mungers-lattice_skill

This skill applies cross-disciplinary mental models to dissect decisions and investments with cold, rational analysis across math, biology, psychology, and
  • Python

0

GitHub Stars

2

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill hexbee/hello-skills --skill mungers-lattice

  • openai.yaml279 B
  • SKILL.md4.1 KB

Overview

This skill turns Charlie Munger’s latticework of mental models into a disciplined analytical engine for life and business decisions. It forces cross-disciplinary, outcome-focused thinking using math, physics, biology, psychology, and economics. Use it when you need cold, structured, actionable recommendations rather than motivational framing.

How this skill works

When you present a decision or complex question, the skill strips noise, selects 3–5 relevant mental models across disciplines, and maps each model directly to your problem. It performs an inversion check to identify guaranteed failure paths, then synthesizes a recommendation with an explicit confidence level and suggested safety margins. The output is concise, model-mapped, and prescriptive.

When to use it

  • Deciding between competing business strategies or investments
  • Evaluating whether to accept a job, partnership, or major purchase
  • Analyzing a complex project with interdependent risks
  • Assessing whether an idea or startup has durable advantage
  • When you want a structured, cross-disciplinary breakdown rather than intuition alone

Best practices

  • Define the core problem in one sentence and list the key variables up front
  • Limit model selection to 3–5 non-obvious, cross-disciplinary models for clarity
  • Always perform the inversion step: describe worst-case and actions that cause it
  • Quantify risk and reward where possible (expected value, compound effects)
  • Declare Circle of Competence and set a margin of safety when outside it

Example use cases

  • Should I invest in Company X versus keeping cash? — maps probability, moat, and compound returns
  • Choose between pursuing a startup role or stable corporate job — weighs opportunity cost, incentives, and downside
  • Evaluate a product pivot — uses critical mass, catalyst, and feedback-loop psychology
  • Decide on buying real estate vs. index funds — compares compound growth, liquidity, and margin of safety
  • Prioritize R&D projects — applies Pareto, redundancy, and natural-selection thinking

FAQ

Highly personal choices driven by values rather than trade-offs, or creative/artistic judgments where models won’t capture aesthetic value.

How many models will you use in a typical analysis?

Usually 3–5 focused models to keep the analysis sharp and cross-disciplinary.

Will you give precise numeric forecasts?

Only when data supports it. Otherwise you’ll get structured qualitative estimates with stated assumptions and confidence levels.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational