avoid-ai-writing

审计并重写内容，去除 AI 写作痕迹。这是一个适用于任何 AI Agent 的实用技能，支持仅检测和原地编辑模式，并支持语气风格设定。

快速演示

输入：

Certainly! Acme Analytics, a vibrant startup nestled in the heart of Boulder's thriving tech ecosystem, has secured $40M in Series B funding — marking a watershed moment for the observability landscape. The platform serves as a unified hub, featuring real-time dashboards, boasting sub-second queries, and presenting a seamless integration layer. Moreover, experts believe Acme is poised to disrupt the market. In conclusion, the future looks bright!

输出：

Acme Analytics raised a $40M Series B led by Sequoia. The Boulder-based startup makes an observability platform that runs queries in under a second and plugs into existing monitoring stacks without custom integration work.

它捕捉到了什么： 聊天机器人式开头（"Certainly!"）、促销语言（"vibrant," "nestled," "thriving"）、重要性膨胀（"watershed moment"）、系动词回避（"serves as," "featuring," "boasting"）、4 个单词替换、模糊引用（"experts believe"）、填充语（"Moreover"）、通用结论（"the future looks bright"）、过度打磨的 uniformity。一段话中有 15+ 处 AI 痕迹。

这个技能做什么

这个可移植的写作技能会审计并重写内容，去除 AI 写作模式（"AI-isms"）。它兼容 Claude Code、Claude Cowork、OpenClaw、Cursor、Hermes、OpenAI Codex、Windsurf、Cline、GitHub Copilot、Claude.ai Projects、ChatGPT Custom GPTs 以及其他 agentskills.io 兼容的 Agent。

三种模式：

• Rewrite（重写，默认） —— 标记 AI 模式并重写文本以修复它们。内置的第二遍检查会捕捉第一遍编辑后仍存留的模式。
• Detect（检测） —— 仅标记 AI 模式，不进行重写。显示哪些标记是真正的问题，哪些是判断性调用。当模式可能是故意的、当你审计不想被修改的内容、或当你只想快速扫描时，这个模式很有用。
• Edit（编辑） —— 使用 Edit 工具对文件进行原地编辑，做出最小的、有针对性的改动，保留已经是人类风格的段落。返回“已做修改 + 验证”报告，而不是整个文件。

可选的语气风格设定（casual / professional / technical / warm / blunt）决定散文听起来的语气，独立于受众背景设定。

为什么是技能，而不仅仅是提示词

一次性的“让这段话听起来像人写的”提示词只能抓住明显的问题。这个技能不同：

• 结构化审计 —— 以四个独立部分返回识别出的问题（含引用文本）、重写版本、变更摘要和第二遍审计。你可以看到到底改了什么、为什么改。
• 两遍检测 —— 第二遍会重新阅读重写结果，捕捉第一遍编辑后仍存留的模式：重复的过渡句、挥之不去的重要性膨胀、漏网的系动词替换。
• 112 条词汇替换表，分 3 个层级 + 10 条第 3 层级短语 —— 不是凭感觉。每个被标记的词都有具体的、更平实的替代词。“Leverage” → “use.”“Commence” → “start.”第 1 层词总是标记，第 2 层词在聚集时标记，第 3 层词仅在高密度时标记。第 1 层又分为 1A 频率标记（delve、tapestry）和 1B 清晰度修改（in order to、utilize）—— 修复方式相同，但只有 1A 是关于该段落如何产生的证据，并且 1B 权重较低，因此冗长修复不会把文档推向 AI 分类。第 3 层 短语（多词套话，如“the integration of”、“decentralized compute”）在逐短语重复时标记，或当一篇内容中堆叠 3+ 个不同短语时标记 —— 这就是 LLM 自我变化套话的形状。
• 61 个模式类别 —— 下面是代表性示例，每个都有改前/改后。包括结构检测（hashtag 堆砌、裸名词短语项目符号列表、多重对冲预测）、AI 工具指纹（占位符、引用标记、UTM 参数）、节奏/一致性检查、对话语域线索和作者端测试。完整目录位于 SKILL.md；这个数量在 CI 中会对照验证。
• Detect 模式 —— 不重写地标记模式。查看哪些标记是真正的问题，哪些是判断性调用。当模式可能是故意的或你在审计不想改动的内容时，这个模式很有用。
• 跨平台运行 —— 一个 SKILL.md 可在 Claude Code、Cowork（作为插件）、OpenClaw 和 Cursor（作为移植规则）中运行。

触发技能

安装后，让你的助手清理 AI 写作：

• "Remove AI-isms from this post"
• "Audit this draft for AI tells"
• "Make this sound less like AI"
• "Clean up AI writing in this paragraph"

在 rewrite 模式（默认）下，技能返回四个部分：

1. Issues found（发现的问题） —— 识别出的每一个 AI 痕迹，附引用文本
2. Rewritten version（重写版本） —— 去除所有 AI 痕迹的干净版本
3. What changed（改了什么） —— 主要编辑的摘要
4. Second-pass audit（第二遍审计） —— 重新阅读重写结果，捕捉任何存留的痕迹

在 detect 模式下，技能返回两个部分：

1. Issues found（发现的问题） —— 识别出的每一个 AI 痕迹，按严重程度（P0/P1/P2）分组
2. Assessment（评估） —— 哪些标记是明确问题，哪些可能是故意或上下文有效的模式

使用以下方式触发 detect 模式：“detect”、“flag only”、“audit only”、“just flag”、“scan”或类似短语。

模式参考

以下是目录中的代表性示例 —— 并非详尽列表（详尽列表在 SKILL.md）。技能的人类可读散文目录和检测引擎故意使用不同数量：引擎实现了 45 个 type 类别，因为它拆分词汇层级并添加了文体/指纹信号（标点分布、功能词熵、绕过技巧检测），这些信号是作为对文档的数学计算，而不是你可以查阅的规则。两者在 detector/CATEGORIES.md 中映射；不要“修正”一个数量去匹配另一个。

内容模式（Content Patterns）

#	模式	改前	改后
1	Significance inflation	"marking a pivotal moment in the evolution of..."	"was founded in 2019 to solve X"
2	Notability name-dropping	"cited in NYT, BBC, and Wired"	"In a 2024 NYT interview, she argued..."
3	Superficial -ing analyses	"symbolizing... reflecting... showcasing..."	Replace with specific facts or cut
4	Promotional language	"nestled within the breathtaking region"	"is a town in the Gonder region"
5	Vague attributions	"Experts believe it plays a crucial role"	"according to a 2019 survey by Gartner"
6	Formulaic challenges	"Despite challenges... continues to thrive"	Name the challenge and the response
7	Novelty inflation	"He introduced a term I hadn't heard before"	"He walked through how X works in practice"

语言模式（Language Patterns）

#	模式	改前	改后
8	Word/phrase replacements (3 tiers)	"leverage... robust... seamless... utilize"	"use... reliable... smooth... use"
9	Copula avoidance	"serves as... features... boasts"	"is... has"
10	Synonym cycling	"developers... engineers... practitioners... builders"	"developers" (repeat the clear word)
11	Template phrases	"a [adj] step towards [adj] infrastructure"	Describe the specific outcome
12	Filler phrases	"In order to," "Due to the fact that"	"To," "Because"
13	False ranges	"from the Big Bang to dark matter"	List the actual topics
14	Parenthetical hedging	"tools (like X and Y)"	Name them directly or cut

结构模式（Structure Patterns）

#	模式	改前	改后
15	Formatting	Em dashes (— and --), bold overuse, emoji headers, bullet-heavy	Commas/periods, prose paragraphs
16	Sentence structure	"It's not X, it's Y" + hollow intensifiers + hedging	Direct positive statements
17	Structural issues	Uniform paragraphs, formulaic openings, too-clean grammar	Varied length, lead with the point
18	Transition phrases	"Moreover," "Furthermore," "In today's [X]"	"and," "also," or restructure
19	Inline-header lists	"Speed: Speed improved by..."	Write the point directly
20	Title case headings	"Strategic Negotiations And Partnerships"	"Strategic negotiations and partnerships"
21	Numbered list inflation	"Here are 7 reasons why..."	Cut to the 2-3 that matter
22	False concession	"While X has limitations, it's still remarkable"	State the real tradeoff
23	Rhetorical question openers	"What if there were a better way to...?"	Lead with the claim

沟通模式（Communication Patterns）

#	模式	改前	改后
24	Chatbot artifacts	"I hope this helps! Let me know if..."	Remove entirely
25	"Let's" constructions	"Let's explore," "Let's break this down"	Just start with the point
26	Cutoff disclaimers	"While details are limited in available sources..."	Find sources or remove
27	Generic conclusions	"The future looks bright," "Only time will tell"	Specific closing thought or cut
28	Emotional flatline	"What surprised me most," "I was fascinated to discover"	Earn the emotion or cut the claim
29	Reasoning chain artifacts	"Let me think step by step," "Breaking this down"	State conclusion, then evidence
30	Sycophantic tone	"Great question!", "You're absolutely right!"	Remove entirely
31	Acknowledgment loops	"You're asking about," "To answer your question"	Just answer directly
32	Confidence calibration	"It's worth noting," "Interestingly," "Surprisingly"	Let the fact speak for itself

