{"kind":"Skill","metadata":{"namespace":"community","name":"thinking-model-combination","version":"0.1.0"},"spec":{"description":"Combine multiple mental models for richer analysis. Use for complex problems requiring multiple lenses, high-stakes decisions, or when single models leave blind spots.","files":{"SKILL.md":"---\nname: thinking-model-combination\ndescription: Combine multiple mental models for richer analysis. Use for complex problems requiring multiple lenses, high-stakes decisions, or when single models leave blind spots.\n---\n\n# Model Combination\n\n## Overview\n\nReal-world problems rarely fit neatly into a single mental model. Model combination uses multiple frameworks together—sequentially, in parallel, or nested—to achieve deeper understanding than any single model provides. The skill is knowing how to combine models productively without creating confusion or analysis paralysis.\n\n**Core Principle:** Multiple lenses reveal what single lenses miss. But combination requires discipline, not just accumulation.\n\n## When to Use\n\n- Complex problems spanning multiple domains\n- High-stakes decisions where blind spots are costly\n- When single models leave important questions unanswered\n- Validating conclusions through different frameworks\n- Teaching comprehensive analysis\n- Building robust decision processes\n\nDecision flow:\n\n```\nAnalyzing a problem?\n  → Does one model fully address it? → yes → Use single model\n  → Are there important blind spots? → yes → ADD COMPLEMENTARY MODEL\n  → Are stakes high enough to justify deeper analysis? → yes → USE MULTIPLE MODELS\n```\n\n## Combination Patterns\n\n### Pattern 1: Sequential (Pipeline)\n\nUse one model's output as another's input:\n\n```markdown\n## Sequential Combination\n\nModel A → Model B → Model C\n\nExample: Product Decision\n1. Jobs to be Done → Identify the real user need\n2. First Principles → Design solution from fundamentals\n3. Pre-mortem → Identify what could go wrong\n4. Reversibility → Assess if we can course-correct\n\nFlow:\n[JTBD identifies need] → [First Principles designs solution] →\n[Pre-mortem finds risks] → [Reversibility determines commitment level]\n\nEach model builds on previous insights.\n```\n\n### Pattern 2: Parallel (Multiple Lenses)\n\nApply models independently, compare results:\n\n```markdown\n## Parallel Combination\n\n     ┌→ Model A → Result A ─┐\nProblem → Model B → Result B → Synthesis\n     └→ Model C → Result C ─┘\n\nExample: Strategic Decision\nApply independently:\n- Red Team: \"How could this fail?\"\n- Opportunity Cost: \"What are we giving up?\"\n- Second-Order Thinking: \"What happens next?\"\n\nSynthesis:\n| Model | Conclusion | Unique Insight |\n|-------|------------|----------------|\n| Red Team | [Finding] | [What only this revealed] |\n| Opportunity Cost | [Finding] | [What only this revealed] |\n| Second-Order | [Finding] | [What only this revealed] |\n\nCombined conclusion: [Synthesis of all three]\n```\n\n### Pattern 3: Nested (Zoom Levels)\n\nUse different models at different scales:\n\n```markdown\n## Nested Combination\n\nMacro level: Model A\n  └→ Meso level: Model B\n       └→ Micro level: Model C\n\nExample: System Optimization\n- Macro (System): Theory of Constraints → Find the bottleneck\n- Meso (Process): Scientific Method → Diagnose bottleneck cause\n- Micro (Action): OODA Loop → Rapid iteration on fixes\n\nThe macro model identifies WHERE to focus.\nThe meso model identifies WHAT is happening.\nThe micro model guides HOW to respond.\n```\n\n### Pattern 4: Adversarial (Thesis-Antithesis)\n\nUse models that challenge each other:\n\n```markdown\n## Adversarial Combination\n\nModel A argues FOR → ← Model B argues AGAINST\n\nExample: Investment Decision\n- Optimistic lens (First Principles): \"Here's why this could work\"\n- Pessimistic lens (Pre-mortem): \"Here's why this will fail\"\n- Neutral lens (Bayesian): \"Here's the actual probability\"\n\nStructure:\n| Aspect | First Principles | Pre-mortem | Bayesian Estimate |\n|--------|------------------|------------|-------------------|\n| Market | [Optimistic case] | [Failure mode] | [P(success)] |\n| Technology | [Optimistic case] | [Failure mode] | [P(success)] |\n| Team | [Optimistic case] | [Failure mode] | [P(success)] |\n\nResolution: Adjust probabilities based on adversarial insights\n```\n\n### Pattern 5: Temporal (Time-Based)\n\nDifferent models for different time horizons:\n\n```markdown\n## Temporal Combination\n\nPast: Model A (understand history)\nPresent: Model B (assess current state)\nFuture: Model C (project outcomes)\n\nExample: Career Decision\n- Past (5 Whys): \"Why am I in this situation?\"\n- Present (Circle of Competence): \"What are my current advantages?