredDescription
WRITING_STYLE_GUIDE_PATH
NoPath to shared writing style guide. Loaded before processing
变量名是否必填描述
WRITING_STYLE_GUIDE_PATH
否共享写作风格指南的路径，处理前会加载该文件

Reference

参考资料

Based on Wikipedia:Signs of AI writing.
基于维基百科《AI生成文本识别特征》指南：Wikipedia:Signs of AI writing