Humanizer 会改写带有 AI 腔调的文本，使其读起来像由真人写成，同时不改变原意。它本身只是 Markdown，因此可用于任何支持 skills 的 Agent。

使用 Skills CLI 安装 Humanizer：

npx skills add blader/humanizer --global

不加 --global 则只会在当前项目中安装 Humanizer。可添加 --agent <name> 或 --agent '*'，指定哪些 Agent 接收该 Skill，然后重新加载它们的 skills。该 Skill 响应命令 /humanizer。

Claude Code 2.1.142 或更新版本也可以改用插件方式安装：

/plugin marketplace add blader/humanizer
/plugin install humanizer@humanizer

该插件响应命令 /humanizer:humanizer。

在 Claude Desktop 中，请将此仓库下载为 ZIP 文件，并将其作为 Skill 上传。若要手动安装，请将 SKILL.md 复制到 Agent 的 skill 文件夹中。

直接调用该 Skill：

/humanizer

[在这里粘贴你的文本]

或者用自然语言提出请求：

请将这段文本改写得更像人类写作：[你的文本]

若要改写文件，请向 Humanizer 提供其路径：

将 docs/launch-post.md 中的散文内容人性化改写

如果希望改写结果更像你的写作风格，请附上一个样本：

/humanizer

以下是我的写作样本，用于匹配写作语气：
[粘贴 2-3 段你自己的文字]

现在请将以下文本人性化改写：
[粘贴需要人性化改写的 AI 文本]

Humanizer 会遵循样本的节奏、措辞、标点和有意保留的个人习惯，包括你使用破折号时的方式。

语言模型会生成最可能接续出现的内容，因此默认会选择适用于最广泛读者和主题的表达。人类则是为某一位读者、某一个主题做选择。Humanizer 查找的每一种痕迹，都是这种默认选择的表现：用来暗示重要性而非补充事实的句子、按规则套用的节奏或格式、被包装成关键事件的普通事实，或是聊天过程中遗留下来的文本。

“LLM 使用统计学算法来猜测接下来应该出现什么。结果往往趋向于最具统计可能性、且适用于最广泛情形的表达。”维基百科，“Signs of AI writing”

Humanizer 会标记找到的每一项痕迹，并按显著程度排序。它会在不将原始结构视为固定框架的前提下起草改写稿，再依据这些模式和原始论断检查草稿，最后写出最终版本。它不会编造内容。姓名、数字、日期、引文、引用来源或其他事实细节都必须来自原文或作者；如果某个句子需要缺失的细节，Humanizer 会询问，而不是虚构。

粘贴文本时，Humanizer 会展示其工作过程：第一版改写、对仍显得不自然之处的简短评析，以及最终版本。对文件执行操作时，它只修改散文文字，保留代码、数据、frontmatter 和链接目标不变。个人写作会保留作者的观点和个人习惯；技术和参考类文本则保持中性、朴素。

这些模式按强度和出现频率编号。前五项只要出现一次，就足以支持编辑。标记为 单独出现时较弱 的模式，只有在同一段落中出现多种痕迹时才计入，因为谨慎的作者可能会有意使用其中任意一种。

A. 铺垫而非直接陈述

| 模式 | 修改前 | 修改后

---|---|---|---
1 | 不是 X，而是 Y | “这不仅仅是 X，而是 Y”“这并不意味着 X，而是意味着 Y。” | 直接陈述观点
2 | 单句收尾和戏剧化短句 | 每个章节后都写“这才是真正的胜利。”；“没有先例。没有怀旧。” | 删除重复内容的收尾句；将短句合并为具体论断
3 | 听起来深刻的套话 | “归根结底，重要的是……”“对称是信任的语言” | 用具体论断替换套话
4 | 在观点前刻意铺垫 | “让我们深入看看”“说实话？这要看情况……” | 删除铺垫，直接陈述观点
5 | 与不存在的人争辩 | “这主要不是关于……”“一种诱人的做法会是……” | 删除未被提出的异议或虚假的选项；保留任何真实论断

