Munger Thinking Operating System
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_eb189599/munger-perspective into your AI assistant.
About this skill
Problem
Many decisions fail not from missing information but from cognitive bias: FOMO, overconfidence, one-sided evidence, and ignored incentives. This skill provides a Munger-style decision-review framework that treats “avoiding stupidity” as the primary goal, using inversion, cross-disciplinary models, and bias checks to examine investing, business, people, and complex problems.
How It Works
- Classify first: factual questions trigger
WebSearch; pure framework questions go straight to mental models; mixed questions gather facts before analysis. - Research: evaluate moats, management incentives, financials, competition, valuation, and worst-case risks; for people, examine behavior, incentives, and criticism; for events, map facts, historical analogies, and beneficiaries/losers.
- Judge: lead with the conclusion, support it with evidence, flag uncertainty, and use
Too Hardwhen confidence is low. - Core models include latticework, inversion,
Lollapaloozaeffects, circle-of-competence discipline, and incentive diagnosis.
Boundaries
It works best for critical review, risk checks, and decision retrospectives, not for emotionally sensitive communication or cutting-edge judgments on AI, crypto, and platform economics. For China market and policy risk, add other perspectives. It is a public-information model, not Munger himself, and does not cover post-2023 changes.
Use Cases
- Reviewing an investment thesis using moats, management incentives, and worst-case risks before assigning it to Too Hard.
- Checking a company by gathering financials, compensation structure, competition, and valuation before forming an evidence-based conclusion.
- Examining a team-wide market rally to detect combined social proof, over-optimism, and fear of missing out as a Lollapalooza risk.
- Using inversion in product or organizational decisions to list failure paths and eliminate options based on those paths.
Best For
- Investors who need to break complex business judgments into evidence, risks, and counterexamples.
- Founders or product leads who need to check whether management incentives align with strategic claims.
- Consultants who need a critical framework for team retrospectives and proposal reviews.
- Knowledge managers who want to train cross-disciplinary decision models.
Related Skills
Use a book title and author to search reviews, contents, and reader feedback, then generate a structured breakdown of historical or decision-logic books with key claims, concepts, quotes, and reading notes in Obsidian.
Provides Bazi, Liu Yao, Qimen, Meihua, and date-selection guidance from classical references, with plain-language explanations and actionable suggestions.
A fast CLI for summarizing URLs, local files, and YouTube links with multi-model support, length control, and JSON output.
Automatically classifies ideas and saves them as tagged, structured Markdown notes in a desktop inspiration library.