From grimoire
Applies mental models (first principles, inversion, second-order thinking) to reason through complex decisions and avoid cognitive biases.
How this skill is triggered — by the user, by Claude, or both
Slash command
/grimoire:apply-mental-models-frameworkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Apply a set of cross-disciplinary mental models — including first principles, inversion, second-order thinking, the map vs. territory distinction, and probabilistic thinking — to reason through complex decisions more clearly and avoid common cognitive biases.
Apply a set of cross-disciplinary mental models — including first principles, inversion, second-order thinking, the map vs. territory distinction, and probabilistic thinking — to reason through complex decisions more clearly and avoid common cognitive biases.
Adopted by: Charlie Munger popularized the "latticework of mental models" approach to decision-making in his Poor Charlie's Almanack (2005), citing the benefits of cross-disciplinary thinking for investors, scientists, and business leaders. Shane Parrish's Farnam Street and "The Great Mental Models" series have made these frameworks widely accessible. Daniel Kahneman's "Thinking, Fast and Slow" provides the psychological research foundation for why System 1 intuitive thinking produces predictable errors and System 2 deliberate reasoning (supported by explicit mental models) corrects them. Impact: The biases documented by Kahneman and Tversky (anchoring, availability heuristic, confirmation bias, planning fallacy, survivorship bias) are not eliminated by intelligence — they are eliminated by process. Mental models are the explicit reasoning tools that create a process-based override for intuitive errors. Research by Milkman et al. (2009) shows that decision-making quality improves when people are prompted to consider multiple perspectives and alternative scenarios — exactly what the mental models here provide.
What it is: decompose a problem to its most fundamental, undeniable truths and rebuild from there rather than reasoning from analogy ("we do it this way because that's how it's done")
How to apply:
Example: conventional thinking about cars: "cars look like this because that's what cars look like." First-principles thinking: "a car needs to move people from A to B, provide safety from impact, and withstand weather. Starting from physics, what's the optimal way to do this?" First-principles reasoning produces Tesla; conventional reasoning produces incremental improvements to existing designs.
Common error: confusing "how things are done" with "how things must be done"; most conventional practices are not derived from first principles — they are accumulated conventions that may or may not reflect optimal solutions.
What it is: instead of asking "how do I achieve X?", ask "how would I ensure I fail at X, or how would I cause X to go terribly wrong?" — then avoid the failure conditions
How to apply:
Munger: "All I want to know is where I'm going to die, so I'll never go there."
Application to decision-making: when choosing between options, invert: "what would I have to believe for this option to be clearly wrong?" If the beliefs required to reject an option are ones you actually hold, the option is probably wrong.
Application to project planning: "what would cause this project to fail?" produces more useful pre-mortems than "how will this project succeed?" because failure modes are often more specific and actionable than success conditions.
What it is: when evaluating an action, trace the consequences not just of the first-order effect (what happens immediately) but of the second and third-order effects (what happens as a result of the first-order effect)
How to apply:
Example: First-order: prescribe more opioids for pain management. Second-order: pain is better managed; dependence increases. Third-order: prescription rates are high; diversion to non-medical use increases; opioid crisis.
Application trigger: whenever someone says "this is clearly good," ask "and then what?" — trace the causal chain two to three steps further than the immediate conclusion.
What it is: all models (including mental models) are simplifications; the map is not the territory; treat maps as useful approximations, not as reality
How to apply:
Application: economic models, medical guidelines, organizational charts — all are maps. The organizations that fail most spectacularly often fail because they optimize for the map (the financial model, the org chart) while reality (the territory) diverges from it. Enron optimized for its accounting model; the territory (actual business economics) was fundamentally different.
What it is: replace binary thinking ("this will succeed / this will fail") with probability distributions across outcomes
How to apply:
Base rate neglect: the most common error in probabilistic thinking is ignoring the base rate in favor of the specific features of the current case. "This startup will succeed because..." ignores the base rate that approximately 90% of startups fail. Incorporate the base rate before adjusting for specific features.
npx claudepluginhub jeffreytse/grimoire --plugin grimoireApplies Naval Ravikant's mental models like compound interest, inversion, principal-agent problem to analyze complex situations, counterintuitive ideas, or business/life decisions.
Challenges assumptions, applies mental models like SWOT, first principles, and inversion, and structures reasoning to sharpen decisions and solve complex problems.
Selects the right mental model for diagnosing problems, making decisions, or analyzing complex situations. Use when current approaches fail or you face unfamiliar problem types.