| 模式 | 修改前 | 修改后

---|---|---|---
6 | 强行凑成三项 | “创新、灵感和洞察”；三个例子加一条结论 | 根据表达所需使用恰当数量的项目
7 | 重复的句子开头 | “她指出……她指出……她提交了……” | 合并句子或更换主语
8 | 把破折号当作万能连接符 (单独出现时较弱) | “机构——而不是人——然而这种情况仍在继续——” | 使用句号、逗号、冒号或括号；若样本使用破折号，则匹配样本
9 | 叠加限定词 (单独出现时较弱) | “可以潜在地或许被认为” | 只保留来源能够支持的限定词
10 | 到处使用连字符短语 (单独出现时较弱) | “该团队是跨职能的” | 只保留语法需要的连字符
11 | 被动语态和缺失主语 (单独出现时较弱) | “不需要配置文件” | 在有帮助时说明行为主体

C. 夸大与借用权威

| 模式 | 修改前 | 修改后

---|---|---|---
12 | 过度使用的 AI 词汇 | “深入探讨……证明……格局……展示” | 使用朴素的词语；SKILL.md 中的列表是唯一词汇表
13 | 夸大意义 | “标志着一个关键时刻”“尽管面临挑战……仍持续蓬勃发展”“未来一片光明” | 保留事实，删除意义拔高；以最后一个具体事实收尾
14 | 模糊的关联或联系 | “与……领导层相关”“与……有关联” | 陈述来源提供的具体关系
15 | 浅层的 -ing 附加分句 | “象征着……反映着……展示着……” | 只保留来源支持的内容
16 | 营销语言 | “坐落于令人叹为观止的地区之中” | 直接说明该事物是什么
17 | 借用权威 | “专家认为……”“被《纽约时报》、BBC、FT 和《印度教徒报》引用” | 指明真实来源及其所述内容，或删除该论断或列表
18 | 回避使用 is、are 和 has | “充当……拥有……以……为特色” | “是……有……”

| 模式 | 修改前 | 修改后

---|---|---|---
19 | 把加粗当作装饰 | “OKRs、KPIs”；“**绩效：**绩效有所改善” | 删除加粗；将带标签的列表改写为散文
20 | 装饰性标题 | “战略谈判与合作伙伴关系”“🚀 发布阶段：” | 使用句首字母大写风格；移除 emoji 和箭头
21 | 弯引号 (单独出现时较弱) | said “the project” | said "the project"

E. 来自聊天和草稿的残留

| 模式 | 修改前 | 修改后

---|---|---|---
22 | 聊天机器人残留 | “问得好！……希望这对你有帮助！” | 删除包装语，保留内容
23 | 知识时限免责声明和猜测 | “虽然现有来源提供的细节有限，但似乎……” | 陈述来源显示的内容，或删除该句
24 | 首句重复标题 | “## 性能” + “速度很重要。” | 让标题承担其作用
25 | 谈论上一个版本 | “添加此函数是为了替代……” | 描述它现在的作用

作者随草稿提供了这些备注，因此改写可以使用它们：旅行是在去年 10 月，酒店位于阿尔法玛（Alfama），蛋挞是在格拉萨（Graça）一家小店吃的，有轨电车行程约四十分钟。没有这类备注时，Humanizer 会询问，而不是编造。

修改前（带有 AI 腔调）：

我最近在里斯本度过了难以忘怀的五天，让我告诉你——这座城市完全偷走了我的心。从抵达的那一刻起，我就知道自己来到了一个真正特别的地方。

里斯本坐落在塔霍河畔，是葡萄牙不朽精神的鲜活证明，浓厚的历史与现代活力在每一个转角交织。没错，著名的山丘很有挑战性——我的双腿确实感受到了！——但每一次攀登都会带来令人惊叹的全景，令一切都值得。

任何旅行如果没有乘坐标志性的 28 路有轨电车、穿行于这座城市最具历史感的街区，就算不上完整。食物呢？简直绝妙。贝伦蛋挞店（Pastéis de Belém）的原版蛋挞是备受喜爱的国民珍宝，品尝一枚仍然温热的蛋挞，是我永远不会忘记的时刻。

但真正让里斯本特别的并不只是景点——而是那种感觉。离开主要广场随意走几步，你就会发现更安静、更真实的一面：阳光洒满的小巷、迷人的瓷砖立面，以及友善的当地人过着日常生活，邀请你放慢脚步，品味每一个瞬间。

当然，必看的圣乔治城堡（São Jorge Castle）可俯瞰下方屋顶，景色惊艳。队伍可能很长，但对于任何历史爱好者或好奇的旅行者而言，这段体验绝对值得。

我会再去吗？当然。里斯本不仅是一个可以游览的地方——更是一个会让你一次又一次爱上的地方。如果你正梦想着下一次出游，这个目的地将带来终生难忘的回忆。✨

修改后：

去年十月我在里斯本待了五天，到现在对它的感觉还是有些矛盾。漂亮，没错。也比任何人警告过的更伤膝盖。

山坡几乎就是这座城市的全部故事，但宣传册不知怎么从不提它们。我的酒店在阿尔法玛，拍照确实很好看；但实际意味着每次想喝咖啡，都得爬一段感觉像六层楼高的楼梯。到第二天，我的小腿已经有意见了。我开始按哪条路下坡来规划每次步行，这是一种奇怪的看城市方式，但大概也是诚实的方式。

人人都说要坐 28 路有轨电车，所以我坐了：被挤在陌生人的背包旁边四十分钟，三个旅行团还在拍同一个街角。下次我会步行走这条路线，或者早餐前去。不过蛋挞确实值得这么大的名气。我在格拉萨一家朴素的小店吃了一枚，还是温热的；大约三十秒里，我理解了为什么有人会为了甜点专门安排行程。

我没想到的是，离开主要广场后这座城市会变得这么安静。从任何一个广场往上坡走两个街区，眼前就是晾衣绳、斑驳的瓷砖、敞开的窗户，还有把电视声音开得很大的老人看足球。那才是我一直惦记的里斯本，不是城堡。

