This repository is a knowledge package designed to create an AI agent skill that embodies Charlie Munger's thinking framework. It doesn't contain executable code but rather curates and structures Munger's mental models, decision heuristics, and communication style into a usable format for AI agent runtimes. The core output is the SKILL.md file, which provides detailed instructions for how an AI agent should adopt Munger's perspective when responding to user queries, including role-playing rules, a response workflow requiring research before answering, and specific guidelines for expressing Munger's characteristic communication style. The repository represents a sophisticated approach to expertise capture and encoding for AI systems. It synthesizes information from over 50 sources including Berkshire Hathaway shareholder meetings, USC/Harvard speeches, interview records, and external criticisms to distill Munger's approach into five core mental models, eight decision heuristics, and a detailed expression DNA. The references/ directory contains the source research materials, demonstrating transparency about the knowledge foundation. Examples/show how the skill works in practice through sample conversations about investment decisions, team management, and content creation. While primarily a knowledge resource, the structure of the SKILL.md file itself offers potential reusability as a template for creating similar 'thinking style' skills for other experts or domains. The systematic approach to encoding expertise through role-playing protocols, mental model collections, decision frameworks, and communication guidelines represents a pattern that could be adapted with domain-specific content substitution for other AI agent skills.