munger-mental-models_skill

This skill helps you apply Charlie Munger's multidisciplinary thinking and Lollapalooza framework to identify super opportunities and avoid common biases.
  • Rust

7

GitHub Stars

1

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 louloulin/claude-agent-sdk --skill munger-mental-models

  • SKILL.md8.8 KB

Overview

This skill presents Charlie Munger’s multidisciplinary investing framework focused on combining mental models and spotting Lollapalooza effects—situations where multiple positive forces align to create outsized opportunities. It codifies core models from mathematics, physics, biology, psychology, microeconomics and military thinking into a practical investment workflow. The skill includes a quantitative Lollapalooza scoring system and a disciplined decision process emphasizing circle of competence and inversion. It is designed to help investors identify, score, and position concentrated bets when several factors compound.

How this skill works

The skill inspects an opportunity across four Lollapalooza dimensions: valuation, business quality, moat depth, and growth catalysts, then computes a composite score to guide position sizing. It applies a sequence: capability check, multidisciplinary analysis, inversion (failure-mode thinking), scoring, and concentrated allocation rules. Built-in model checks cover compounding math, critical thresholds, network effects, incentives and cognitive biases to surface durable advantages and catastrophic risks. Outputs are a Lollapalooza level (e.g., Super, Strong, Standard) and recommended allocation bands.

When to use it

  • Evaluating opportunities where multiple catalysts and advantages may compound.
  • Deciding whether to concentrate capital in a single high-conviction idea.
  • Performing due diligence beyond pure financial metrics to include psychology and ecosystem effects.
  • Screening for asymmetric risk/reward situations that warrant heavy weighting.
  • Structuring an investment checklist to avoid domain overreach.

Best practices

  • Always run the circle-of-competence checklist; skip ideas outside your knowledge domain.
  • Combine Graham-style valuation floors with Buffett-style quality checks before applying Lollapalooza scoring.
  • Perform explicit inversion: list ways the thesis fails and how likely each is.
  • Favor concentration only when the Lollapalooza score meets your predefined threshold and risks are understood.
  • Use multidisciplinary lenses (math, physics, biology, psychology, economics) to test whether factors reinforce or cancel.

Example use cases

  • Scoring a consumer brand with strong network effects, high ROIC and global catalysts to decide on a 15–25% allocation.
  • Assessing a technology company for scale effects and critical-mass tipping points before concentrated purchase.
  • Applying the probability and compounding models to long-term holdings to estimate future value under different growth scenarios.
  • Using incentive-structure analysis to detect misaligned management compensation that could negate other positive factors.

FAQ

The score sums four normalized components (valuation, quality, moat, catalysts) weighted equally; thresholds map to allocation bands (Super, Strong, Standard, etc.).

When should I concentrate rather than diversify?

Concentrate only when the Lollapalooza score meets your tested threshold, you understand failure modes, and the idea lies inside your competence; otherwise limit position size.

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