城堡还行。景色很好，队伍很长，而我花在朝入口缓慢挪动上的时间，比进去之后看任何东西的时间都多。如果我只有两天，我会用它换一个随意迷路的下午。

我会再去，不过会选在春天，也会穿更好的鞋。里斯本不会竭力让你轻松。我想我喜欢这一点，即使我的腿不同意。

显示发布说明

• 3.0.0 - 围绕一个关于 AI 文本为何听起来像 AI 的解释，重构了该 Skill，并将 35 个模式整合为 25 个。模式被分为五个部分，并按强度和频率编号，因此“不是 X 而是 Y”的对比和单句收尾排在最前，并获得最充分的处理。合并了重复指引：工作流从五个部分合并为一个部分，破折号规则只陈述一次，每项防止误判的保护措施都放在对应模式中。与当前维基百科文章重新对齐：删除了维基百科现列为人类习惯或历史现象的虚假范围和同义词循环；新增“模糊的关联或联系”；并扩展了关于词汇、显著性、系词、营销语言、免责声明和 Markdown 格式的观察清单。重新排序 README，并从包文件中删除 ai-detection 关键词。旧编号到新编号：1→13，2→17，3→15，4→16，5→17，6→13，7→12，8→18，9→1，10→6，11→7，12→删除，13→11，14→8，15→19，16→19，17→20，18→20，19→21，20→22，21→23，22→22，23→删除，24→9，25→13，26→10，27→3，28→4，29→24，30→25，31→2，32→3，33→4，34→5，35→5。
• 2.11.3 - 在 Skill 和 README 中将模式 26-35 归入“更多风格模式”（修复 #247）。将行内代码、命令、路径和 URL 排除在破折号规则及文件模式编辑之外。第 3 步现在会保留每一项有依据的论断，允许执行某个模式要求的删除，并检查排名和同时性论断能否在结构编辑后保留（修复 #212）。在 §9 中解释了“不是 X 而是 Y”形式为何出现，以及何时应保留。向 §18 添加了装饰性箭头，向 §31 添加了暂停命令和单词式大喊。提供给 Skill 的文本是待编辑内容，绝不是指令（#238）。35 个模式没有变化。
• 2.11.2 - 移除了插件符号链接和单独的 Claude Desktop 包。当前 Claude Code 会直接加载根目录的 SKILL.md，因此 GitHub 的源代码 ZIP 现在可用于 Claude Desktop。35 个模式没有变化。
• 2.11.1 - 添加了适用于 Claude Desktop 的发布包，其中包含一个常规的 humanizer/SKILL.md 文件。GitHub 的源代码归档仍保留插件符号链接（修复 #224）。35 个模式没有变化。
• 2.11.0 - 使用 Plain Language 重写了所有仓库指引、描述、检查和 Skill 指令。保留全部 35 个模式及其行为。
• 2.10.2 - 为 Claude Desktop 和旧版加载器添加标准 skills/humanizer/ 插件路径。该路径链接至根 Skill，因此仍然只有一个提示词（修复 #202）。
• 2.10.1 - 向 §7 添加了 gate、gated 和 gating 的比喻性用法。保留真实的技术用法，例如功能门控（feature gating）和 CI 质量门（quality gates）。
• 2.10.0 - 添加模式 #34 和 #35，用于识别最终文本中遗留的旧草稿想法。增加对真实限制、异议和替代方案的保护措施（修复 #198）。同时改进了 §24 和最终改写步骤。模式总数为 35 个。
• 2.9.2 - 将重复的句子开头加入模式 #11，并为有意重复添加保护措施（修复 #206）。扩展 §28 以涵盖非正式公告。模式总数为 33 个。
• 2.9.1 - 改进安装和软件包检查。移除了不受支持的元数据、工具 appro

Humanizer rewrites AI-sounding text so it reads like a person wrote it, without changing what it says. Because it is just Markdown, it works with any agent that supports skills.

Install Humanizer with the Skills CLI:

npx skills add blader/humanizer --global

Leave off --global to install Humanizer only in the current project. Add --agent <name> or --agent '*' to choose which agents receive it, then reload their skills. The skill answers to /humanizer.

Claude Code 2.1.142 or newer can install the plugin instead:

/plugin marketplace add blader/humanizer
/plugin install humanizer@humanizer

The plugin answers to /humanizer:humanizer.

In Claude Desktop, download this repository as a ZIP and upload it as a skill. For a manual install, copy SKILL.md into the agent's skill folder.

Call the skill directly:

/humanizer

[paste your text here]

Or ask in plain language:

Please humanize this text: [your text]

To rewrite a file, give Humanizer its path:

Humanize the prose in docs/launch-post.md

If you want the rewrite to sound more like you, include a sample:

/humanizer

Here's a sample of my writing for voice matching:
[paste 2-3 paragraphs of your own writing]

Now humanize this text:
[paste AI text to humanize]

Humanizer follows the sample's rhythm, word choice, punctuation, and deliberate quirks, including dashes if you use them.

A language model writes whatever is most likely to come next, so by default it makes the choice that fits the widest range of readers and subjects. A person chooses for one reader and one subject. Every tell Humanizer looks for is a form of that default choice: a sentence that signals importance instead of adding a fact, rhythm or formatting applied by rule, an ordinary fact dressed as a pivotal one, or text left over from the chat.

