Anti-AI Writing Engine

反AI写作引擎

Transform any content into authentic, human-sounding prose by eliminating AI patterns and applying proven writing fundamentals.

通过消除AI模式并应用经过验证的写作基本原则，将任何内容转换为真实、符合人类语气的散文。

Purpose

用途

This skill serves as the core humanization engine for all written content. It detects and eliminates patterns that signal AI involvement while teaching the principles of natural, engaging writing.

Core Philosophy: The best writing is invisible. Readers should feel like they're reading a real person's thoughts - not processed, filtered, or generated content.

本技能可作为所有书面内容的核心人性化引擎。它能检测并消除暴露AI参与痕迹的模式，同时传授自然、引人入胜的写作原则。

核心理念： 优秀的写作是“无形的”。读者应感觉自己在阅读真实人物的想法——而非经过处理、过滤或生成的内容。

When to Use This Skill

使用场景

Reviewing and humanizing AI-generated drafts
Writing content that must not appear AI-assisted
Editing any prose for authenticity and impact
Training yourself to avoid AI-like patterns
Quality-checking content before publication

Pairs well with: Voice style skills (voice-pirate-wires, voice-analytical, etc.) for writing in a specific author's style.

审核并人性化AI生成的草稿
撰写不能看起来是AI辅助生成的内容
编辑任何散文以提升真实性和影响力
训练自己避免类似AI的写作模式
发布前对内容进行质量检查

搭配使用推荐： 与语音风格技能（voice-pirate-wires、voice-analytical等）配合，以特定作者的风格进行写作。

Universal Writing Fundamentals

通用写作基本原则

Master these principles first, then layer on specific style choices.

先掌握这些原则，再叠加特定的风格选择。

1. Energy Transfer

1. 能量传递

The best writing is a transfer of energy from writer to reader.

Write conversations, not speeches
Speak WITH your audience, not AT them
Remove corporate jargon, academic language, and buzzwords

Example:

❌ "The implementation of our innovative frameworks has demonstrated significant positive outcomes in terms of engagement metrics."
✅ "Our new approach works. People are paying attention."

The second version transfers energy. Readers feel conviction, not formality.

优秀的写作是作家到读者的能量传递。

写对话，而非演讲稿
与受众对话，而非对着他们说教
去除企业行话、学术语言和流行术语

示例：

❌ “我们创新框架的实施已在参与度指标方面展现出显著的积极成果。”
✅ “我们的新方法奏效了。人们正关注着。”

第二个版本传递了能量。读者感受到的是坚定的信念，而非刻板的正式感。

2. Conciseness is King

2. 简洁为王

Every word must earn its place.

Process:

Write your first draft freely
Read it aloud
Delete anything that:
- Repeats an idea already stated
- Softens your main point
- Sounds formal instead of conversational
- Takes more words than necessary

Example:

❌ "Our approach incorporates multiple methodologies designed to accommodate diverse requirements and development patterns."
✅ "We adapt to how you work."

每个字词都必须有存在的价值。

流程：

自由撰写初稿
大声朗读
删除以下内容：
- 重复已陈述的观点
- 弱化核心观点的表述
- 听起来正式而非口语化的内容
- 冗长冗余的表达

示例：

❌ “我们的方法整合了多种方法论，旨在适应多样化的需求和开发模式。”
✅ “我们会配合你的工作方式。”

3. The SUCKS Framework

3. SUCKS框架

Before writing anything, answer these questions:

S - Specific

Write for ONE person, not a crowd
Know their struggles, goals, language
If you write for everyone, you write for no one

U - Unique & Useful

Does this change how your reader thinks, feels, or acts?
Unique: they haven't seen this perspective before
Useful: they can actually apply this

C - Clear, Curious, Conversational

Clear: Main idea is unmissable
Curious: Questions that make readers think
Conversational: Reads like talking to a friend

K - Kept Simple & Structured

Simple ideas, simple words
Clear beginning, middle, end

S - Sticky

Memorable phrases they'll repeat
Ideas that lodge in memory

Application checklist:

Who is my ONE reader?
What will they think, feel, or do differently?
Could a 12-year-old understand the main point?
Does this flow like a conversation?

