blader / humanizer
blader / humanizer
Humanizer 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.
Humanizer Humanizer 可以重写听起来像 AI 生成的文本，使其读起来更像人类所写，同时不改变其原意。由于它只是 Markdown 格式，因此它适用于任何支持技能（skills）的智能体。
How it works Humanizer uses 35 patterns from Wikipedia’s “Signs of AI writing”, maintained by WikiProject AI Cleanup. It makes a first pass without treating the original structure as fixed. Then it checks the draft against those patterns and the original claims before rewriting whatever still needs work.
工作原理 Humanizer 使用了由 WikiProject AI Cleanup 维护的维基百科“AI 写作迹象”（Signs of AI writing）中的 35 种模式。它会先进行初步处理，而不将原始结构视为固定不变。随后，它会根据这些模式和原始论点检查草稿，并重写仍需改进的部分。
“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.” It does not make things up. A name, number, date, quote, citation, or other factual detail must come from the source or the writer.
“大语言模型（LLMs）使用统计算法来猜测接下来应该出现什么。其结果往往倾向于在最广泛的情况下统计概率最高的内容。”它不会凭空捏造。姓名、数字、日期、引语、引用来源或其他事实细节必须来自原始资料或作者本人。
For personal writing, Humanizer keeps the writer’s style. Technical and reference prose stays neutral and plain. If you provide a writing sample, Humanizer follows that sample instead of its default style rules.
对于个人写作，Humanizer 会保留作者的风格。技术和参考性文章则保持中立和平实。如果你提供写作样本，Humanizer 将遵循该样本，而不是其默认的风格规则。
When you paste text, Humanizer shows its work before giving you the final version. You see the first rewrite and a short critique of anything that still sounds artificial. Point it at a file and it changes only the prose, leaving code, data, frontmatter, and link targets alone.
当你粘贴文本时，Humanizer 会在给出最终版本前展示其处理过程。你会看到初次重写的内容，以及对任何听起来仍显生硬之处的简短点评。如果指向一个文件，它只会修改正文，而保留代码、数据、元数据（frontmatter）和链接目标不变。
Usage
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
使用方法
直接调用技能：/humanizer [在此粘贴你的文本]
或者用通俗语言提问：Please humanize this text: [你的文本]
若要重写文件，请提供文件路径：Humanize the prose in docs/launch-post.md
Match your voice
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.
匹配你的语调
如果你希望重写后的内容更像你自己的风格，请包含一个样本：
/humanizer Here's a sample of my writing for voice matching: [粘贴 2-3 段你自己的写作内容] Now humanize this text: [粘贴需要润色的 AI 文本]
Humanizer 会模仿样本的节奏、用词、标点符号以及刻意的表达习惯。
The 35 patterns (部分示例)
| # | Pattern | Before | After |
|---|---|---|---|
| 1 | Inflated importance | ”marking a pivotal moment…" | "was established in 1989…“ |
| 1 | 夸大重要性 | “标志着……的关键时刻” | “于 1989 年作为……的一部分成立” |
| 7 | Overused AI words | ”Actually… testament… landscape" | "also… needs… remain common” |
| 7 | 过度使用的 AI 词汇 | “实际上……见证……格局” | “也……需要……仍然常见” |
| 18 | Emojis | ”🚀 Launch Phase: 💡 Key Insight:“ | Remove emojis |
| 18 | 表情符号 | “🚀 启动阶段：💡 关键洞察：” | 移除表情符号 |
(Note: The full list of 35 patterns follows the same logic of replacing AI-typical phrasing with direct, human-readable prose.)
Full example Details such as the month and neighborhood need to come from the writer. If they are missing, Humanizer should ask instead of making them up.
完整示例 月份和街区等细节必须由作者提供。如果缺失，Humanizer 应该询问，而不是凭空捏造。
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…
修改前（AI 味）： 我最近在里斯本度过了难忘的五天，我必须告诉你——这座城市彻底偷走了我的心。从我到达的那一刻起，我就知道我来到了一个真正特别的地方。里斯本坐落在塔霍河畔，是充满活力的见证……