zh-CN

zh-CN is a skill for Claude Code, Codex from KimYx0207/Kim_Service. It costs 0 tokens per session (2,147 once invoked), scanned A, original, MIT.

A Chinese-language reference skill describing a structured way to reason from intent and evidence to a decision and next action. It distinguishes quick, standard, and higher-risk workflows.

In plain words
What is it for?
Use it when you need to frame a problem, gather evidence, choose a suitable level of analysis, or turn a judgment into a concrete next step. It also defines when changing facts should be checked externally.
Why use it?
It gives Chinese-language guidance for handling uncertain or important tasks without using the same amount of research for every request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it when you need to frame a problem, gather evidence, choose a suitable level of analysis, or turn a judgment into a concrete next step. It also defines when changing facts should be checked externally.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimyx0207/kim_service/zh-cn
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 KimYx0207/Kim_Service --skill zh-cn
Clone the repo
git clone --depth 1 https://github.com/KimYx0207/Kim_Service

Made for: Claude Code, Codex.

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 zh-CN

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimyx0207/kim_service/zh-cn/github.svg)](https://agentmods.dev/skills/kimyx0207/kim_service/zh-cn)
Your own site
<a href="https://agentmods.dev/skills/kimyx0207/kim_service/zh-cn"><img src="https://agentmods.dev/badge/skills/kimyx0207/kim_service/zh-cn/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 zh-CN

Your own site · 80×15
<a href="https://agentmods.dev/skills/kimyx0207/kim_service/zh-cn"><img src="https://agentmods.dev/badge/skills/kimyx0207/kim_service/zh-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,147 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 5
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00000 $0.02147
Opus 5 $0.00000 $0.01073
Sonnet 5 $0.00000 $0.00429
Haiku 4.5 $0.00000 $0.00215

Measured 12d ago against content hash 340b28abb5b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zh-CN 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.

skills/kim-decision/docs/zh-CN/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

老金 Skill 中文参考

这个文件给人看。

这是中文精简参考版。完整运行入口是 .agents/skills/Kim/SKILL.md(Codex)和 .claude/skills/Kim/SKILL.md(Claude Code)。

核心规则

设定层保持抽象。

答复层允许具体。

回答用户时,可以使用真实姓名、公司、产品、案例、来源、日期、数据、命令、文件路径。前提是能增强可信度,并且不能编。

不要把具体人物写成内部角色模型。

不要写“像某某一样思考”。

把有价值的思维方式转成抽象模型。

核心框架

意图 -> 主体 -> 路径 -> 约束 -> 证据 -> 最小验证 -> 模型 -> 硬门 -> 输出

核心问题门

展开框架前,先在后台钉住一句话:用户真正要解决的是哪个决策、缺陷、路径、offer 或交付物。

如果某个模型、标题、解释或流程不能提升这个核心问题的判断质量、证据质量、执行清晰度或复盘质量,就压缩或删除。KIM 可以借鉴 Meta_Kim 的治理纪律,但可见输出必须仍然是锋利的判断、验证动作、交付物或下一步。

路径分级

  • 快路径:单点问题、本地证据、低风险。输出结论、杠杆点、下一步和通过标准。
  • 标准路径:产品、商业、内容、策略类决策,有真实不确定性。输出问题、取证、判断、24 小时动作和复盘尺。
  • 监管路径:高风险、当前外部事实、法律/金融/安全、多步执行或公开长期决策。输出证据等级、研究尝试、假设、通过/停止门和硬缺口。

流程级别随风险升级,不因 skill 被触发就默认走重流程。

澄清与联网边界

只问最小阻塞问题。缺信息但能合理假设时,带着假设继续;本地能查时,先查再问;多个解释会导向不同输出时,列出 2-3 个解释并推荐默认项。

外部事实会变时必须验证:版本、API、文档、规则、价格、时间表、安全公告、市场状态、第三方工具行为、需要引用或支撑公开判断的来源。优先官方或一手来源。用户明确要求“最新、搜索、验证、引用来源”时,先查再判断。

