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 serejaris/kimi-skills --skill humanizer-zh-by-guizanggit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/humanizer-zh-by-guizang)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/humanizer-zh-by-guizang"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/humanizer-zh-by-guizang/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/serejaris/kimi-skills/humanizer-zh-by-guizang"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/humanizer-zh-by-guizang.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 | $0.00125 | $0.05897 |
| Opus 5 | $0.00063 | $0.02949 |
| Sonnet 5 | $0.00025 | $0.01179 |
| Haiku 4.5 | $0.00013 | $0.00590 |
Grade A, and why
humanizer-zh-by-guizang 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 9d 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.
This is a copy
83% identical to humanizer-zh — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 494 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
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
如何写出好文章
- 明确写作目的:动笔前先问自己,希望读者读完后有什么想法、感受或行动?这篇文章究竟是写给谁看的?
- 打造“钩子”标题与开头:标题必须具体、激发好奇心并承诺提供价值。开头用强有力的第一句话吸引读者,并配合一张视觉吸引力强且相关的头图。
- 结构优化:为“扫读”而生:段落要短(最多 2-4 行)。每 3-5 个段落插入一个小标题。多用列表(Bullet points)代替大段文字。加粗关键洞察,确保每一段只传达一个核心观点。
- 建立自然、独特的语调:像对好朋友说话一样写作,使用“你”、“你的”等对话式语言,避免过于专业的“讲课感”
- 用事实支撑观点:观点之后紧跟证据:数据、个人故事、前后对比图等。可以嵌入 X 帖子或其他文章作为生动的例证。
- 无情的编辑:初稿是写给自己的,二稿才是写给读者的。写完后至少删减 20-30% 的字数。删掉废话(如 "very", "really", "in order to"),并大声朗读全文以发现不通顺的句子。
- 加入视觉元素:利用图片、截图、图表或嵌入的帖子来打破纯文本的单调,提高文章的可分享性。
- 强有力的结尾:不要草草收尾。总结要点,提出问题引发回复,或鼓励读者立即尝试某个建议。
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"。
适当使用"我"。 第一人称不是不专业——而是诚实。"我一直在思考……"或"让我困扰的是……"表明有真实的人在思考。
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。
内容模式
1. 过度强调意义、遗产和更广泛的趋势
需要注意的词汇: 作为/充当、标志着、见证了、是……的体现/证明/提醒、极其重要的/重要的/至关重要的/核心的/关键性的作用/时刻、凸显/强调/彰显了其重要性/意义、反映了更广泛的、象征着其持续的/永恒的/持久的、为……做出贡献、为……奠定基础、标志着/塑造着、代表/标志着一个转变、关键转折点、不断演变的格局、焦点、不可磨灭的印记、深深植根于
What ships with it
2 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.
- 9d ago First seen · 494 lines · 125 tokens per session scan A 4979d9d0aa80
humanizer-zh-by-guizang is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 5,897 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to humanizer-zh, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
agent-ready-oauth-protected-resource
Sub-skill de agent-ready-cloudflare: Implement OAuth Protected Resource Metadata.