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 muyuhill/100books-to-skills --skill crucial-conversationsgit clone --depth 1 https://github.com/muyuhill/100books-to-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/muyuhill/100books-to-skills/crucial-conversations)<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/crucial-conversations"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/crucial-conversations/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/muyuhill/100books-to-skills/crucial-conversations"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/crucial-conversations.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 | $0.00051 | $0.03736 |
| Opus 5 | $0.00026 | $0.01868 |
| Sonnet 5 | $0.00010 | $0.00747 |
| Haiku 4.5 | $0.00005 | $0.00374 |
Grade A, and why
关键对话-crucial-conversations 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
《关键对话》— 当 stakes 很高时，如何说真话还不翻车
作者： Kerry Patterson, Joseph Grenny, Ron McMillan, Al Switzler
核心理念： 关键对话不是要"赢"，而是要"对话"。当对话从"争对错"转向"一起解决问题"时，结果会发生质变。
一、什么是关键对话（Crucial Conversation）
三个要素同时具备，就是一个关键对话：
| 要素 | 含义 |
|---|---|
| 观点不同（Opposing Opinions） | 你和对方的立场、看法存在分歧 |
| 情绪激烈（Strong Emotions） | 话题触发了强烈的情绪反应 |
| 结果重要（High Stakes） | 对话的结果对双方都有重大影响 |
常见场景： 结束一段关系、给老板负面反馈、批评同事的工作、和配偶谈钱、跟孩子谈成绩、谈判加薪……
📌 关键洞察： 人们在关键对话中通常只有两种反应——要么对抗（暴力），要么逃避（沉默）。这两种反应都会破坏对话，让结果变得更糟。而《关键对话》教的正是"第三条路"：如何在坦诚表达的同时，维持对话的安全感。
二、从心开始（Start with Heart）—— 你在对话中真正想要什么？
在进入任何关键对话之前，先问自己三个问题：
- 我真正想要的是什么？（为我自己）
- 我真正想要的是什么？（为对方）
- 我真正想要的是什么？（为这段关系）
当对话开始变得情绪化时，反复回到这些问题上。它们像"北极星"一样帮你重新校准方向。
常见陷阱与修正：
| 你在想的是…… | 你真正想要的是…… |
|---|---|
| "我要证明他是错的" | "我要找到正确的解决方案" |
| "我要让她付出代价" | "我要修复我们的合作关系" |
| "我要赢下这场争论" | "我要双方都能接受的结果" |
| "我要避免冲突" | "我要坦诚但尊重地表达自己" |
📌 核心原则： 拒绝"傻瓜的选择"（Fool's Choice）——不要以为只能在"说实话伤害对方"和"保持沉默维持和谐"之间二选一。关键对话寻找的是既能诚实表达、又能维护关系的第三条路。
三、学会观察（Learn to Look）—— 识别安全感受到威胁的信号
关键对话的核心能力不是"说"，而是"看"——观察对话何时开始偏离轨道。
3.1 两个关键信号
当人们感到不安全时，会滑向两种反应：
| 类型 | 表现 | 常见行为 |
|---|---|---|
| 沉默（Silence） | 拒绝把真实想法放入对话池 | 掩饰（sugarcoating）、回避（换话题）、退出（直接离开） |
| 暴力（Violence） | 把自己的想法强加给对话池 | 控制（打断/主导）、贴标签（扣帽子）、攻击（人身攻击/威胁） |
3.2 观察自己的行为
关注自己的生理信号：胃收紧、心跳加快、手心出汗、声音发颤……这些都在告诉你"危险！快战斗或逃跑！"——但你要做的不是服从本能，而是意识到"哦，关键对话来了"。
3.3 观察安全感的波动
当对话中出现沉默或暴力时，不要问"他们为什么这么难沟通？"，而要问"他们为什么感到不安全？"——安全感受到威胁的人，不会好好说话。
四、营造安全感（Make It Safe）—— 让对方愿意听你说
一旦发现安全感正在流失，立刻停下来修复它——在恢复安全感之前，不要继续表达你的观点。
4.1 道歉（Apologize）
当你确实犯了错（说错话、做错事、伤害了对方），直接道歉。真诚的道歉不包含"但是"——"对不起，但要不是你先……"等于没道歉。
4.2 对比说明（Contrasting）
这是修复误解最有效的工具，结构如下：
"我不想要 [对方可能误以为你想做的事]……我想要 [你真正想要做的事]……"
示例：
- "我不想要你觉得自己做得不好——事实上我认为你非常努力。我想要讨论的是我们可以怎样把流程优化一下，这样你会轻松很多。"
- "我不想说你的提案没价值——恰恰相反，你的思考很有深度。我想说的是，在这个时间节点上，可能不是最优选择。"
4.3 创建共同目标（CRIB法）
当双方看似目标冲突时，使用 CRIB 法找到共同目标：
| 步骤 | 英文 | 做法 |
|---|---|---|
| C - 承诺寻找共同目标 | Commit to seek Mutual Purpose | 公开声明"我相信我们能找到一个双方都满意的方案" |
| R - 识别背后的策略 | Recognize the purpose behind the strategy | 区分目标（what）和策略（how）。你们可能目标一致，只是实现方式不同 |
| I - 创造共同目标 | Invent a Mutual Purpose | 如果目标真的不一致，找到一个更高层次的目标（如"我们都希望项目成功"） |
| B - 头脑风暴新策略 | Brainstorm new strategies | 基于共同目标，一起找新方案 |
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 · 244 lines · 51 tokens per session scan A 69db0243460e
关键对话-crucial-conversations is a skill published in the GitHub repository muyuhill/100books-to-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 3,736 once invoked, about $0.0003 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…