重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
second-order-thinking by guia-matthieu/clawfu-skills
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill second-order-thinking超越即时后果,理解决策的连锁反应。掌握霍华德·马克斯的投资框架,洞察他人所忽视之处。
| 方面 | 详情 |
|---|---|
| 来源 | 霍华德·马克斯 - 《投资最重要的事》(2011),查理·芒格 |
| 核心原则 | "一阶思维说:'这是一家好公司,我们买吧。'二阶思维说:'这是一家好公司,但所有人都认为它很棒,所以它被高估了。卖出。'" |
| 为何重要 | 大多数人只考虑直接影响。二阶思考者能预见连锁反应——并发现他人错过的机会和风险。 |
| Claude 负责 | 您决定 |
|---|
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 构建内容框架 | 最终信息传递 |
| 建议说服技巧 | 品牌声音 |
| 创建草稿变体 | 版本选择 |
| 识别优化机会 | 发布时间 |
| 分析竞争对手方法 | 战略方向 |
Apply second-order thinking to this decision: [decision]
What are the first, second, and third-order consequences?
What might we be missing?
If we [action], what will competitors/market do in response?
Map the chain reaction and help me see if this is still smart.
We're considering [policy/rule change].
Apply second-order thinking to identify unintended consequences.
## 一阶思维 vs 二阶思维
### 一阶思维 (大多数人的做法)
- 只考虑即时、明显的影响
- 回答:"接下来会发生什么?"
- 线性和直接
- 通常导致拥挤的立场
**示例:** "提高价格将增加收入。"
### 二阶思维 (少数人的做法)
- 考虑后果的后果
- 回答:"然后呢?"
- 非线性和系统性
- 通常揭示反直觉的真相
**示例:** "提高价格将增加收入……但随后
一些客户会流失,竞争对手会降价竞争,
剩余的客户会寻找替代品。净效应不明确。"
### 马克斯公式
"对于每一个行动,问:然后呢?
在那之后呢?
在那之后呢?"
持续追问,直到你描绘出合理的连锁反应链。
## 后果链框架
### 分步流程
**1. 陈述决策/行动**
"我们决定 [X]。"
**2. 一阶效应 (即时)**
"直接且立即地,这会导致 [A, B, C]。"
**3. 二阶效应 (反应)**
"作为对 [A, B, C] 的回应,人们/市场将 [D, E, F]。"
**4. 三阶效应 (适应性调整)**
"随着 [D, E, F] 的展开,我们将看到 [G, H, I]。"
**5. 净评估**
"考虑到所有层级,这个决策仍然是最优的吗?"
### 模板
[我们正在考虑的内容]
| 效应 | 影响对象 | 概率 |
|---|---|---|
| 高/中/低 | ||
| 高/中/低 |
| 第一效应 | 可能的反应 | 概率 |
|---|---|---|
| 高/中/低 | ||
| 高/中/低 |
| 第二效应 | 进一步后果 | 概率 |
|---|---|---|
| 高/中/低 | ||
| 高/中/低 |
| 参与者 | 一阶效应 | 他们将…… | 因为…… |
|---|---|---|---|
| 客户 | |||
| 竞争对手 | |||
| 员工 | |||
| 监管机构 | |||
| 市场 |
## 二阶思维模式
### 1. 适应性反应
**模式:** 当你改变某事物时,人们会适应。
示例: 公司提供无限带薪休假。
- 一阶: 员工休假更多,更快乐
- 二阶: 员工感到内疚,休假更少
- 三阶: 倦怠增加,与预期效果相反
**启示:** 预测人们将如何适应激励措施。
### 2. 竞争性反应
**模式:** 你的行动会引发反制行动。
示例: 你降价 20%。
- 一阶: 更多客户,更高销量
- 二阶: 竞争对手匹配价格,你的优势消失
- 三阶: 价格战侵蚀全行业利润
- 四阶: 弱势玩家退出,行业整合
**启示:** 思考整个游戏,而不仅仅是你的一步棋。
### 3. 容量限制
**模式:** 好事会吸引拥挤。
示例: 你发现了一个服务不足的市场。
- 一阶: 高利润,快速增长
- 二阶: 竞争对手注意到,进入市场
- 三阶: 市场变得竞争激烈,利润压缩
- 四阶: 洗牌,只有强者生存
**启示:** 可持续优势需要可防御性。
### 4. 意外后果
**模式:** 规则/政策创造新的行为。
示例: 学校根据考试成绩支付教师薪酬。
- 一阶: 教师专注于备考,分数上升
- 二阶: 教学范围缩小到仅限考试内容
- 三阶: 学生在未测量的领域学习效果实际上下降
- 四阶: 最好的教师离开,擅长钻营者留下
**启示:** 激励措施会以意想不到的方式塑造行为。
### 5. 回归倾向
**模式:** 极端情况不会持续。
示例: 股票价格因炒作上涨三倍。
- 一阶: 持有者感觉富有,买入更多
- 二阶: 估值吸引怀疑者,做空者
- 三阶: 叙事转变,抛售压力
- 四阶: 价格回归公允价值
**启示:** 询问当情况正常化时会发生什么。
## 需要避免的陷阱
### 陷阱 1: "以前有效过"
**一阶:** 策略 X 对公司 Y 有效。
**二阶:** 但现在每个人都知道 X。它已被定价。使其有效的条件已经改变。模仿者稀释了优势。
### 陷阱 2: "越多越好"
**一阶:** 添加功能 Y 将吸引更多用户。
**二阶:** 但 Y 增加了复杂性,减慢了上手速度。它混淆了定位。支持成本上升。高级用户喜欢它,新用户流失。
### 陷阱 3: "削减成本"
**一阶:** 减少支出可提高利润率。
**二阶:** 但削减研发会减慢产品开发。削减销售会延迟增长。削减质量会增加流失率。最优秀的员工会跳槽到竞争对手那里。
### 陷阱 4: "降低价格"
**一阶:** 更低的价格吸引更多客户。
**二阶:** 但这暗示了低质量。吸引价格敏感的客户,他们容易流失。竞争对手匹配,优势消失。利润挤压,无法投资产品。
### 陷阱 5: "不惜一切代价增长"
**一阶:** 激进增长可占领市场。
**二阶:** 但不可持续的支出造成脆弱性。单位经济不成立。当资金枯竭时,公司崩溃。
### 解药
对于每一个"显而易见"的好主意,强迫自己问:
"可能会出什么问题?"
"这可能会如何适得其反?"
"其他人会如何回应?"
## 二阶决策框架
### 决策前检查清单
□ 我是否至少描绘了 2 个层级的后果?
□ 我是否考虑了每个关键参与者将如何回应?
□ 我是否识别了潜在的意外影响?
□ 我是否考虑了回归均值/正常化?
□ 我是否思考了当竞争对手反应时会发生什么?
□ 我是否考虑了如果这"成功"会发生什么(成功会带来自身的问题)?
### 决策矩阵
| 因素 | 一阶 | 二阶 | 净效应 |
|--------|-------------|--------------|-----|
| 收入 | +/- | +/- | ? |
| 成本 | +/- | +/- | ? |
| 竞争地位 | +/- | +/- | ? |
| 团队/文化 | +/- | +/- | ? |
| 选择权 | +/- | +/- | ? |
### 最终评估问题
1. "如果每个人都这样做,它还会有效吗?"
2. "我相信什么而市场不相信?"
3. "要让这件事适得其反,什么必须是真的?"
4. "我思考这个决策的方式和其他人一样吗?"
### 马克斯的测试
"一阶思维说:'这看起来不错。我们做吧。'
二阶思维说:'这看起来不错,但其他人也都这么认为吗?
我看到了什么别人没看到的?他们看到了什么我漏掉的?'"
输入:
"我们正在考虑推出免费增值层级以更快增长。应用二阶思维。"
输出:
推出我们 SaaS 产品的免费层级,以加速用户获取。
| 效应 | 影响 | 概率 |
|---|---|---|
| 更多注册 | 显著增加 | 高 |
| 营销成本下降 | 降低 CAC | 高 |
| 服务器成本增加 | 更多用户,更多基础设施 | 高 |
| 团队专注于转化漏斗 | 从直接销售转移 | 中 |
一阶结论: 这看起来很棒!更多用户,更低的 CAC。
| 第一效应 | 可能的反应 | 概率 |
|---|---|---|
| 更多注册 | 免费用户要求支持 | 高 |
| 更多注册 | 免费用户请求功能 | 高 |
| 更低的 CAC | 竞争对手复制免费增值模式 | 中 |
| 团队转移 | 销售团队抵制/离职 | 中 |
| 更多用户 | 产品被定位为"廉价" | 中 |
| 第二效应 | 进一步后果 | 概率 |
|---|---|---|
| 免费用户要求支持 | 支持不堪重负,付费用户受影响 | 中 |
| 免费用户请求功能 | 产品路线图转向免费用户需求 | 中 |
| 竞争对手复制免费增值模式 | 付费层级面临价格压力 | 中 |
| "廉价"定位 | 企业不愿购买 | 高 |
| 销售团队离职 | 失去关系,交易放缓 | 中 |
正向连锁反应: ✅ 如果产品易于分享,可实现病毒式增长 ✅ 庞大的用户基础创造网络效应 ✅ 免费层级 = 营销渠道 ✅ 从更多用户处获得数据/洞见
负向连锁反应: ⚠️ 免费用户 != 目标客户 ⚠️ 转化率可能很低 (典型的 2-5%) ⚠️ 资源从付费客户转移 ⚠️ 以后更难提价 ⚠️ 企业销售变得更难 ("有免费的为什么要付费?")
"免费增值模式优化的是什么?"
计算:
多 25% 的收入是否值得 50 倍的用户和压缩的定价?
在推出免费增值之前,验证:
替代的二阶行动:
输入:
"我们的主要竞争对手刚刚降价 30%。我们应该跟进吗?"
输出:
竞争对手降价 30%。立即面临回应压力。
"他们降价了。我们必须跟进,否则会失去客户。"
他们为什么降价?
如果我们跟进会发生什么?
| 如果我们跟进 | 一阶 | 二阶 | 三阶 |
|---|---|---|---|
| 我们的价格下降 30% | 收入短期下降约 30% | 利润率压缩,裁员? | 创新放缓,服务降级 |
| 客户留下 | 保留率得以维持 | 但价值更低 | 客户现在期望低价 |
| 竞争对手反应 | 他们再次跟进? | 价格战升级 | 有人倒闭 |
如果我们不跟进会发生什么?
| 如果我们不跟进 | 一阶 | 二阶 | 三阶 |
|---|---|---|---|
| 一些客户离开 | 收入损失 | 留下的客户对价格不那么敏感 | 更高质量的客户群 |
| 我们显得高端 | 被认为昂贵 | 被迫差异化 | 有机会增加价值,证明价格合理 |
| 竞争对手获得份额 | 他们增长 | 但利润率更低 | 他们的增长可能无利可图 |
"跟进他们的价格,假设他们的策略是正确的。"
如果他们的降价是弱势而非强势的表现呢?如果为了 30% 的节省而离开的客户是你最差的客户呢?如果这迫使你以最终能增强你实力的方式进行差异化呢?
| 选项 | 二阶后果 |
|---|---|
| 跟进价格 | 价格战,利润率压缩,竞相触底 |
| 不跟进,差异化 | 失去一些客户,推动价值创新 |
| 不跟进,细分 | 保持企业定价,让他们占据 SMB 市场 |
| 不跟进,增加价值 | 捆绑服务,增加感知价值 |
| 暂时跟进 | 表明愿意战斗,然后提价 |
不要立即跟进。相反:
二阶赢家: 不跟进并利用这种压力变得更好的公司,往往能赢得长期胜利。
输入:
"我们正在考虑实施四天工作周。应用二阶思维。"
输出:
实施四天工作周 (32 小时),全额薪酬。
| 效应 | 预期 | 概率 |
|---|---|---|
| 员工满意度提高 | 团队更快乐 | 高 |
| 招聘优势 | 更多申请者 | 高 |
| 每小时生产力提高 | 专注工作 | 中 |
| 成本相同,工作日减少 | 似乎更高效 | 高 |
一阶结论: 看起来是明显的胜利!
| 第一效应 | 反应/后果 | 概率 |
|---|---|---|
| 团队更快乐 | 期望重置——5 天现在感觉像惩罚 | 高 |
| 更多申请者 | 被福利吸引,而非使命 | 中 |
| 生产力提高 | 有些角色无法压缩 (支持,销售) | 高 |
| 成本相同 | 周一至周五客户覆盖问题 | 中 |
| 第二效应 | 进一步连锁反应 | 概率 |
|---|---|---|
| 5 天感觉像惩罚 | 如果你需要激增产能,会产生怨恨 | 高 |
| 错误的申请者 | 文化稀释,使命脱节 | 中 |
| 有些角色不适合 | 两级制度,内部冲突 | 高 |
| 覆盖缺口 | 客户投诉,竞争劣势 | 中 |
谁受益?
