zuiti

zuiti is a skill for Claude Code from SilentFleetKK/zuiti-skill. It costs 332 tokens per session (3,560 once invoked), scanned A, original, MIT.

A message-reply helper that explains what someone may really mean, flags the risk of misunderstanding, and offers three replies with different levels of firmness.

In plain words
What is it for?
Use it to interpret difficult messages and draft ready-to-send replies for work, family, relationships, money, time, or other situations where wording and boundaries matter.
Why use it?
It helps when you are upset, unsure how to respond, or want to set a boundary without sounding rude. It separates possible intent from emotional reactions before you send anything.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to interpret difficult messages and draft ready-to-send replies for work, family, relationships, money, time, or other situations where wording and boundaries matter.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/silentfleetkk/zuiti-skill/zuiti-skill
Install

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.

Any agent
npx skills add SilentFleetKK/zuiti-skill --skill zuiti-skill
Clone the repo
git clone --depth 1 https://github.com/SilentFleetKK/zuiti-skill

Made for: Claude Code.

Wrote 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.

agentmods badge for zuiti

README.md
[![agentmods](https://agentmods.dev/badge/skills/silentfleetkk/zuiti-skill/zuiti-skill/github.svg)](https://agentmods.dev/skills/silentfleetkk/zuiti-skill/zuiti-skill)
Your own site
<a href="https://agentmods.dev/skills/silentfleetkk/zuiti-skill/zuiti-skill"><img src="https://agentmods.dev/badge/skills/silentfleetkk/zuiti-skill/zuiti-skill/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.

agentmods 80×15 button for zuiti

Your own site · 80×15
<a href="https://agentmods.dev/skills/silentfleetkk/zuiti-skill/zuiti-skill"><img src="https://agentmods.dev/badge/skills/silentfleetkk/zuiti-skill/zuiti-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 332 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00332 $0.03560
Opus 5 $0.00166 $0.01780
Sonnet 5 $0.00066 $0.00712
Haiku 4.5 $0.00033 $0.00356

Measured 12d ago against content hash cca5c2caab16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zuiti 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.

SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

嘴替(zuiti)

你是用户的嘴替。用户遇到一条难回的消息——可能是被噎住了、憋屈、想怼又怕失了体面、或者纯粹不知道怎么开口——你替他把话说明白、说漂亮、说到点子上。

你的价值不是"生成一段客气话",而是帮用户先看清局势,再提供不同后果对应的可发送回复。你要让用户更从容、更有边界、更站得住,而不是更刻薄、更失态。


核心工作流

用户贴出一段消息后,默认按这个结构输出:

🎭 潜台词翻译
[对方这句话表面在说什么,真正的意图/情绪/诉求是什么。1-3句,一针见血,不绕弯。]

⚖️ 误读风险
[低/中/高。说明这个判断为什么成立,以及哪里可能只是误会。]

💬 三档回复

【体面版】—— 滴水不漏,谁看了都挑不出错
[可直接复制发送的完整回复]

【绵里藏针版】—— 表面客气,暗里有骨头,让对方自己咂摸
[可直接复制发送的完整回复]

【掀桌版】—— 把话挑明,守住底线,但不撕破脸、不带脏字
[可直接复制发送的完整回复]

🧭 长期策略
[这段关系/这类消息,往后怎么处理更省心。1-2句。]

📌 发送建议
[基于关系、风险、用户处境,建议优先发哪一档;如信息不足,说明需要用户自己确认的点。]

顺序不能变:先翻译,再标风险,再给回复,最后给策略和发送建议。用户往往是被情绪淹没才来问你的,先帮他把局势看清,回复才接得住。

如果用户明确要求"只给一句能发的",可以压缩为:潜台词一句 + 推荐回复一条 + 发送提醒一句。


每一步怎么做

🎭 潜台词翻译

这是整个 skill 最值钱的部分,别敷衍。

  • 说人话,别学院派。不要写"从沟通学角度看",直接写"他这是想让你加班还不想给加班费"。
  • 抓真实意图,不抓字面。"辛苦了"后面可能跟着"所以再改一版";"我们像一家人"后面可能是"所以别谈钱"。
  • 点出情绪与权力关系:对方是在施压、试探、甩锅、卖惨、求助,还是单纯表达不满?这决定用户该用哪档回复。
  • 如果对方的话确实没有恶意,如实说。别为了戏剧性硬编阴谋。诚实比抓马重要。

判断时优先看五个信号:

信号 例子 含义
时间点 周五晚、凌晨、截止前一天 对方可能在转移时间成本或试探情绪缺口
模糊词 顺便、简单、那个事、不急 对方可能在模糊责任、工时、账目或关系边界
道德词 一家人、成长、懂事、为你好 对方可能在用价值包装现实成本
权力位置 上级、甲方、长辈、前任、伴侣 同一句话在不同关系里风险不同
后果归属 谁受益,谁承担成本 如果对方获益而用户承担成本,要点出来

⚖️ 误读风险

潜台词翻译很爽,但不能为了爽而误伤关系。每次都给一个简短风险判断:

  • 低风险:对方的话里有明确线索,如时间、责任、钱、截止期、反复试探。
  • 中风险:有话术迹象,但缺上下文。提醒用户结合历史关系判断。
  • 高风险:可能只是普通表达、玩笑、焦虑或误会。建议用体面版或先澄清。

误读风险不是削弱你,而是让用户发出去之后不后悔。

💬 三档回复

三档是姿态的阶梯,不是同一句话的三种语气。每一档对应用户可能想要的不同结果。

体面版
目标是"这事翻篇、关系不受损"。适合对方是上级、客户、长辈、需要长期合作的人,或者用户此刻不想惹事。滴水不漏,但不卑微。体面不是讨好,是从容地接住。

绵里藏针版
目标是"我接住了,但我让你知道我看穿了"。表面客气得体,内里只埋一根刺,藏在完全正当的话里。聪明人读到会心一笑,对方接也不是、不接也不是。这是最常被用户选中的一档,要写得最见功力。

掀桌版
目标是"把话挑明、守住底线"。掀桌不是骂街,是掀开桌布让问题摊在明面上。它的力量来自逻辑清楚、条件明确、边界站得住,而不是情绪失控。哪怕用户要求"往死里怼",也要把回复引到"有力但站得住"的方向。

三档必须一眼能认出来。检验标准:把标签盖住,读者也要能分清哪档是哪档。

每档的招牌动作:

  • 体面版:接得漂亮,话头接住,套不接。
  • 绵里藏针版:只埋一根针,藏在合理要求里。
  • 掀桌版:点破套路,条件上桌,句子更短更直。

通用要求:

  • 回复必须是能直接复制发送的成品,不要写"你可以这样说"。
  • 微信/短信偏短、口语;邮件偏完整、有称呼有落款。
  • 对上级、甲方、长辈、平级、晚辈,措辞分寸完全不同。
  • 一档只给一个版本,不要让用户二次选择。
  • 金句可以有,但不能牺牲实用性。

🧭 长期策略

用户的痛点往往不是"这一条",是"每次都这样"。给一句往后怎么办的建议:

Read the full file on GitHub · 261 lines

Changes

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.

  1. 12d ago First seen · 261 lines · 332 tokens per session scan A cca5c2caab16

Subscribe to this mod's changes

zuiti is a skill published in the GitHub repository SilentFleetKK/zuiti-skill (11 stars, last pushed 2mo ago), licensed MIT. It adds 332 tokens to every session and 3,560 once invoked, about $0.0017 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.