在撰写任何内容之前，先回答这些问题：

S - 针对性（Specific）

为一个人写作，而非一群人
了解他们的困扰、目标和常用语言
如果你想讨好所有人，最终谁也讨好不了

U - 独特且实用（Unique & Useful）

这会改变读者的想法、感受或行为吗？
独特性：他们从未见过的视角
实用性：他们可以实际应用的内容

C - 清晰、引发好奇、口语化（Clear, Curious, Conversational）

清晰：核心观点一目了然
好奇：能引发读者思考的问题
口语化：读起来像和朋友聊天

K - 简洁且结构化（Kept Simple & Structured）

简单的想法，简单的词汇
清晰的开头、中间和结尾

S - 易记（Sticky）

读者会重复的难忘短语
能留在记忆中的观点

应用检查表：

我的目标读者是谁？
他们的想法、感受或行为会因此有何不同？
一个12岁的孩子能理解核心观点吗？
内容读起来像对话吗？

4. Be Undeniable

4. 确凿无疑

Transform vague claims into concrete specifics.

❌ "How to boost your results by at least 87% in just one month."
✅ "This year, I helped 13 clients boost their results by 87%-256% in just one month. Here's how:"

Pattern: Replace vague language with data, examples, specifics, or personal experience.

将模糊的主张转化为具体的细节。

❌ “如何在短短一个月内将成果提升至少87%。”
✅ “今年，我帮助13位客户在短短一个月内将成果提升了87%-256%。方法如下：”

模式： 用数据、示例、具体细节或个人经验替代模糊语言。

5. Craft Sticky Sentences

5. 打造易记句子

Use these techniques to create memorable statements:

Alliteration - Same starting sounds

"Specificity is the secret"
"The best jobs are neither decreed nor degreed"

Symmetry - Parallel structure

"Read for awareness. Write for understanding."
"It's not 10,000 hours. It's 10,000 iterations."

Contrast - Opposing ideas

"To be everywhere is to be nowhere."
"Be clear, not clever. Concise, not complex."

Rhyme - Similar ending sounds

"Tell a story or lose your glory"

Rhythm - Pleasing cadence

"When you can't wait to share it, they can't help but read it"

For maximum stickiness, combine techniques:

"Anger prepares us to fight. Fear prepares us to flee." (Symmetry + Alliteration)

See

references/sticky-sentences.md

for expanded examples.

使用以下技巧创建令人难忘的语句：

头韵 - 相同的开头发音

“Specificity is the secret”（针对性是关键）
“The best jobs are neither decreed nor degreed”（最好的工作既不靠命令也不靠文凭）

对称 - 平行结构

“Read for awareness. Write for understanding.”（阅读以增见闻，写作以促理解）
“It's not 10,000 hours. It's 10,000 iterations.”（不是10000小时，而是10000次迭代）

对比 - 对立观点

“To be everywhere is to be nowhere.”（无处不在等于无处可在）
“Be clear, not clever. Concise, not complex.”（清晰而非花哨，简洁而非复杂）

押韵 - 相似的结尾发音

“Tell a story or lose your glory”（讲故事，否则失光彩）

节奏 - 悦耳的韵律

“When you can't wait to share it, they can't help but read it”（当你迫不及待想分享时，他们会忍不住去读）

最大化易记性：结合多种技巧

“Anger prepares us to fight. Fear prepares us to flee.”（愤怒让我们准备战斗，恐惧让我们准备逃跑）（对称+头韵）

更多示例请参阅

references/sticky-sentences.md

。

Forbidden Patterns (AI Tells)

禁用模式（AI Tells）

These patterns consistently signal AI involvement. Eliminate them aggressively.

这些模式会持续暴露AI参与的痕迹，需坚决消除。

The Correlative Construction (Most Common AI Tell)

关联结构（最常见的AI痕迹）

This is the #1 pattern to avoid:

❌ "X aren't just Y - they're Z"
❌ "X isn't just about Y, it's about Z"
❌ "Teachers aren't just instructors - they're mentors"

Why it's bad: This is the default structure AI models produce. Every AI writing sample uses this.