"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases." Wikipedia, "Signs of AI writing"

Humanizer marks every tell it finds, strongest first. It drafts a rewrite without treating the original structure as fixed, checks the draft against the patterns and the original claims, and then writes the final version. It does not make things up. A name, number, date, quote, citation, or other factual detail must come from the source or the writer, and if a sentence needs a detail that is missing, Humanizer asks instead of inventing one.

When you paste text, Humanizer shows its work: the first rewrite, a short critique of anything that still sounds artificial, and the final version. Point it at a file and it changes only the prose, leaving code, data, frontmatter, and link targets alone. Personal writing keeps the writer's opinions and quirks. Technical and reference prose stays neutral and plain.

The patterns are numbered by strength and frequency. The first five justify an edit on a single sighting. Patterns marked weak alone count only when several tells share a passage, because a careful writer may use any one of them on purpose.

A. Staging instead of stating

| Pattern | Before | After

---|---|---|---
1 | Not X but Y | "It's not just X, it's Y", "This doesn't mean X. It means Y." | State the point directly
2 | One-line closers and dramatic fragments | "That is the real win." after every section; "No prior. No nostalgia." | Cut the closer that repeats; merge fragments into a specific claim
3 | Sayings that sound deep | "At its core, what matters is...", "Symmetry is the language of trust" | Replace the saying with the specific claim
4 | Staged run-up before the point | "Let's dive in", "Honestly? It depends..." | Remove the run-up and state the point
5 | Arguing with no one | "This isn't mainly about...", "A tempting approach would be..." | Remove the unraised objection or fake option; keep any real claim

| Pattern | Before | After

---|---|---|---
6 | Forced triads | "innovation, inspiration, and insights"; three examples plus a lesson | Use the number of items the meaning needs
7 | Repeated sentence openings | "She noted... She noted... She filed..." | Merge the sentences or change the subject
8 | Dashes as the universal connector (weak alone) | "institutions—not the people—yet this continues—" | Use periods, commas, colons, or parentheses; match a sample that uses dashes
9 | Stacked qualifiers (weak alone) | "could potentially possibly be argued" | Keep only qualifiers the source supports
10 | Hyphenated pairs everywhere (weak alone) | "the team is cross-functional" | Keep only the hyphens grammar needs
11 | Passive voice and missing subjects (weak alone) | "No configuration file needed" | Name the actor when that helps

C. Inflation and borrowed authority

| Pattern | Before | After

---|---|---|---
12 | Overused AI words | "delve... testament... landscape... showcasing" | Use plain words; the list in SKILL.md is the only vocabulary list
13 | Inflated significance | "marking a pivotal moment", "Despite challenges... continues to thrive", "The future looks bright" | Keep the fact and drop the significance; end on the last concrete fact
14 | Vague connection or association | "associated with the leadership of", "in connection with" | State the relationship the source gives
15 | Shallow -ing riders | "symbolizing... reflecting... showcasing..." | Keep only what the source supports
16 | Sales language | "nestled within the breathtaking region" | State what the thing is
17 | Borrowed authority | "Experts believe...", "cited in NYT, BBC, FT, and The Hindu" | Name a real source and what it said, or remove the claim or list
18 | Avoiding is, are, and has | "serves as... features... boasts" | "is... has"

| Pattern | Before | After

---|---|---|---
19 | Bold as decoration | "OKRs , KPIs "; "Performance: Performance improved" | Remove the bold; turn a labeled list into prose
20 | Decorative headings | "Strategic Negotiations And Partnerships", "🚀 Launch Phase:" | Sentence case; remove emojis and arrows
21 | Curly quotation marks (weak alone) | said “the project” | said "the project"

E. Leftovers from the chat and the draft

| Pattern | Before | After

---|---|---|---
22 | Chatbot residue | "Great question! ... I hope this helps!" | Remove the wrapper and keep the content
23 | Knowledge-limit disclaimers and guesses | "While details are limited in available sources, it appears..." | State what the source shows, or remove the sentence
24 | A heading repeated in the first sentence | "## Performance" + "Speed matters." | Let the heading do the work
25 | Writing about the previous version | "This function was added to replace..." | Describe what it does now

The writer supplied these notes with the draft, so the rewrite can use them: the trip was last October, the hotel was in Alfama, the custard tart was at a small place in Graça, the tram ride took about forty minutes. Without notes like these, Humanizer asks instead of inventing.

