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 SilentFleetKK/zuiti-skill --skill zuiti-skillgit clone --depth 1 https://github.com/SilentFleetKK/zuiti-skillWrote 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/silentfleetkk/zuiti-skill/zuiti-skill)<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.
<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>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 | $0.00332 | $0.03560 |
| Opus 5 | $0.00166 | $0.01780 |
| Sonnet 5 | $0.00066 | $0.00712 |
| Haiku 4.5 | $0.00033 | $0.00356 |
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.
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:
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 · 261 lines · 332 tokens per session scan A cca5c2caab16
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.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
dispatching-parallel-agents
A workflow for assigning separate coding agents to independent tasks that do not share state or depend on one another. Each agent receives a focused scope, constraints, and an expected result.