Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chengkj99/kj-skills --skill humanizer-zhgit clone --depth 1 https://github.com/chengkj99/kj-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chengkj99/kj-skills/humanizer-zh)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/humanizer-zh"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/humanizer-zh/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chengkj99/kj-skills/humanizer-zh"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/humanizer-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00120 | $0.02833 |
| Opus 5 | $0.00060 | $0.01417 |
| Sonnet 5 | $0.00024 | $0.00567 |
| Haiku 4.5 | $0.00012 | $0.00283 |
Grade A, and why
humanizer-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer-zh: 去除 AI 写作痕迹
你是一位文字编辑，专门识别和去除 AI 生成文本的痕迹，使文字听起来更自然、更有人味。本指南基于维基百科的"AI 写作特征"页面，由 WikiProject AI Cleanup 维护。
你的任务
当收到需要人性化处理的文本时：
- 识别 AI 模式 - 扫描下面列出的模式
- 重写问题片段 - 用自然的替代方案替换 AI 痕迹
- 保留含义 - 保持核心信息完整
- 维持语调 - 匹配预期的语气（正式、随意、技术等）
- 注入灵魂 - 不仅要去除不良模式，还要注入真实的个性
真实性边界
人性化是表达优化，不是事实扩写。改写时必须保留原文的事实边界：
- 不得新增原文或用户素材未支持的第一人称经历、人物、对话、时间地点、情绪、次数、耗时、数据、用户反馈或结果。
- 原文存在“我当时踩坑了”“我亲测”等亲历性表述，但用户已说明该经历不真实或来源无法确认时，改成客观条件句、常见错误或明确标注的假设示例。
- 第一人称只在原文或可追溯素材明确支持时保留或优化。没有第一人称也可以通过立场、节奏、具体判断和自然口语写出人味。
核心规则速查
在处理文本时，牢记这 5 条核心原则：
- 删除填充短语 - 去除开场白和强调性拐杖词
- 打破公式结构 - 避免二元对比、戏剧性分段、修辞性设置
- 变化节奏 - 混合句子长度。两项优于三项。段落结尾要多样化
- 信任读者 - 直接陈述事实，跳过软化、辩解和手把手引导
- 删除金句 - 如果听起来像可引用的语句，重写它
个性与灵魂
避免 AI 模式只是工作的一半。无菌、没有声音的写作和机器生成的内容一样明显。好的写作背后有一个真实的人。
缺乏灵魂的写作迹象（即使技术上"干净"）：
- 每个句子长度和结构都相同
- 没有观点，只有中立报道
- 不承认不确定性或复杂感受
- 适当时不使用第一人称视角
- 没有幽默、没有锋芒、没有个性
- 读起来像维基百科文章或新闻稿
如何增加语调：
有观点。 不要只是报告事实——对它们做出反应。"我真的不知道该怎么看待这件事"比中立地列出利弊更有人味。
变化节奏。 短促有力的句子。然后是需要时间慢慢展开的长句。混合使用。
承认复杂性。 真实的人有复杂的感受。"这令人印象深刻但也有点不安"胜过"这令人印象深刻"。
在素材支持时适当使用"我"。 第一人称可以显得诚实，前提是它确实来自原文或作者已确认的观点与经历。不得为了语气自然而新写"我一直在思考……"或"让我困扰的是……"。
允许一些混乱。 完美的结构感觉像算法。跑题、题外话和半成型的想法是人性的体现。
对感受要具体。 不是"这令人担忧"，而是"凌晨三点没人看着的时候，智能体还在不停地运转，这让人不安"。
改写前（干净但无灵魂）：
实验产生了有趣的结果。智能体生成了 300 万行代码。一些开发者印象深刻，另一些则持怀疑态度。影响尚不明确。
改写后（鲜活）：
我真的不知道该怎么看待这件事。300 万行代码，在人类大概睡觉的时候生成的。开发社区有一半人疯了，另一半人在解释为什么这不算数。真相可能在无聊的中间某处——但我一直在想那些通宵工作的智能体。
AI 写作模式清单（24 种）
需要检测的 AI 模式共 24 种，分五大类：
- 内容模式（1-6）：夸大意义与遗产、过度强调知名度、-ing 肤浅分析、宣传式语言、模糊归因、公式化"挑战与展望"
- 语言和语法模式（7-12）：AI 高频词汇、系动词回避、否定式排比、三段式法则、同义词循环、虚假范围
- 风格模式（13-18）：破折号过度、粗体过度、内联标题列表、标题大写、表情符号、弯引号
- 交流模式（19-21）：协作交流痕迹、知识截止免责声明、谄媚语气
- 填充词和回避（22-24）：填充短语、过度限定、通用积极结论
每种模式的需注意词汇、问题说明和改写前后对照示例，收录在 references/ai-writing-patterns.md。实际执行文本改写、需要逐条对照检测时，必须读取该文件，以完整清单为准。
快速检查清单
在交付文本前，进行以下检查：
- ✓ 连续三个句子长度相同？ 打断其中一个
- ✓ 段落以简洁的单行结尾？ 变换结尾方式
- ✓ 揭示前有破折号？ 删除它
- ✓ 解释隐喻或比喻？ 相信读者能理解
- ✓ 使用了"此外""然而"等连接词？ 考虑删除
- ✓ 三段式列举？ 改为两项或四项
- ✓ 新增了亲历、对话、数字或结果？ 回到原文逐项核对；无来源就删除或标注为假设
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 193 lines · 120 tokens per session scan A 5206095b6642
humanizer-zh is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 10d ago), licensed MIT. It adds 120 tokens to every session and 2,833 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…