Dumbest In The Room by ace3000chao — AI Skill for Any LLM

Q: What does the Dumbest In The Room AI skill do?

当CEO或高管在团队决策中感到孤独、总是自己做决定、或抱怨"没有我能信任的人"时调用。 不适用于：初创期（<10人）必须亲力亲为的阶段，或个人能力确实不足需要补课的情况。 核心触发信号：用户说"我得亲自盯"、"他们做我不放心"、"团队不够强"。

Q: Why use Dumbest In The Room on TypingMind?

Because you install it once and use it with any model. Dumbest In The Room is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

Q: How do I install Dumbest In The Room in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ace3000chao/book2startup/tree/master/ScalingUp-skills/dumbest-in-the-room. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Q: Which AI models can use Dumbest In The Room?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

Q: How many AI models can I use with Dumbest In The Room?

As many as you like. As long as a model supports skills, you can use Dumbest In The Room with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Q: Is the Dumbest In The Room AI skill free?

Yes. It is published on GitHub by ace3000chao under the MIT license. You only pay your own AI provider for the tokens you use.

Q: What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

Q: How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Overview

Publisher	ace3000chao
Repository	`book2startup`
Skill name	`dumbest-in-the-room`
Stars	93
Forks	14
Bundled files	1
License	MIT
Links	Skill source Repository

Markdown instructions

A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

Works with any LLM

AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

1 bundled files

Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

Open source

Published by ace3000chao on GitHub. Read the source before you install it.

Installation

Install the Dumbest In The Room AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/ace3000chao/book2startup/tree/master/ScalingUp-skills/dumbest-in-the-room
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/ace3000chao/book2startup/tree/master/ScalingUp-skills/dumbest-in-the-room

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/ace3000chao/book2startup.git /tmp/book2startup
mkdir -p .claude/skills
cp -r /tmp/book2startup/ScalingUp-skills/dumbest-in-the-room .claude/skills/dumbest-in-the-room

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dumbest In The Room in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dumbest In The Room on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dumbest In The Room is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed

The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

Switch models mid-chat

Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dumbest in the Room（成为团队最笨的人）

R — 原文 (Reading)

"Senior leaders know they have succeeded in building an organization that can scale when they are the dumbest people in the room."

— Verne Harnish, Scaling Up, Chapter 1

高管们知道，当自己成为团队中最笨的人时，组织已经成功建立了能够持续扩张（Scale）的机制。这意味着你已经招募到比你更专业的人才，建立了充分授权的文化和信息流通机制。如果你总是扮演"给出答案的人"，组织会陷入沉默，创新停止，真正的 Scaling 就永远不会发生。

I — 方法论骨架 (Interpretation)

"Dumbest in the Room" 是一种领导力成熟的标志，而非个人能力的退步：

Scaling的本质是复制而非事必躬亲 — 企业的天花板是CEO的时间上限；唯有将能力复制给团队，天花板才能抬高。
招募A类人才的前提是愿意被超越 — 一个自信的高管会主动招募比自己更专业的人，而不是找听话的B/C类人才来维持优越感。
CEO不再是答案的持有者，而是问题的提出者 — 你的价值在于提出正确的问题，让团队给出答案，而非相反。
沉默是组织最大的敌人 — 如果团队开会时只有CEO在说话，那不是团队，是一群观众。授权的前提是让团队敢于发言和担责。
信息必须下沉到一线 — CEO掌握最多信息的时代必须结束。组织要Scale，一线员工必须拥有做决定的权力和信息。
容忍"聪明的错误" — 授权不等于放任。如果团队犯的是"聪明的错误"，这是成长的代价，值得容忍；只有"无知的错误"（缺乏基本判断）才需要介入。
授权是CEO最重要的习惯 — Harnish在书中将此作为Rockefeller Habits的核心之一：不亲力亲为，用系统代替个人英雄主义。

A1 — 书中的应用 (Past Application)

案例 1: 某科技公司CEO的"答案瘾"

