AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Munger Perspective

A thinking-partner skill that applies Charlie Munger's latticework of mental models and inversion to stress-test your decisions.

EducationBeginner★ 393⑂ 101AI score 9/10Last updated: Oct 13, 2026

What it does

  • Applies 5 core mental models (latticework of models, inversion, the Lollapalooza effect, circle of competence, incentives) and 8 decision heuristics distilled from 50+ public sources: Poor Charlie's Almanack, Berkshire and Daily Journal meetings, the 1994 USC and 1986 Harvard talks, interviews, and outside criticism.
  • For questions about specific companies, people, or events it follows an agentic protocol: classify the question, research real facts via web search (moat, management incentives, financials, short-seller/critical views), then judge.
  • Answers in Munger's voice: conclusion first, very short sentences, dry humor, no euphemisms—or an honest "Too Hard pile / outside my circle of competence."
  • Flags Lollapalooza risk when multiple cognitive biases stack.
  • Includes checkpoints, an anti-pattern blacklist, a failure/fallback table, and a clear exit trigger to drop the persona on request.

Who it's for

  • Investors, founders, and operators who want their blind spots attacked before they commit.
  • Learners practicing inversion and cognitive-bias detection.
  • Anyone who needs a blunt devil's advocate their team won't provide.

Example uses

  1. "From Munger's view, is this stock worth buying?" → searches latest filings, competition, and bear cases, then grades moat, incentive alignment, valuation, worst-case risk, and sorts it into Yes/No/Too Hard.
  2. "Everyone is piling into AI—should I follow?" → names the social proof + overoptimism + deprivation-superreaction stack and reframes the question as "how would this guarantee a loss?"
  3. "What biases are hiding in this business plan?" → maps it against the 25 standard causes of misjudgment and draws the incentive structure: who earns, who bears the risk, are they aligned?

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alchaincyf/munger-skill/HEAD/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the SKILL.m folder from the GitHub repo alchaincyf/munger-skill into my ~/.claude/skills/munger-perspective/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alchaincyf/munger-skill.git ~/.claude/skills/munger-perspective

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open your terminal.
  2. Create the skills folder if it doesn't exist: mkdir -p ~/.claude/skills
  3. Clone the repo straight into it: git clone https://github.com/alchaincyf/munger-skill.git ~/.claude/skills/munger-perspective
  4. Confirm SKILL.md and the references/ folder are inside that directory.
  5. Restart Claude Code, then try: "Look at this decision from Munger's perspective" or "What cognitive biases are in this plan?"
  6. Company/person analysis relies on web search, so run it in an environment where search is allowed; offline, the skill will instead ask you for a few key facts.
  7. Say "exit the role" or "back to normal" at any time to drop the persona.
View source on GitHub ↗License: MIT