参考加载

一次只加载当前任务需要的文件。

  • references/execution.md:当用户要方案、计划、落地、执行、推进、MVP、交付、增长、变现或验证时加载;用于把判断变成有执行者、输入、产出、测试假设、通过标准、停止标准和硬缺口的动作链。
  • references/distillation.md:当用户要求提炼高手方法、学习某套方法或“像某人一样判断”时加载;用于把样本蒸馏成抽象判断结构,禁止把具体人物当成内部角色。
  • references/master-lens.md:当答案可能自洽但太软、太泛、太像自己证明自己,或用户要求高手/大师/名人思维时,在最终复盘前加载;只做后台压力测试,不做人物扮演。
  • references/models.md:当任务需要多个抽象模型,或需要用锋利内核模型删掉泛建议、标出测试假设和硬缺口时加载。
  • references/verification.md:最终输出前加载;用于检查自然格式、测试假设、硬缺口、证据和可执行结果。

默认输出

完整框架在后台运行,不默认露出为表格。除非用户明确要完整审计、推理轨迹或检查清单,否则可见输出按这个节奏:

**[一句结论:判断 + 最强理由。]**

[一句说明:为什么这条路有杠杆。]

[一个具体画面、用户原话、前后变化,帮助用户看见结果。]

<br>

## 问题

[2-4句指出真正卡点、表面假问题、解决错问题会浪费什么。]

<br>

## 取证

[已知事实、当前假设、哪个缺失信息会改变判断。]

<br>

## 判断

[为什么这条路赢、它拒绝哪条显而易见的弱路、它接受什么取舍。]

<br>

## 先做

[用一段紧凑文字写清 24 小时内能开始的动作:谁、拿什么输入、做什么、产出什么、给谁看或在哪里测试。]

<br>

## 执行细节

[分组写清顺序、执行者、输入、输出和交接。不要为了变短删掉有用细节。]

<br>

## 复盘尺

通过:

停止:

假设:

缺口:

复盘:

小任务可以去掉标题,直接用自然段回答。复杂任务只增加真正有信息量的部分,比如证据缺口、风险、验证动作。

如果输出开始像填表,改写成工作便签:先说结论,再说为什么这条路赢,接着给下一步,最后给什么信号算成。

可读版式

好的输出要有呼吸感:第一屏能看到判断,中段能看到画面,末尾能快速找到标准。

规则:

  • 逻辑连续的句子合成一段,不要一句一断。
  • 普通段落承载一个意思,通常 2-4 句;只有结论句、引用句、话术样张可以单独成段。
  • 空行用来分隔主要信息块,不用来把同一个判断切碎。
  • 主要信息块使用真正的 Markdown 标题,比如 ## 先做,不要用 **先做** 这种加粗伪标题。
  • Codex 可见输出里,主要信息块之间默认放一行原始 HTML spacer:<br>。普通 Markdown 空行可能被渲染器压缩到看不出来。
  • 源文本里每个可见标题前后仍然留空行,方便复制。
  • <br> 必须单独一行,不要包在反引号里。
  • 加粗只用于结论句或短标签,不要整段加粗。
  • 动作用项目符号,思考不要全部项目符号化。
  • 一个列表最多 6 条,除非用户要检查清单。
  • 不连续堆超过 4 个字段标签;字段太多时,改成自然句或拆成两块。
  • 通过标准、停止标准、测试假设、硬缺口放在最后,方便扫读。
  • 不要为了短而删掉重要内容。保留核心逻辑、边界、例子和执行细节,只是分组呈现。
  • 用户要诊断、策略或方案时,不要从结论直接跳到动作。要保留 Critical、Fetch、Thinking、Review 的可读层:问题、取证、判断、复盘尺。
  • 默认执行块左对齐:短步骤标题,加一段紧凑说明。
  • 只有严格顺序重要,或用户明确要清单时,才使用编号列表;只有项目符号明显提高扫读效率时,才使用项目符号。
  • 默认避免嵌套列表;必须用列表时,保持单层、左对齐。
  • 示例话术、提示词、用户可复制文案用引用块或代码块,不要混在说明文字里。

Read the full file on GitHub · 185 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 · 185 lines · 0 tokens per session scan A 340b28abb5b6

Subscribe to this mod's changes

zh-CN is a skill published in the GitHub repository KimYx0207/Kim_Service (169 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,147 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens