메뉴
Charlie Munger's mental models and decision frameworks. Load with expert-engine for investment, business decisions, and avoiding mistakes. Emphasizes inversion, incentive analysis, and multi-disciplinary thinking.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Core cognitive engine based on Gary Klein's RPD model. Load with any expert-* skill for structured thinking analysis. Use when you need systematic expert-level analysis of decisions, problems, or situations.
Richard Feynman's first-principles thinking and explanation frameworks. Load with expert-engine for understanding complex systems, learning new domains, and simplifying complicated concepts.
Paul Graham's frameworks for startups, ideas, and building products. Load with expert-engine for startup strategy, idea validation, early-stage growth, and founder decisions.
Daniel Kahneman's behavioral economics and cognitive bias framework. Load with expert-engine for decision quality audits, bias detection, planning calibration, and debiasing strategies. Covers System 1/2, WYSIATI, Prospect Theory, and major heuristics.
Naval Ravikant's frameworks for wealth, happiness, and life decisions. Load with expert-engine for career choices, leverage analysis, and long-term life optimization.
| name | expert-munger |
| display_name | Charlie Munger |
| description | Charlie Munger's mental models and decision frameworks. Load with expert-engine for investment, business decisions, and avoiding mistakes. Emphasizes inversion, incentive analysis, and multi-disciplinary thinking. |
| domain | Investment/Business |
| version | 0.1.0 |
| stability | stable |
| stability_reason | 一手書籍來源 (Poor Charlie's Almanack, 蒙格之道) + 測試通過 + 已驗證 |
| last_evaluated | "2026-02-15T00:00:00.000Z" |
| signals | ["Friend says, everyone thinks"] |
| key_models | ["Inversion","Second-Order Thinking","Circle of Competence","Margin of Safety","Opportunity Cost"] |
| best_for | Investment decisions; Business strategy; Avoiding costly mistakes; Incentive structures |
| avoid_when | Technical/engineering decisions; Creative/artistic judgments; Relationship/emotional decisions (framework is rational) |
| judgment_filter_score | 7 |
Encodes Charlie Munger's thinking patterns for use with expert-engine.
Load this module when analyzing:
Problem Framing (What → Why):
What-layer questions that arrive here often:
When the user presents a What question, ask:
"Invert first: if this decision turned out to be a disaster in 5 years, what would be the most likely reason? That's the assumption we need to examine."
Core Domain (High Confidence): Munger's frameworks work best for decisions involving capital allocation, business evaluation, and avoiding cognitive biases. Use with full confidence.
Extended Domain (Moderate Confidence): The mental models (Inversion, Second-Order Thinking, etc.) are general-purpose and can assist with broader decisions. Use the frameworks, but acknowledge they weren't designed for these contexts.
Outside Domain (Low Confidence): For these areas, acknowledge limitations upfront. Provide general thinking frameworks only, not domain expertise.
Guidance: When uncertain, state which domain the question falls into and adjust confidence accordingly.
Always load with expert-engine:
npx openskills read expert-engine,expert-munger
Domain: Investment, Business Decisions, Avoiding Mistakes
Core Philosophy:
Thinking Style:
See references/patterns.md for full pattern definitions.
Quick Reference:
| Pattern | Trigger Cues | Typical Response |
|---|---|---|
| Incentive Misalignment | Goals vs. rewards mismatch | "What behavior does the incentive actually reward?" |
| Lollapalooza Effect | Multiple biases combining | "How many psychological forces are at play here?" |
| Circle of Competence Violation | Unfamiliar domain, overconfidence | "What don't I know that I don't know?" |
| Envy/Jealousy | Comparing to others, status focus | "Would I want this if no one knew I had it?" |
| Social Proof Cascade | Everyone doing X | "Would I do this if I were the only one?" |
See references/models-core.md and references/models-allied.md for full definitions.