谁不受益?
隐藏的后果:
代替一刀切的四天工作周:
二阶制胜行动: 找到你想要的具体好处 (减少倦怠,更好的人才),并以更直接的方式解决它,无需一刀切的政策。
## 在任何重大决策之前
□ 我是否陈述了一阶效应?
□ 我是否至少问了两次"然后呢?"
□ 我是否考虑了每个利益相关者将如何回应?
□ 我是否识别了潜在的意外后果?
□ 我是否思考了竞争反应?
□ 我是否考虑了如果这成功会发生什么?(成功带来的问题)
□ 我是否考虑了回归均值?
□ 我的思考方式与普通人不同吗?
## 二阶分析: [决策]
### 决策内容
[我们正在考虑的内容]
### 利益相关者反应
| 利益相关者 | 第一反应 | 第二反应 |
|-------------|----------------|-----------------|
| 客户 | | |
| 竞争对手 | | |
| 员工 | | |
| 投资者 | | |
| 监管机构 | | |
### 后果链
| 层级 | 效应 | 概率 | 严重性 |
|-------|--------|-------------|----------|
| 一阶 | | | |
| 二阶 | | | |
| 三阶 | | | |
### 成功情景连锁反应
如果这完美成功,成功会带来什么问题?
### 失败情景连锁反应
如果这失败,会引发什么连锁反应?
### 净评估
考虑到所有层级,我们应该继续吗?
模式 : cyborg
name: second-order-thinking category: thinking subcategory: decision-making version: 1.0 author: MKTG Skills source_expert: Howard Marks, Charlie Munger source_work: The Most Important Thing difficulty: intermediate estimated_value: $3,000 strategic consulting session tags: [thinking, decisions, strategy, consequences, Howard-Marks, mental-models] created: 2026-01-25 updated: 2026-01-25
每周安装量
48
代码仓库
GitHub 星标数
54
首次出现
2026年2月13日
安全审计
安装于
gemini-cli46
opencode46
codex45
cursor44
github-copilot44
kimi-cli43
Think beyond immediate consequences to understand the chain reactions of decisions. Master Howard Marks' investment framework for seeing what others miss.
| Aspect | Details |
|---|---|
| Source | Howard Marks - "The Most Important Thing" (2011), Charlie Munger |
| Core Principle | "First-level thinking says, 'This is a good company, let's buy.' Second-level thinking says, 'This is a good company, but everyone thinks it's great so it's overpriced. Sell.'" |
| Why This Matters | Most people only consider immediate effects. Second-order thinkers anticipate the cascading consequences—and see opportunities and risks others miss. |
| Claude Does | You Decide |
|---|---|
| Structures content frameworks | Final messaging |
| Suggests persuasion techniques | Brand voice |
| Creates draft variations | Version selection |
| Identifies optimization opportunities | Publication timing |
| Analyzes competitor approaches | Strategic direction |
Apply second-order thinking to this decision: [decision]
What are the first, second, and third-order consequences?
What might we be missing?
If we [action], what will competitors/market do in response?
Map the chain reaction and help me see if this is still smart.
We're considering [policy/rule change].
Apply second-order thinking to identify unintended consequences.
## First vs. Second-Order Thinking
### First-Order Thinking (What Most People Do)
- Considers only immediate, obvious effects
- Answers: "What happens next?"
- Linear and direct
- Often leads to crowded positions
**Example:** "Raising prices will increase revenue."
### Second-Order Thinking (What Few Do)
- Considers consequences of consequences
- Answers: "And then what?"
- Nonlinear and systemic
- Often reveals counterintuitive truths
**Example:** "Raising prices will increase revenue... but then
some customers will churn, competitors will undercut, and
remaining customers will seek alternatives. Net effect unclear."