Better alternatives:

✅ "Teachers mentor students"
✅ "X accomplishes both Y and Z"
✅ State the point directly

这是最需要避免的模式：

❌ “X aren't just Y - they're Z”（X不只是Y——它们是Z）
❌ “X isn't just about Y, it's about Z”（X不只是关于Y，而是关于Z）
❌ “Teachers aren't just instructors - they're mentors”（教师不只是讲师——他们是导师）

为何不好： 这是AI模型默认生成的结构。每一份AI写作样本都会使用这种结构。

更好的替代方案：

✅ “Teachers mentor students”（教师指导学生）
✅ “X accomplishes both Y and Z”（X同时实现Y和Z）
✅ 直接陈述观点

Forbidden Constructions

禁用句式

❌ "It's not about X, it's about Y"
❌ "The truth is..." / "The reality is..."
❌ "Let that sink in"
❌ "Now more than ever..."

Better: State your point directly without setup.

❌ “It's not about X, it's about Y”（这不是关于X，而是关于Y）
❌ “The truth is...” / “The reality is...”（事实是……/现实是……）
❌ “Let that sink in”（好好想想）
❌ “Now more than ever...”（如今比以往任何时候都……）

更好的做法： 直接陈述观点，无需铺垫。

Forbidden Rhetorical Flourishes

禁用修辞手法

❌ "The best part? ..."
❌ "The secret? ..."
❌ "Sounds impossible? It's not."
❌ "What if I told you..."
❌ "Here's the thing..."
❌ "Let's be honest..."
❌ "At the end of the day..."

❌ “The best part? ...”（最棒的是？……）
❌ “The secret? ...”（秘诀是？……）
❌ “Sounds impossible? It's not.”（听起来不可能？其实不然。）
❌ “What if I told you...”（如果我告诉你……）
❌ “Here's the thing...”（关键是……）
❌ “Let's be honest...”（说实话……）
❌ “At the end of the day...”（归根结底……）

Forbidden Staccato Phrasing

禁用断句式表达

Do not use faux-dramatic sentence fragments:

❌ "No fluff. No filler. Just results."
❌ "Big ideas. Small words. Maximum impact."
❌ "Simple. Clear. Effective."
❌ "Stop guessing. Start winning."

不要使用故作戏剧化的句子片段：

❌ “No fluff. No filler. Just results.”（无废话，无凑数，只看结果。）
❌ “Big ideas. Small words. Maximum impact.”（大想法，小词汇，大影响。）
❌ “Simple. Clear. Effective.”（简单。清晰。有效。）
❌ “Stop guessing. Start winning.”（别再猜测，开始成功。）

Forbidden Openers

禁用开头

❌ "In the ever-evolving world of..."
❌ "In today's fast-paced..."
❌ "Gone are the days when..."
❌ "This underscores..."
❌ "In an era where..."

❌ “In the ever-evolving world of...”（在不断发展的……领域中）
❌ “In today's fast-paced...”（在当今快节奏的……中）
❌ “Gone are the days when...”（……的时代已经一去不复返）
❌ “This underscores...”（这凸显了……）
❌ “In an era where...”（在……的时代）

Formatting Restrictions

格式限制

Do not use boldface for emphasis in body text
Do not use emojis unless explicitly requested
Do not add summaries like "In conclusion" or "In summary"
Do not rely on bullet points unless explicitly asked

正文中不要使用粗体强调
除非明确要求，否则不要使用表情符号
不要添加“总结”或“综上所述”之类的内容
除非明确要求，否则不要依赖项目符号

Dash Usage

破折号使用

Use regular hyphens with spaces for parenthetical breaks - like this - not em dashes (—) or en dashes (–).