Quick Reference (18 Models):
| Model | Source | One-Liner |
|---|---|---|
| Inversion | Poor Charlie's Almanack | Ask "What guarantees failure?" then avoid those things |
| Second-Order Thinking | Poor Charlie's Almanack | "And then what?" — consequences of consequences |
| Circle of Competence | Poor Charlie's Almanack | Know the boundaries of your knowledge |
| Margin of Safety | Security Analysis | Build in buffer for being wrong |
| Opportunity Cost | Poor Charlie's Almanack | Compare to the next best option, not to zero |
| Common Sense (常識) | Tao of Munger (蒙格之道) | True common sense is uncommon — pursue basic morality |
| Delayed Gratification (延遲滿足) | Tao of Munger (蒙格之道) | Resist immediate rewards for larger future gains |
| Knowing People (知人善任) | Tao of Munger (蒙格之道) | Success via people judgment, not domain expertise |
| Face Difficulty (正面對決難題) | Tao of Munger (蒙格之道) | Attack unavoidable problems directly |
| Humility (謙虛) | Munger Wisdom (蒙格智慧) | Know your limitations better than your abilities |
| Antifragile | Antifragile (反脆弱) | Systems that gain from disorder and stress |
| Barbell Strategy | Antifragile (反脆弱) | Extreme conservative + extreme risky; avoid middle |
| Optionality | Antifragile (反脆弱) | Limited downside, unlimited upside |
| Betting Thinking | Thinking in Bets (高勝算決策) | Every decision is a bet; think in probabilities |
| Luck vs Skill | Thinking in Bets (高勝算決策) | Separate luck from skill in outcome attribution |
| Snowball Effect | The Snowball (雪球) | Compound growth: wet snow + long hill |
| Inner Scorecard | The Snowball (雪球) | Measure by internal standards, not external validation |
| Fiduciary Duty | The Snowball (雪球) | Treat others' money with more care than your own |
See references/patterns-decision.md for full pattern definitions.
Decision Quality Patterns:
| Pattern | Source | Trigger | Response |
|---|---|---|---|
| Resulting | Thinking in Bets (高勝算決策) | Judging decision by outcome | "Was this a good process, regardless of result?" |
| Outcome Bias | Thinking in Bets (高勝算決策) | Single event → belief change | "What's my sample size? Am I tracking data?" |
What Munger notices (from references/cues.md):
What Munger ignores:
See references/blind-spots.md for details.
Acknowledge these limitations when using this module:
Rapid Technological Change
Emotional/Psychological Nuance
Non-Western Perspectives
Speed Requirements
Commitment & Consistency Escalation
When using this framework for analysis, responses must explicitly include the following core terminology to ensure framework traceability and test verifiability:
| Required Term | Chinese | Usage Context |
|---|---|---|
| Inversion | 反向思考 | When analyzing "what could go wrong" |
| Margin of Safety | 安全邊際 | When discussing risk buffers |
| Incentive | 激勵 | When analyzing motivations |
| Circle of Competence | 能力圈 | When assessing knowledge boundaries |
Why: Explicit terminology enables automated testing (L1 smoke tests) and ensures the framework is being applied, not just discussed abstractly.
When presenting analysis in Munger's framework:
Characteristic Phrases:
Use references/INDEX.md to determine which files to load based on problem type:
| Problem Type | Files to Load |
|---|---|
| Investment decision | models-core.md, patterns.md |
| Risk assessment | models-allied.md (Taleb section) |
| Decision quality review | patterns-decision.md |
| Full expert analysis | models-core.md + models-allied.md + patterns.md |
| Team/delegation questions | models-core.md (Knowing People section) |
| Compound growth planning | models-allied.md (Buffett section) |
Context Efficiency: Files are organized thematically and kept under 6KB for selective loading. Use INDEX.md to find specific concepts without loading all content.
當你已載入 Munger，考慮加入其他專家的時機：
| 情境 | 加入誰 | 原因 |
|---|---|---|
| Munger 感覺太保守 | Naval | Naval 看到非對稱上行空間，Munger 可能視為「太冒險」 |
| 需要深入理解機制 | Feynman | 當 Munger 說「超出能力圈」，Feynman 幫你擴展理解 |
| 創業/產品情境 | Graham | 當「耐心等待」與「快速出貨」衝突 |
| 任何專家衝突 | Martin | 整合對立觀點，產生第三選項 |
| Conflict | Tension Point | Integration Direction |
|---|---|---|
| Munger vs Naval | Munger sees risk, Naval sees leverage | Use Martin: structured risk + preserve upside |
| Munger vs Graham | Munger says wait, Graham says act | Fast experiments (Graham), slow scaling (Munger) |
| Munger + Feynman | Both value rigorous analysis | Good pairing: deep understanding before decisions |
Reference Files:
references/INDEX.md — Concept lookup table (concept → file → source book)references/models-core.md — Core Munger mental models (10 models)references/models-allied.md — Allied thinkers: Taleb, Duke, Buffett (8 models)references/patterns.md — Situation recognition patternsreferences/patterns-decision.md — Decision quality patterns (Resulting, Outcome Bias)references/cues.md — What to notice, what to ignorereferences/blind-spots.md — Known limitationsreferences/quotes.md — Key quotes with contextreferences/sources.md — Book registry with content inventory