### The Marks Formula
"For every action, ask: And then what?
And then what after that?
And then what after that?"
Continue until you've mapped the plausible chain.
## Consequence Chain Framework
### Step-by-Step Process
**1. State the Decision/Action**
"We decide to [X]."
**2. First-Order Effects (Immediate)**
"Directly and immediately, this causes [A, B, C]."
**3. Second-Order Effects (Responses)**
"In response to [A, B, C], people/markets will [D, E, F]."
**4. Third-Order Effects (Adaptations)**
"As [D, E, F] play out, we'll see [G, H, I]."
**5. Net Assessment**
"Considering all levels, is this decision still optimal?"
### Template
[What we're considering]
| Effect | Who/What Affected | Probability |
|---|---|---|
| High/Med/Low | ||
| High/Med/Low |
| First Effect | Likely Response | Probability |
|---|---|---|
| High/Med/Low | ||
| High/Med/Low |
| Second Effect | Further Consequence | Probability |
|---|---|---|
| High/Med/Low | ||
| High/Med/Low |
| Player | First-Order | They Will... | Because... |
|---|---|---|---|
| Customers | |||
| Competitors | |||
| Employees | |||
| Regulators | |||
| Market |
## Second-Order Thinking Patterns
### 1. The Adaptation Response
**Pattern:** When you change something, people adapt.
Example: Company offers unlimited PTO.
- First-order: Employees take more vacation, happier
- Second-order: Employees feel guilty, take LESS vacation
- Third-order: Burnout increases, opposite of intended effect
**Lesson:** Anticipate how people will adapt to incentives.
### 2. The Competitive Response
**Pattern:** Your move triggers counter-moves.
Example: You cut prices 20%.
- First-order: More customers, higher volume
- Second-order: Competitors match price, your advantage disappears
- Third-order: Price war erodes margins industry-wide
- Fourth-order: Weaker players exit, consolidation
**Lesson:** Think about the game, not just your turn.
### 3. The Capacity Constraint
**Pattern:** Good things attract crowding.
Example: You discover underserved market.
- First-order: High margins, rapid growth
- Second-order: Competitors notice, enter market
- Third-order: Market becomes competitive, margins compress
- Fourth-order: Shakeout, only strong players survive
**Lesson:** Sustainable advantage requires defensibility.
### 4. The Unintended Consequence
**Pattern:** Rules/policies create new behaviors.
Example: School pays teachers based on test scores.
- First-order: Teachers focus on test prep, scores rise
- Second-order: Teaching narrows to tested material only
- Third-order: Student learning actually decreases in unmeasured areas
- Fourth-order: Best teachers leave, game-players stay
**Lesson:** Incentives shape behavior in unexpected ways.
### 5. The Reversion Tendency
**Pattern:** Extremes don't persist.
Example: Stock price triples on hype.
- First-order: Holders feel rich, buy more
- Second-order: Valuation attracts skeptics, shorts
- Third-order: Narrative shifts, selling pressure
- Fourth-order: Price reverts toward fair value
**Lesson:** Ask what happens when things normalize.
## Traps to Avoid
### Trap 1: "It Worked Before"
**First-order:** Strategy X worked for Company Y.
**Second-order:** But now everyone knows about X. It's priced in. The conditions that made it work have changed. Copycats dilute the advantage.
### Trap 2: "More is Better"
**First-order:** Adding feature Y will attract more users.
**Second-order:** But Y adds complexity, slowing onboarding. It confuses positioning. Support costs rise. Power users love it, new users bounce.
### Trap 3: "Cut Costs"
**First-order:** Reducing spending improves margins.
**Second-order:** But cutting R&D slows product. Cutting sales delays growth. Cutting quality increases churn. Best employees leave for competitors.
### Trap 4: "Lower Prices"
**First-order:** Lower prices attract more customers.
**Second-order:** But it signals low quality. Attracts price-sensitive customers who churn. Competitors match, nullifying advantage. Margins squeeze, can't invest in product.
### Trap 5: "Growth at All Costs"
**First-order:** Aggressive growth captures market.
**Second-order:** But unsustainable spending creates fragility. Unit economics don't work. When funding dries up, company collapses.
### The Antidote
For every "obvious" good idea, force yourself to ask:
"What could go wrong?"
"How might this backfire?"
"What will others do in response?"
## Second-Order Decision Framework
### Pre-Decision Checklist
□ Have I mapped at least 2 levels of consequences?
□ Have I considered how each key player will respond?
□ Have I identified potential unintended effects?
□ Have I considered reversion to mean/normalization?
□ Have I thought about what happens when competitors react?
□ Have I considered what happens if this "works" (success brings its own problems)?
### Decision Matrix
| Factor | First-Order | Second-Order | Net |
|--------|-------------|--------------|-----|
| Revenue | +/- | +/- | ? |
| Costs | +/- | +/- | ? |
| Competitive position | +/- | +/- | ? |
| Team/culture | +/- | +/- | ? |
| Optionality | +/- | +/- | ? |
### Final Assessment Questions
1. "If everyone did this, would it still work?"
2. "What do I believe that the market doesn't?"
3. "What would have to be true for this to backfire?"
4. "Am I thinking about this decision the same way everyone else is?"
### Marks' Test
"First-level thinking says: 'This looks good. Let's do it.'
Second-level thinking says: 'This looks good, but so does everyone think that?
What am I seeing that others don't? What are they seeing that I'm missing?'"
Input:
"We're considering launching a freemium tier to grow faster. Apply second-order thinking."
Output:
Launch a free tier of our SaaS product to accelerate user acquisition.
| Effect | Impact | Probability |
|---|---|---|
| More signups | Significantly increased | High |
| Marketing costs decrease | Reduced CAC | High |
| Server costs increase | More users, more infra | High |
| Team focuses on conversion funnel | Shift from direct sales | Medium |
First-order conclusion: This looks great! More users, lower CAC.
| First Effect | Likely Response | Probability |
|---|---|---|
| More signups | Free users demand support | High |
| More signups | Free users request features | High |
| Lower CAC | Competitors copy freemium | Medium |
| Team shift | Sales team resists/leaves | Medium |
| More users | Product positioned as "cheap" | Medium |
| Second Effect | Further Consequence | Probability |
|---|---|---|
| Free users demand support | Support overwhelmed, paid users suffer | Medium |
| Free users request features | Product roadmap shifts to free user needs | Medium |
| Competitors copy freemium | Price pressure on paid tiers | Medium |
| "Cheap" positioning | Enterprise reluctant to buy | High |
| Sales team leaves | Lose relationships, deals slow | Medium |
Positive Cascade: ✅ Viral growth if product is shareable ✅ Large user base creates network effects ✅ Free tier = marketing channel ✅ Data/learnings from more users
Negative Cascade: ⚠️ Free users != target customers ⚠️ Conversion rate likely low (2-5% typical) ⚠️ Resources shift from paying customers ⚠️ Harder to raise prices later ⚠️ Enterprise sales become harder ("Why pay when there's free?")
"What does freemium optimize for?"
The math:
Is 25% more revenue worth 50x more users and compressed pricing?
Before launching freemium, validate:
Alternative second-order moves:
Input:
"Our main competitor just cut prices 30%. Should we match?"
Output:
Competitor cut prices 30%. Immediate pressure to respond.
"They cut prices. We must match or lose customers."
Why did they cut prices?
What happens if we match?
| If We Match | First-Order | Second-Order | Third-Order |
|---|---|---|---|
| Our prices drop 30% | Revenue drops ~30% short-term | Margins compress, layoffs? | Innovation slows, service degrades |
| Customers stay | Retention maintained | But at lower value | Customers now expect low prices |
| Competitor response | They match again? | Price war escalates | Someone goes out of business |
What happens if we DON'T match?
| If We Don't Match | First-Order | Second-Order | Third-Order |
|---|---|---|---|
| Some customers leave | Lost revenue | Remaining customers are less price-sensitive | Higher quality customer base |
| We look premium | Perceived as expensive | Forced to differentiate | Opportunity to add value, justify |
| Competitor gains share | They grow | But at lower margins | Their growth may be unprofitable |
"Matching their price assumes their strategy is correct."