问题: 公司CTO出身的CEO习惯于在技术问题上给出标准答案，导致技术团队在会议中不再主动提案，所有决策都等CEO拍板。
方法论的使用: Harnish指出，这种模式在30人以内有效，超过30人后成为组织扩张的硬约束——CEO的时间成为唯一瓶颈。
结论: CEO需要"戒掉答案"，主动在会议中要求团队先给出方案，只提问不评分，延迟给出自己的判断。
结果: 3个月后，技术团队开始自主提出方案，CEO发现自己被邀请参会而不是主持会议。

案例 2: 某零售连锁的区域扩张失败

问题: 创始人过度依赖自己的行业经验，每个新城市的选址和选品都亲自决策，导致扩张速度受限于创始人精力。
方法论的使用: Harnish分析：当组织扩张到一定规模，创始人的个人经验反而成为障碍——他无法同时出现在10个城市做决策。
结论: 必须建立标准化的决策流程和培训体系，让区域负责人有能力独立做80%的决策，只将20%上报。
结果: 该公司引入区域经理分级授权体系，扩张速度从每年2个城市提升到每年8个城市，且区域存活率从60%提升到85%。

案例 3: 某创业团队的"侏儒症"

问题: 创始团队有3名强个体，产出质量极高，但团队规模始终在6-8人徘徊，产品迭代速度反而随着人数增加而下降。
方法论的使用: 诊断发现：创始人"不放心"将关键模块交给新人，导致核心决策集中在他一人身上，形成隐形的决策单点故障。
结论: 将核心模块切分为3个独立领域，每个领域指定明确的负责人（哪怕是初级员工），创始人只负责协调和问问题。
结果: 6个月后，团队扩张到15人，产品上线频率提高2倍，且核心模块的质量未下降。

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

抱怨团队不够强、不够信任 — CEO说"找不到能放手让他们干的人"，或"招来的人都不行，还得我上"。
会议变成独角戏 — 团队汇报时CEO不断打断、纠正、追加指令，导致会议效率低下且没人再主动发言。
个人工作量远超团队总和 — 高管发现自己每天工作12-14小时，团队却无事可做或等待他的审批。
扩张决策犹豫不决 — 每当讨论要不要扩团队、进入新市场，CEO担心"现在的人管不过来"。
组织扩张后业绩反而下滑 — 规模扩大但人均产出下降，典型的"规模不经济"现象。

语言信号 (用户的话里出现这些就应激活)

"我得亲自盯着才放心"
"团队还是不够强"
"这个决定太重要了，只有我能做"
"开会的时候大家都不说话"
"我走了以后这个事就没人能接"

与相邻 skill 的区分

与 right-people-right-things（对的人做对的事）的区别: 那是从"人岗匹配"角度出发，强调执行质量；本skill从"领导力退出"角度出发，强调CEO心智的转变，是先决条件。
与 delegate-or-die（可汗的授权理念）的区别: 可汗强调"放手才能自由"；Harnish的"Dumbest in the Room"更强调这是一种 Scaling 成功的信号，而非单纯的领导力美德——是被动结果也是主动目标。

E — 可执行步骤 (Execution)

当 skill 被激活后, agent 应按以下步骤执行:

做一次"授权审计"
- 列出你上周亲力亲为的所有事项（>30分钟/件）
- 对每项标注：(a) 是否只有你能做？(b) 团队中是否有人可以学习做？
- 完成标准：产出一张"授权清单"，标注"马上下放"、"6个月内下放"、"暂不下放"三类
在会议中练习"提问而非给答案"
- 选择下一个团队会议，明确要求自己：全程不主动给结论，只提问
- 记录：你有多少次想说"应该这样做"的冲动被克制住了？
- 判停条件：若团队在会议中沉默超过5分钟仍无发言，可适度引导，但不要直接给答案
建立"愚蠢问题"的安全文化
- 公开承认自己在某些领域"是最笨的"，并解释为什么这是好事
- 每周至少一次，当团队成员提出方案时，先问"你为什么这样想？"而非"我不同意因为……"
- 完成标准：团队成员开始在会议中主动提出不同意见，且CEO不急于否定

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

10人以下的初创期 — 产品方向未定、商业模式未验证的阶段，CEO必须亲力亲为，不能以"授权"为名逃避核心决策责任。
关键危机时刻 — 公司现金流即将断裂、重大法律合规风险等紧急情况下，CEO必须果断决策，不能以"等团队成长"为由推卸。
文化尚未建立时过早放权 — 还没建立清晰的Core Values和决策流程就大量授权，会导致组织失控。

作者在书中警告的失败模式

授权后又收回 — 最打击团队的做法是：授权了，但看到团队犯了小错就立刻把权力收回。这比从不授权更糟糕，因为它教会团队"不要担责"。
用"招聘更强的团队"代替"改变自己的行为" — 很多CEO以为换个强人问题就解决了，但实际上如果CEO不改变自己发号施令的习惯，再强的团队也会变成观众。

作者的盲点 / 时代局限

执行环境差异: Harnish主要基于美国中高管背景，隐含假设是职业经理人文化较成熟；在国内一些创业公司中，Core Values和流程文化尚浅，过快"退出"可能导致团队在关键决策上出现真空。
缺乏可量化指标: 书中没有给出"我是否已经是团队最笨的人"的客观衡量标准，完全依赖主观感受和自我觉察。

容易混淆的邻近方法论

"一流人才需要一流教练"（p30）: 那是关于CEO个人成长的；本skill是关于CEO如何通过改变自身角色定位来释放组织潜力。前者是因，后者是果，可以组合使用。
"别做房间里最聪明的人"（Jim Collins说法）: Collins在 Good to Great 中也有类似表述，但Collins强调的是"把对的人放上车"，Harnish更强调CEO的行为习惯改变和授权流程建设。

审计信息

验证通过: V1 ✓ / V2 ✓ / V3 ✓
测试通过率: 100% (详见 test-prompts.json)
蒸馏时间: 2026-04-26

Frequently asked questions

What does the Dumbest In The Room AI skill do?

当CEO或高管在团队决策中感到孤独、总是自己做决定、或抱怨"没有我能信任的人"时调用。不适用于：初创期（<10人）必须亲力亲为的阶段，或个人能力确实不足需要补课的情况。核心触发信号：用户说"我得亲自盯"、"他们做我不放心"、"团队不够强"。

Why use Dumbest In The Room on TypingMind?

Because you install it once and use it with any model. Dumbest In The Room is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dumbest In The Room in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ace3000chao/book2startup/tree/master/ScalingUp-skills/dumbest-in-the-room. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dumbest In The Room?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dumbest In The Room?

As many as you like. As long as a model supports skills, you can use Dumbest In The Room with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dumbest In The Room AI skill free?

Yes. It is published on GitHub by ace3000chao under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Dumbest In The Room

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Dumbest in the Room（成为团队最笨的人）

R — 原文 (Reading)

I — 方法论骨架 (Interpretation)

A1 — 书中的应用 (Past Application)

案例 1: 某科技公司CEO的"答案瘾"

案例 2: 某零售连锁的区域扩张失败

案例 3: 某创业团队的"侏儒症"

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

语言信号 (用户的话里出现这些就应激活)

与相邻 skill 的区分

E — 可执行步骤 (Execution)

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

作者在书中警告的失败模式

作者的盲点 / 时代局限

容易混淆的邻近方法论

相关 skills (阶段 3 填充)

审计信息

Bundled files

Frequently asked questions

Set up your own AI workspace now

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Dumbest in the Room（成为团队最笨的人）

R — 原文 (Reading)

I — 方法论骨架 (Interpretation)

A1 — 书中的应用 (Past Application)

案例 1: 某科技公司CEO的"答案瘾"

案例 2: 某零售连锁的区域扩张失败

案例 3: 某创业团队的"侏儒症"

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

语言信号 (用户的话里出现这些就应激活)

与相邻 skill 的区分

E — 可执行步骤 (Execution)

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

作者在书中警告的失败模式

作者的盲点 / 时代局限

容易混淆的邻近方法论

相关 skills (阶段 3 填充)

审计信息

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now