元模式（Meta Patterns）

#	模式	改前	改后
33	Excessive structure	5 headers in 200 words, "Overview:", "Key Points:"	Merge sections, use specific headers
34	Rhythm and uniformity	All sentences 15–25 words, all paragraphs same length	Mix short/long, fragments, questions
35	Over-polishing	Every irregularity sanded away, perfectly uniform prose	Keep natural disfluency, varied rhythm
36	Rewrite-vs-patch threshold	5+ vocabulary flags + 3+ pattern categories + uniform rhythm	Advise full rewrite, not patching

结构检测（v3.4）

在 v3.4 中加入，用于捕捉通过替换同义词绕过词汇表但仍依赖结构化形状的 LLM 输出。Crypto/web3/AI-infra 内容最集中地出现这些模式，但这些规则适用于任何社交长度的帖子。

#	模式	改前	改后
37	Tier 3 phrases (multi-word boilerplate)	"the integration of," "decentralized compute," "community-driven," "long-term sustainability" stacked across a piece	Replace the repeated phrase with a specific claim, or vary genuinely. Flagged per-phrase at ≥2 hits, or as a cluster when ≥3 distinct phrases appear
38	Future-narrative closers	"may become one of the most important narratives of the next market cycle"	Pick the falsifiable version. "X may exceed Y by 2027" is a prediction; the template form is not
39	Hedge-stacked predictions	"could potentially create," "may eventually unlock"	Pick one. Each hedge cancels the next
40	"Real/actual" adjective inflation	"real on-chain tokenomics," "actual reward sustainability"	Drop the empty intensifier and add the specific claim. Carve-out: "real on-chain settlement, not bridged IOUs" is honest contrastive writing — the AI tell is the unsaid contrast
41	Hashtag stuffing	15-tag trailing block: #AI #Crypto #Web3 #Innovation #FutureTech…	2-3 specific tags max, or none. Empirical threshold: 6+ tags is near-universal in LLM social output, rare in thoughtful human posts
42	Bullet lists of bare noun phrases	* Stable mining efficiency / Reliable pool connectivity / Optimized RandomX performance / Low failed share rates / Effective hardware utilization / Consistent thermal stability	Convert to prose, or rewrite each item as a full claim with a verb and a number. Carve-out: genuine list content (changelogs, parameter docs, ingredient lists) where bare NPs are correct

AI 工具指纹及后续补充（v3.5–3.8）

#	模式	改前	改后
43	Unfilled placeholders	[Your Name], [INSERT SOURCE], 2025-XX-XX	Fill in with real content or delete — shipped placeholders are a near-definitive tell
44	Chatbot citation markup	citeturn0search0, oai_citation, contentReference[oaicite:0]	Strip the markup token entirely
45	AI-tool URL parameters	utm_source=chatgpt.com, utm_source=copilot.com	Strip the tracking parameter; keep the URL if the link matters
46	Speculative gap-filling	"maintains a low profile," "likely began his career"	Cut the guess, or replace with a sourced fact
47	Hyphenated-pair overuse	"a high-quality, well-architected, future-proof solution"	Cut to the modifier that matters; no hyphen in predicate ("the report is high quality")
48	Infomercial engagement hooks	"The catch?", "The kicker?", "Here's the thing."	Delete the hook, state the thing
49	Vocabulary diversity (low TTR)	Narrow, repetitive word range across 200+ words	Broaden the what — name specific things, cite specific cases
50	Self-labeling significance	"That last move is the contrarian one," "This is the interesting part"	Cut the label; let the explanation carry the weight, or reposition the item so it stands out on its own
51	List-label periods	- **Intros.** Years of conferences and operator network. (also unbolded: - Intros. Years of...)	Use a colon, not a period, on a list label: - **Intros:** years of conferences and operator network.

对话语域模式（v3.15）

在一次真实交流中，一位维护者用“I prefer to talk human to human”指出了一条看起来像辅助生成的 GitHub issue 回复，此后加入了这些模式。两者都是判断性调用，而不是正则可检测的（普通人类段落和 AI 生成的段落可能结构相同；线索在于语域和多余的上下文，而不是固定形状）—— 参见 detector/CATEGORIES.md 的 §C 注释，了解为何第一次尝试“一堵文字墙检测器”被回滚。

#	模式	改前	改后
52	Wall-of-text replies	A 4+ sentence, sub-150-word reply delivered as one unbroken paragraph with no line breaks — the shape LLMs default to in issue/PR comments, chat, and DMs	Break at thought boundaries. One idea per line-group, the way a person actually types a reply
53	Recap-flattery opener	"Thanks for all the legwork here — the migration script and the rollback plan you worked through are what made this possible."	Substance first. If thanks is warranted, one plain clause without the recap: "Thanks for the legwork — this looks right to me"

分享帖框架（v3.20）

#	模式	改前	改后
54	Lingering-attention claims	"The line I keep coming back to:", "I can't stop thinking about this," "this has been rattling around in my head all week"	Open on the thing itself. Carve-out: keep the frame when a reason follows ("I keep coming back to exit-voice because it predicts who quits")

叙述式坦诚（v3.21）

#	模式	改前	改后
55	Narrated candor	"Two caveats I would rather flag than let you discover later:", "I want to be upfront:"	State the caveats. Judgment-only: the same words carry real content in conflict-of-interest disclosure ("in the interest of full disclosure, I own shares in…"), which a regex cannot separate from the empty frame

两个作者端测试补全了目录（判断性检查，而非自动检测）：段落重排免疫（能否交换两个正文段落而不破坏整篇文章？）和跑步机效应（“这一段实际上有什么新东西？”）。

完整示例

改前（AI 生成）：

Certainly! Here's a comprehensive overview of Acme's Series B.

Acme Analytics, a vibrant startup nestled in the heart of Boulder's thriving tech ecosystem, has secured $40M in Series B funding — marking a watershed moment for the company and the observability landscape at large. The round was led by Sequoia, with participation from Andreessen Horowitz, Y Combinator, and Index Ventures, underscoring the robust investor confidence in Acme's vision.

The platform serves as a unified hub for engineering teams, featuring real-time dashboards, boasting sub-second query performance, and presenting a seamless integration layer. It's not just another monitoring tool — it's a paradigm shift in how organizations navigate complex distributed systems. Experts believe Acme is poised to disrupt the $15B observability market. Studies show that companies utilizing comprehensive monitoring solutions can ascertain issues 40% faster.

• 🚀 Performance: The platform streamlines incident response, empowering engineers to resolve issues faster.
• 💡 Scale: Acme fosters collaboration across teams, from frontend developers to SRE practitioners to platform builders to infrastructure engineers.
• ✅ Adoption: Customer adoption continues to accelerate, reflecting broader industry trends.

Moreover, Acme's approach showcases the potential of modern observability — symbolizing a shift toward proactive monitoring, reflecting years of R&D investment, and highlighting the intricate interplay between data collection and actionable intelligence. Despite challenges common in the crowded monitoring space, Acme continues to thrive. In order to fully capitalize on this momentum, the company plans to expand its go-to-market endeavors.

In conclusion, the future looks bright for Acme Analytics. Only time will tell how this game-changer will reshape the observability paradigm. Feel free to reach out if you'd like more details!

改后（清理后）：

Acme Analytics raised a $40M Series B led by Sequoia. The Boulder-based startup makes an observability platform that runs queries in under a second and plugs into existing monitoring stacks without custom integration work.

The pitch is speed. Their median time-to-resolution is 12 minutes, compared to the 45-minute industry average that Datadog reported in 2024. That gap is why 380 companies are paying for it.

They'll use the money to hire sales reps in EMEA and add log management. The monitoring market is crowded, but Acme's bet is that most teams still stitch together three or four tools and lose time switching between them.

这个技能捕捉到了什么： 聊天机器人痕迹（Certainly!, Feel free to reach out）、3 个 em dash、促销语言（vibrant, nestled, thriving）、重要性膨胀（watershed moment）、系动词回避（serves as, featuring, boasting, presenting）、10 个单词替换（landscape, robust, seamless, paradigm, streamline, empower, foster, utilize, ascertain, endeavor）、同义词循环（developers/practitioners/builders/engineers）、否定平行结构（It's not just X, it's Y）、知名度点名人（Sequoia, a16z, YC, Index stacked for credibility）、模糊引用（Experts believe, Studies show）、填充短语（In order to, Moreover）、带 emoji 的内联标题列表、浅层 -ing 分析（symbolizing... reflecting... highlighting...）、公式化挑战（Despite challenges... continues to thrive）、通用结论（the future looks bright, only time will tell）、采纳要点中隐含的错误范围。

那是 35+ 处 AI 痕迹。

检测引擎

这个技能内置一个确定性的、零依赖的检测引擎，位于 detector/ —— 也就是上面规则描述的同一个 45 类别引擎，作为可运行代码。它可以在 Node (>=18) 和浏览器中运行，无需构建步骤。

它也是数字分数的唯一来源：技能本身（以及 detect 模式）报告哪些模式存在以及严重程度（P0/P1/P2），引擎将它们转换为一个计算出的 0–100 score。SKILL.md 中刻意没有第二个散文式估算分数 —— 一个评分器，而不是两个。

引擎还附带一个保留验证器。detector/validate.js 会将重写结果与原文进行比较，并在编辑触及了不该触及的内容时失败：代码块、YAML frontmatter、blockquote、表格单元格、行内代码、URL、文件路径、标题结构，或当重写结果以比开始时更多的标记模式结束时。

免责声明

这是一个独立的个人项目，与任何公司无关、未受任何公司赞助或背书。所有表达的观点均为我自己的。

许可证

MIT