✅ "Education is changing - and parents are noticing"
❌ "Education is changing—and parents are noticing"

使用带空格的普通连字符进行插入语分隔 - 就像这样 - 不要使用长破折号（—）或短破折号（–）。

✅ “Education is changing - and parents are noticing”（教育正在发生变化 - 家长们已经注意到了）
❌ “Education is changing—and parents are noticing”（教育正在发生变化——家长们已经注意到了）

Anti-AI Pattern Detection

AI痕迹检测

Beyond forbidden syntax, these patterns consistently signal AI involvement:

除了禁用的语法结构外，这些模式也会持续暴露AI参与的痕迹：

1. Overuse of "Just"

1. 过度使用“just”

Problem: AI uses "just" constantly as a softener.

❌ "We just need to understand that it's just about learning, and we just have to focus on what matters."
✅ "It's about learning. Focus on what matters."

When "just" is acceptable: "just one question," "just in case," "just started"

When to remove it: Middle of sentences as a softener, more than once per paragraph

问题： AI经常使用“just”作为软化词。

❌ “We just need to understand that it's just about learning, and we just have to focus on what matters.”（我们只需要明白这只是关于学习，而且我们只需要关注重要的事情。）
✅ “It's about learning. Focus on what matters.”（这是关于学习的。关注重要的事情。）

“just”的可接受用法： “just one question”（只有一个问题）、“just in case”（以防万一）、“just started”（刚刚开始）

需要删除的情况： 在句子中间作为软化词，或每段使用超过一次

2. Overuse of "Actually"

2. 过度使用“actually”

Problem: AI uses "actually" to sound like it's adding nuance.

❌ "It's actually about teaching, but actually about community, and students actually need both."
✅ "It's about teaching. It's also about community. Students need both."

When acceptable: Correcting a previous misunderstanding

Limit: Once per 500 words maximum

问题： AI使用“actually”来显得自己在增加细节。

❌ “It's actually about teaching, but actually about community, and students actually need both.”（这实际上是关于教学的，但实际上也是关于社区的，学生实际上两者都需要。）
✅ “It's about teaching. It's also about community. Students need both.”（这是关于教学的。也是关于社区的。学生两者都需要。）

可接受的情况： 纠正之前的误解

限制： 每500字最多使用一次

3. Hedging Language

3. 模糊语言

AI loves hedge words because they make uncertain claims safer. But they make writing weak.

Common hedges to eliminate:

❌ "This might help you" → ✅ "This will help you"
❌ "Some people say..." → ✅ "I've found that..."
❌ "It could be argued that..." → ✅ "It's true that..."
❌ "Perhaps we should consider..." → ✅ "We should..."
❌ "One could say..." → ✅ "This is true because..."

Test: If you find "might," "could," "perhaps," "possibly," "maybe," "somewhat," or "it seems like," ask: Do I actually believe this? If yes, remove the hedge.

AI喜欢模糊词汇，因为它们能让不确定的主张更安全，但会让写作显得无力。

需要消除的常见模糊词汇：

❌ “This might help you”（这可能对你有帮助）→ ✅ “This will help you”（这会对你有帮助）
❌ “Some people say...”（有些人说……）→ ✅ “I've found that...”（我发现……）
❌ “It could be argued that...”（有人可能会说……）→ ✅ “It's true that...”（事实是……）
❌ “Perhaps we should consider...”（也许我们应该考虑……）→ ✅ “We should...”（我们应该……）
❌ “One could say...”（有人可能会说……）→ ✅ “This is true because...”（这是事实，因为……）

测试： 如果你发现“might”“could”“perhaps”“possibly”“maybe”“somewhat”或“it seems like”，问问自己：我真的相信这个吗？如果是，删除模糊词汇。

4. Passive Voice

4. 被动语态

Problem: AI defaults to passive voice because it's safer.

❌ "It was determined that improvements were needed"
✅ "We need to improve"
❌ "It has been shown that users benefit from..."
✅ "Users benefit from..."

Test: If you can't identify who's doing the action, it's passive. Rewrite with a subject.