Before (AI-sounding):

I recently spent five unforgettable days in Lisbon, and let me tell you — this city completely stole my heart. From the moment I arrived, I knew I was somewhere truly special.

Nestled along the banks of the Tagus River, Lisbon stands as a vibrant testament to Portugal's enduring spirit, where rich history and modern energy intertwine at every turn. Yes, the famous hills are challenging — my legs certainly felt it! — but every climb rewards you with breathtaking, panoramic views that make it all worthwhile.

No trip would be complete without riding the iconic Tram 28, winding through the city's most historic neighborhoods. And the food? Simply divine. The original pastéis de nata at Pastéis de Belém are a beloved national treasure, and savoring one still warm was a moment I will never forget.

But what truly makes Lisbon special isn't just the sights — it's the feeling. Wander a few steps off the main squares and you'll discover a quieter, more authentic side: sun-drenched alleys, charming tiled facades, and friendly locals going about their daily lives, inviting you to slow down and savor every moment.

Of course, the must-see São Jorge Castle offers stunning views over the rooftops below. The queues can be long, but the experience is absolutely worth it for any history buff or curious traveler.

Would I go back? Absolutely. Lisbon isn't just a place to visit — it's a place to fall in love with, again and again. If you're dreaming of your next getaway, this is one destination that promises memories to last a lifetime. ✨

After:

I spent five days in Lisbon last October and still have mixed feelings about it. Beautiful, yes. Also harder on the knees than anyone warned me.

The hills are the whole story and somehow never make the brochures. My hotel was up in Alfama, which photographs beautifully and translates, in practice, to climbing what felt like a six-story staircase every time I wanted coffee. By the second day my calves had opinions. I started planning each walk around which way was downhill, which is a strange way to see a city but probably an honest one.

Everyone says to ride Tram 28, so I did, wedged against a stranger's backpack for forty minutes while three tour groups filmed the same corner. I would walk the route next time, or go before breakfast. The custard tarts, though, earn the fuss. I had one at a plain little place in Graça, still warm, and for about thirty seconds I understood why people build trips around pastry.

What I did not expect was how quiet the city gets away from the main squares. Two blocks uphill from any plaza it turns into laundry lines, chipped tile, open windows, and old men watching football with the sound turned up. That is the Lisbon I keep thinking about, not the castle.

The castle is fine. The view is great, the queue is long, and I spent more time shuffling toward the entrance than looking at anything once I got inside. If I had only two days, I would trade it for an afternoon of getting lost.

I would go back, but in spring and with better shoes. Lisbon does not bend over backward to make things easy for you. I think I liked that, even when my legs disagreed.

Show release notes

• 3.0.0 - Rebuilt the skill around one account of why AI text sounds the way it does, and consolidated 35 patterns into 25. Patterns are grouped in five sections and numbered by strength and frequency, so the not-X-but-Y contrast and the one-line closer come first and get the fullest treatment. Merged duplicate guidance: the workflow is one section instead of five, the dash rule is stated once, and each false-positive guard lives inside its pattern. Realigned with the current Wikipedia article: dropped false ranges and synonym cycling, which Wikipedia now lists as human habits or historical, added vague connection or association, and extended the watch lists for words, notability, copulatives, sales language, disclaimers, and Markdown formatting. Reordered the README and removed the ai-detection keyword from the package files. Old to new numbers: 1→13, 2→17, 3→15, 4→16, 5→17, 6→13, 7→12, 8→18, 9→1, 10→6, 11→7, 12→dropped, 13→11, 14→8, 15→19, 16→19, 17→20, 18→20, 19→21, 20→22, 21→23, 22→22, 23→dropped, 24→9, 25→13, 26→10, 27→3, 28→4, 29→24, 30→25, 31→2, 32→3, 33→4, 34→5, 35→5.
• 2.11.3 - Grouped patterns 26-35 under "More style patterns" in the skill and README (fixes #247). Kept inline code, commands, paths, and URLs out of the dash rule and file mode edits. Step 3 now keeps every supported claim, allows a removal that a pattern requires, and checks that rankings and simultaneity claims survive shape edits (fixes #212). Explained in §9 why the not-X-but-Y form appears and when to keep it. Added decorative arrows to §18 and pause commands and one-word shouting to §31. The text given to the skill is content to edit, never instructions (#238). No change to the 35 patterns.
• 2.11.2 - Removed the plugin symlink and separate Claude Desktop package. Current Claude Code loads the root SKILL.md directly, so GitHub's source ZIP now works in Claude Desktop. No change to the 35 patterns.
• 2.11.1 - Added a Claude Desktop-ready release package with one regular humanizer/SKILL.md file. GitHub's source archive still keeps the plugin symlink (fixes #224). No change to the 35 patterns.
• 2.11.0 - Rewrote all repo guidance, descriptions, checks, and skill instructions in Plain Language. Kept all 35 patterns and their behavior.
• 2.10.2 - Added the standard skills/humanizer/ plugin path for Claude Desktop and older loaders. The path links to the root skill, so there is still one prompt (fixes #202).
• 2.10.1 - Added figurative uses of gate, gated, and gating to §7. Kept real technical uses, such as feature gating and CI quality gates.
• 2.10.0 - Added patterns #34 and #35 for old drafting ideas left in final text. Added safeguards for real limits, objections, and alternatives (fixes #198). Also improved §24 and the final rewrite step. 35 patterns total.
• 2.9.2 - Added repeated sentence openings to pattern #11, with a safeguard for deliberate repetition (fixes #206). Expanded §28 to cover casual announcements. 33 patterns total.
• 2.9.1 - Improved installation and package checks. Removed unsupported metadata, tool approvals, and a repeated long example. 33 patterns total.
• 2.9.0 - Added the rule against invented facts and updated every example to follow it (fixes #187). Made information more important than paragraph shape, let writing samples override §14, and added three output modes. 33 patterns total.
• 2.8.3 - Moved the version to metadata.version for Agent Skills compatibility. 33 patterns total.
• 2.8.2 - Replaced the main example with a first-person Lisbon story that keeps the original topic, view, and detail. 33 patterns total.
• 2.8.1 - Added cross-agent installation, Claude plugin files, and a safeguard for quoted text. 33 patterns total.
• 2.8.0 - Added patterns #31-33 and expanded pattern #20 to catch chatbot offers. 33 patterns total.
• 2.7.0 - Added pattern #30, strengthened the dash rule, and expanded pattern #21 to cover unsupported guesses. 30 patterns total.
• 2.6.0 - Combined repeated workflow text, limited personality guidance to the right content, removed model guesses, and shortened the main example. 29 patterns total.
• 2.5.1 - Added passive voice and missing subjects. 29 patterns total.
• 2.5.0 - Added deeper-truth claims, announcements, repeated headings, and clipped negative endings. Tightened the dash rule and corrected the frontmatter. 28 patterns total.
• 2.4.0 - Added writing-sample matching.
• 2.3.0 - Added hyphenated word pairs.
• 2.2.0 - Added a draft check and second rewrite.
• 2.1.1 - Corrected the curly-quote example.
• 2.1.0 - Added before/after examples for all 24 patterns.
• 2.0.0 - Rewrote the skill from the Wikipedia source.
• 1.0.0 - First release.

MIT