What if their price cut is a sign of weakness, not strength? What if the customers who leave for 30% savings are your worst customers? What if this forces you to differentiate in ways that ultimately strengthen you?
| Option | Second-Order Consequences |
|---|---|
| Match the price | Price war, margin compression, race to bottom |
| Don't match, differentiate | Lose some customers, force value innovation |
| Don't match, segment | Keep enterprise pricing, let them have SMB |
| Don't match, add value | Bundle services, increase perceived value |
| Temporary match | Signal willingness to fight, then raise |
Don't immediately match. Instead:
The second-order winner: The company that doesn't match and instead uses this pressure to get better often wins long-term.
Input:
"We're considering implementing a 4-day work week. Apply second-order thinking."
Output:
Implement 4-day work week (32 hours) at full pay.
| Effect | Expected | Probability |
|---|---|---|
| Employee satisfaction increases | Happier team | High |
| Recruiting advantage | More applicants | High |
| Productivity per hour increases | Focused work | Medium |
| Costs same, days worked fewer | Seems efficient | High |
First-order conclusion: Seems like a clear win!
| First Effect | Response/Consequence | Probability |
|---|---|---|
| Happier team | Expectations reset—5 days now feels punishing | High |
| More applicants | Attracted to perk, not mission | Medium |
| Productivity up | Some roles can't compress (support, sales) | High |
| Costs same | Customer coverage issues M-F | Medium |
| Second Effect | Further Cascade | Probability |
|---|---|---|
| 5 days feels punishing | If you need surge capacity, resentment | High |
| Wrong applicants | Culture dilution, mission disconnect | Medium |
| Some roles don't fit | Two-tier system, internal conflict | High |
| Coverage gaps | Customer complaints, competitive disadvantage | Medium |
Who benefits?
Who doesn't benefit?
Hidden consequences:
Instead of blanket 4-day week:
The second-order winning move: Find the specific benefit you want (reduced burnout, better talent) and solve it more directly without the blanket policy.
## Before Any Major Decision
□ Have I stated the first-order effects?
□ Have I asked "And then what?" at least twice?
□ Have I considered how each stakeholder will respond?
□ Have I identified potential unintended consequences?
□ Have I thought about competitive response?
□ Have I considered what happens if this succeeds? (success problems)
□ Have I considered reversion to mean?
□ Am I thinking differently than the average person?
## Second-Order Analysis: [Decision]
### The Decision
[What we're considering]
### Stakeholder Responses
| Stakeholder | First Reaction | Second Response |
|-------------|----------------|-----------------|
| Customers | | |
| Competitors | | |
| Employees | | |
| Investors | | |
| Regulators | | |
### Consequence Chain
| Level | Effect | Probability | Severity |
|-------|--------|-------------|----------|
| First | | | |
| Second | | | |
| Third | | | |
### Success Scenario Cascade
If this works perfectly, what problems does success create?
### Failure Scenario Cascade
If this fails, what cascades from that?
### Net Assessment
Given all levels, should we proceed?
Mode : cyborg
name: second-order-thinking category: thinking subcategory: decision-making version: 1.0 author: MKTG Skills source_expert: Howard Marks, Charlie Munger source_work: The Most Important Thing difficulty: intermediate estimated_value: $3,000 strategic consulting session tags: [thinking, decisions, strategy, consequences, Howard-Marks, mental-models] created: 2026-01-25 updated: 2026-01-25
Weekly Installs
48
Repository
GitHub Stars
54
First Seen
Feb 13, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli46
opencode46
codex45
cursor44
github-copilot44
kimi-cli43
AI代理协作核心原则:提升开发效率的6大Agentic开发原则指南
7,600 周安装
React Native 移动应用开发指南:使用JavaScript构建原生iOS和Android应用
55 周安装
UI/UX Pro Max:一站式设计智能数据库,提供配色、字体、图表及技术栈最佳实践
65 周安装
微信公众号技术文章写作指南:结构化流程与SEO优化规范
55 周安装
Facebook/Instagram广告定向专家:兴趣查找、类似受众、地理定向与人口统计
52 周安装
Facebook/Instagram广告创意分析工具 - 风险评分、A/B测试、创意疲劳检测与优化建议
53 周安装
Notion知识捕获AI工具:将对话自动转化为结构化文档,提升团队知识管理效率
62 周安装