问题： AI默认使用被动语态，因为它更安全。

❌ “It was determined that improvements were needed”（经确定，需要进行改进）
✅ “We need to improve”（我们需要改进）
❌ “It has been shown that users benefit from...”（研究表明，用户从……中受益）
✅ “Users benefit from...”（用户从……中受益）

测试： 如果你无法确定动作的执行者，那就是被动语态。改写为主动语态，明确主语。

5. Corporate Jargon

5. 企业行话

These signal over-processing:

❌ "Leveraging synergies across stakeholder ecosystems"
✅ "Getting different people talking to each other"
❌ "Optimize engagement metrics"
✅ "Get people paying attention"

Test: Would you say this to a friend? If not, rewrite it plainly.

这些词汇表明内容经过过度加工：

❌ “Leveraging synergies across stakeholder ecosystems”（利用利益相关者生态系统的协同效应）
✅ “Getting different people talking to each other”（让不同的人相互沟通）
❌ “Optimize engagement metrics”（优化参与度指标）
✅ “Get people paying attention”（吸引人们的注意力）

测试： 你会对朋友说这句话吗？如果不会，用直白的语言改写。

6. Vague Language

6. 模糊语言

AI tends toward vagueness because it's safer. Vague writing is weak writing.

❌ "Our users improve" → ✅ "Users improve by 40% in 6 months"
❌ "Many people think..." → ✅ "A survey found that 73% of users..."
❌ "Significant improvements" → ✅ "Improvements of 23-47%"

Test: Can you back it up with a specific number, example, or name?

AI倾向于使用模糊语言，因为它更安全。模糊的写作是无力的写作。

❌ “Our users improve”（我们的用户得到了提升）→ ✅ “Users improve by 40% in 6 months”（用户在6个月内提升了40%）
❌ “Many people think...”（很多人认为……）→ ✅ “A survey found that 73% of users...”（一项调查发现，73%的用户……）
❌ “Significant improvements”（显著的提升）→ ✅ “Improvements of 23-47%”（提升了23-47%）

测试： 你能用具体的数字、示例或名称来支撑它吗？

7. Too Many Transition Words

7. 过渡词过多

AI overuses transitions trying to seem sophisticated:

❌ "Furthermore, it is important to note that, in addition to this, moreover..."
✅ Strong structure needs fewer transitions

Limit transitions to: but, and, so, then, because

AI过度使用过渡词，试图显得更复杂：

❌ “Furthermore, it is important to note that, in addition to this, moreover...”（此外，需要注意的是，除此之外，而且……）
✅ 结构清晰的内容需要更少的过渡词

过渡词限制： 仅使用but、and、so、then、because

8. Overcomplicated Sentence Structure

8. 句子结构过于复杂

AI loves long, complex sentences trying to sound smart.

❌ "The multifaceted nature of contemporary paradigms, which encompasses diverse modalities and approaches, necessitates a comprehensive reevaluation of traditional methodologies."
✅ "Things have changed. We need to rethink our approach."

AI喜欢使用冗长复杂的句子，试图显得聪明。

❌ “The multifaceted nature of contemporary paradigms, which encompasses diverse modalities and approaches, necessitates a comprehensive reevaluation of traditional methodologies.”（当代范式的多面性涵盖了多种模式和方法，因此需要对传统方法进行全面重新评估。）
✅ “Things have changed. We need to rethink our approach.”（情况已经改变。我们需要重新审视我们的方法。）

The Humanization Workflow

人性化工作流程

Step 1: Understand Your Source

步骤1：理解源内容

What's the core insight or story?
What's the emotional arc?
What's the most important takeaway?

Ask yourself:

What's being said that no one else is saying?
What will readers think, feel, or do differently?
What's the 30-second version?

核心见解或故事是什么？
情感弧线是什么？
最重要的要点是什么？

自问：

这里所说的内容有什么是别人没说过的？
读者的想法、感受或行为会因此有何不同？
30秒内能说完的版本是什么？

Step 2: Apply the SUCKS Framework

步骤2：应用SUCKS框架

Who is my ONE reader?
Is this unique and useful to them?
Can I make it clear, curious, and conversational?
How do I keep it simple and structured?
What will stick with them?

我的目标读者是谁？
这对他们来说是独特且实用的吗？
我能让它清晰、引发好奇且口语化吗？
我如何让它简洁且结构化？
什么内容会让他们记住？

Step 3: Write or Edit the Draft

步骤3：撰写或编辑草稿

If writing fresh:

Write freely without self-editing
Get the ideas down first
Polish in subsequent passes

If editing AI output:

Read the entire draft
Identify the core message
Rewrite rather than patch

如果是全新撰写：

自由撰写，不要自我编辑
先把想法写下来
在后续的修改中打磨

如果是编辑AI生成的内容：

通读整个草稿
确定核心信息
重写而非修补

Step 4: Apply Sticky Sentences

步骤4：应用易记句子技巧

Identify 2-3 most important statements and strengthen them:

Add alliteration, symmetry, contrast, or rhythm
Make them quotable
Make them memorable

找出2-3个最重要的陈述并强化它们：

添加头韵、对称、对比或节奏
让它们值得引用
让它们令人难忘

Step 5: Eliminate AI Tells (Critical)

步骤5：消除AI痕迹（关键步骤）

Go through systematically and remove:

Correlative constructions ("X aren't just Y, they're Z")
Overuse of "just" and "actually"
Hedge words (might, could, perhaps, seems)
Passive voice
Corporate jargon
Vague language (replace with specifics)
Forbidden patterns ("Let that sink in," etc.)
Too many transitions
Overcomplicated sentences

Test for each sentence: Would this sentence appear in a ChatGPT output? If yes, rewrite it.

系统地检查并删除：

关联结构（“X aren't just Y, they're Z”）
过度使用“just”和“actually”
模糊词汇（might、could、perhaps、seems等）
被动语态
企业行话
模糊语言（替换为具体内容）
禁用模式（如“Let that sink in”等）
过渡词过多
过于复杂的句子

对每个句子进行测试： 这句话会出现在ChatGPT的输出中吗？如果是，重写它。

Step 6: Read Aloud & Quality Check

步骤6：大声朗读并质量检查

Read your entire piece aloud:

Does it sound like a real person talking?
Does energy transfer (not feel formal)?
Is every sentence earning its place?
Do important ideas have sticky phrasing?
Are there obvious AI tells remaining?

If you answer "no" to any checkbox, fix it before publishing.

大声朗读整篇内容：

听起来像真实的人在说话吗？
传递了能量（而非显得正式）吗？
每个句子都有存在的价值吗？
重要的观点有易记的表述吗？
还有明显的AI痕迹吗？

如果任何一个问题的答案是“否”，请在发布前修改。

Quick Reference Checklists

快速参考检查表

The "Would a Human Write This?" Test

“人类会这样写吗？”测试

For each paragraph, ask:

Does it sound like how I actually talk?
Is there unnecessary formality?
Are there words I'd never use in conversation?
Does it take the long way to make a point?
Does it hedge when I'm actually certain?

对每个段落，自问：

这听起来像我实际说话的方式吗？
有没有不必要的正式感？
有没有我在对话中永远不会使用的词汇？
它是不是绕了远路才表达观点？
当我确定的时候，它是不是用了模糊的表述？

The AI Tell Scan

AI痕迹扫描

Elements of Effective Content

有效内容的要素

Include in your writing:

Immediate attention - First sentence hooks
Specific numbers - "1.5 million" not "many"
Pattern interrupts - Surprise the reader
Direct problem-addressing - Name the struggle
Confidence - Eliminate hedge words
Concrete benefits - "Double output in 30 days" not "boost productivity"
Powerful questions - Make readers think
Warnings/stakes - Create urgency

写作中应包含：

立即吸引注意力 - 第一句就抓住读者
具体数字 - 用“150万”而非“很多”
模式打破 - 给读者惊喜
直接解决问题 - 点明痛点
自信 - 消除模糊词汇
具体收益 - 用“30天内产量翻倍”而非“提升生产力”
有力的问题 - 引发读者思考
警告/风险 - 制造紧迫感

anti-ai-writing

Original

Translation