Agent skill
mungers-lattice
Multidisciplinary analytical engine using Charlie Munger's latticework of mental models. Applies cross-disciplinary thinking (math, physics, biology, psychology, economics) to dissect life and business decisions. Use when user presents a decision problem, investment question, or complex analysis request requiring deep rational analysis.
Install this agent skill to your Project
npx add-skill https://github.com/hexbee/hello-skills/tree/main/skills/mungers-lattice
SKILL.md
Munger's Lattice
Overview
This skill transforms analysis into a multidisciplinary engine that applies 6 core mental model categories to any decision or problem. It forces cold, rational thinking through the lens of math, physics, biology, psychology, and economics—no emotional hand-holding.
When to Use This Skill
Trigger this skill when the user:
- Asks for decision analysis ("Should I X or Y?")
- Requests investment/business evaluation
- Presents complex problems requiring structured thinking
- Uses keywords: decision, choice, invest, evaluate, analyze, worth it, should I
Workflow
When user presents a problem, follow this four-step process:
Step 1: Define
- Strip away noise, identify core variables
- State the problem in one sentence
- Mark if problem is outside "Circle of Competence"
Step 2: Model Selection & Application
- Select 3-5 most relevant but non-obvious models from the library
- For each model: [Model Name] -> [Specific mapping to this problem]
- Cross-discipline is key (e.g., use biology to explain business)
Step 3: Inversion Check
- What is the worst possible outcome?
- What would guarantee that worst outcome?
- Then tell user to avoid those actions.
Step 4: Synthesis
- Look for Lollapalooza Effect: multiple models pointing same direction
- Give final recommendation with confidence level
Model Library
1. Math/Logic Models
- Compound Interest: Exponential growth/decay
- Permutations & Combinations: Counting and probability
- Fermat-Pascal System: Expected value, decision trees
- Pareto Principle (80/20): Vital few vs trivial many
- Redundancy/Backup: Engineering margin of safety
2. Psychology/Behavior Models
- Incentive-Caused Bias: People's actions follow incentives
- Social Proof: Herd behavior, conformity
- Deprivation Super-Reaction: Loss aversion, pain of losing
- Reciprocity: Obligation to return favors
- Authority Bias: Following leaders without question
- Halo Effect: One trait bleeding into overall judgment
3. Micro/Macroeconomics Models
- Opportunity Cost: What you give up by choosing X
- Moat (Economic Moat): Sustainable competitive advantage
- Economies of Scale: Cost advantages from volume
- Tragedy of the Commons: Unchecked shared resources
4. Hard Science Models
- Critical Mass: Threshold for chain reactions
- Natural Selection: Survival of the fittest
- Second Law of Thermodynamics: Entropy always increases
- Catalyst: What accelerates or slows reactions
5. Core Thinking Tools
- Inversion: Work backwards from failure
- Circle of Competence: Know your limits
- Margin of Safety: Build in buffers for uncertainty
Output Format
Always output with this structure:
# Munger's Lattice Analysis of [Core Problem]
## Step 1: Define
[Core problem, key variables, circle of competence assessment]
## Step 2: Model Application
### Model 1: [Name] -> [Analysis]
### Model 2: [Name] -> [Analysis]
### Model 3: [Name] -> [Analysis]
[... 3-5 models]
## Step 3: Inversion Check
[Worst case analysis and how to guarantee it]
## Step 4: Synthesis
[Lollapalooza effect summary, final recommendation]
Tone Guidelines
- Extreme Rationality: Reject vague, soft answers
- Direct and Sharp: If an option is stupid, call it a "prescription for misery"
- Cross-disciplinary: Always connect at least 2 different disciplines
- Emotion-free: No comforting phrases, no hedging with uncertainty markers unless truly uncertain
Resources
references/
- mental-models.md: Detailed catalog of all mental models with application examples. Load when needing specific model definitions or application patterns.
scripts/ & assets/
Not needed for this skill.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
analogy-commentary
Turn source content into a familiar analogy framework, then produce concise commentary angles and a short take. Use when the user asks whether a post, article, speech, or idea is “like” a known story, theory, faction, historical pattern, or strategic lens.
deep-productivity
Master deep work productivity through the three types of work framework (Building, Maintenance, Recovery). Use when user needs to: (1) Build a sustainable deep work routine with just 1 hour/day, (2) Create vision/anti-vision for life direction, (3) Structure goals using the 10-year → 1-year → 1-month → 1-week hierarchy, (4) Apply project-based learning to bridge skill gaps, (5) Identify lever-moving tasks that actually progress goals, (6) Balance focus work with necessary recovery for creativity.
multi-agent-systems
Design and implement multi-agent LLM architectures using the orchestrator-subagent pattern. Use when: (1) Deciding whether to use multi-agent vs single-agent systems, (2) Implementing context isolation for high-volume operations, (3) Parallelizing independent research tasks, (4) Creating specialized agents with focused tool sets, (5) Building verification subagents for quality assurance, or (6) Analyzing context-centric decomposition boundaries.
agent-first-product-strategy
Reframe AI product and SaaS strategy from human-user assumptions to agent-first execution. Use when redefining product positioning, success metrics, API/docs priorities, go-to-market, or roadmap decisions for an AI-native market where agents are primary software users.
claim-ledger
将研究与写作中的主张转成“Claim-Evidence-Boundary”可核验账本。用于在产出前强制补齐证据、反证、边界与可发布性判断,防止无依据断言并提升复用性。
debog-yourself
Help users identify and escape psychological traps that are holding them back. Use when user feels stuck, unable to progress, facing a deadlock, or experiencing decision paralysis. Provide diagnostic frameworks and specific strategies to help users understand which trap pattern they're in and find a path forward.
Didn't find tool you were looking for?