\"\n- Future (Regret Minimization): \"What will 80-year-old me think?\"\n\nTimeline:\nPast analysis → Present assessment → Future projection → Decision\n```\n\n## Combination Recipes\n\n### Recipe 1: High-Stakes Decision\n\n```markdown\n## High-Stakes Decision Recipe\n\nCombine: Reversibility + Pre-mortem + Opportunity Cost + Second-Order\n\nStep 1 - Reversibility Check:\nIs this Type 1 or Type 2?\n[Assessment]\n\nStep 2 - Pre-mortem:\nAssume failure, explain why\n[Failure modes]\n\nStep 3 - Opportunity Cost:\nWhat's the best alternative?\n[Alternatives foregone]\n\nStep 4 - Second-Order:\nWhat happens after the immediate effect?\n[Cascading consequences]\n\nSynthesis:\nGiven [reversibility], with risks of [pre-mortem findings],\ngiving up [opportunity cost], leading to [second-order effects],\nthe decision is: [Conclusion]\n```\n\n### Recipe 2: System Diagnosis\n\n```markdown\n## System Diagnosis Recipe\n\nCombine: Cynefin + Theory of Constraints + Feedback Loops + Leverage Points\n\nStep 1 - Cynefin:\nWhat domain is this? [Clear/Complicated/Complex/Chaotic]\nAppropriate approach: [Sense-Categorize-Respond / Sense-Analyze-Respond / etc.]\n\nStep 2 - Theory of Constraints:\nWhere's the bottleneck?\n[Constraint identification]\n\nStep 3 - Feedback Loops:\nWhat reinforcing/balancing loops exist?\n[Loop mapping]\n\nStep 4 - Leverage Points:\nWhere can small changes have big effects?\n[Intervention points]\n\nSynthesis:\nThis is a [domain] problem. The constraint is [X].\nThe key feedback loop is [Y]. The highest leverage point is [Z].\n```\n\n### Recipe 3: Innovation Challenge\n\n```markdown\n## Innovation Recipe\n\nCombine: First Principles + TRIZ + Effectuation + Via Negativa\n\nStep 1 - First Principles:\nWhat are the fundamental truths?\n[Core elements]\n\nStep 2 - TRIZ:\nWhat contradictions exist? What inventive principles apply?\n[Contradiction resolution]\n\nStep 3 - Effectuation:\nWhat means do we have? What's affordable loss?\n[Means inventory and constraints]\n\nStep 4 - Via Negativa:\nWhat should we remove or avoid?\n[Subtractions]\n\nSynthesis:\nStarting from [first principles], resolving [contradiction] via [TRIZ principle],\nusing [available means], and removing [via negativa items],\nthe innovation path is: [Approach]\n```\n\n### Recipe 4: Argument Evaluation\n\n```markdown\n## Argument Evaluation Recipe\n\nCombine: Steel-manning + Bayesian + Debiasing\n\nStep 1 - Steel-manning:\nWhat's the strongest version of this argument?\n[Strengthened argument]\n\nStep 2 - Bayesian:\nWhat's my prior? What evidence would update it?\nPrior: [X%]\nEvidence that would increase: [List]\nEvidence that would decrease: [List]\n\nStep 3 - Debiasing:\nWhat biases might affect my evaluation?\n[Bias checklist]\n\nSynthesis:\nThe steel-manned argument is [X]. Given [evidence] and controlling for [biases],\nmy updated probability is [Y%]. Conclusion: [Assessment]\n```\n\n## Combination Anti-Patterns\n\n### Too Many Models\n\n```markdown\n## Anti-Pattern: Model Soup\n\nProblem: Using 5+ models without clear purpose\nResult: Confusion, analysis paralysis, contradictory conclusions\n\nSymptoms:\n- Can't synthesize findings\n- Each model says something different\n- Analysis takes forever\n- No clear recommendation emerges\n\nFix: Maximum 3-4 models with clear roles\n     Define how models relate BEFORE applying\n     Designate a \"tiebreaker\" model for conflicts\n```\n\n### Incompatible Models\n\n```markdown\n## Anti-Pattern: Forced Marriage\n\nProblem: Combining models with conflicting assumptions\nExample: Effectuation (embrace uncertainty) + Detailed planning (predict future)\n\nSymptoms:\n- Models contradict each other fundamentally\n- Can't reconcile conclusions\n- Feels like arguing with yourself\n\nFix: Use models in sequence for different phases\n     Or use as adversarial pair intentionally\n     Don't try to blend incompatible worldviews\n```\n\n### Model Without Purpose\n\n```markdown\n## Anti-Pattern: Checkbox Combination\n\nProblem: Adding models to seem thorough, not for insight\nResult: Wasted effort, no additional value\n\nSymptoms:\n- Model confirms what you already knew\n- No new insights from additional model\n- Adding models \"just in case\"\n\nFix: Add model only if it addresses a specific blind spot\n     Ask: \"What question does this model answer that others don't?\"\n```\n\n## Model Combination Template\n\n```markdown\n# Model Combination Analysis: [Problem]\n\n## Problem Characterization\n[Describe the problem and why combination is needed]\n\n## Combination Pattern\nPattern: [Sequential/Parallel/Nested/Adversarial/Temporal]\nRationale: [Why this pattern]\n\n## Models Selected\n| Model | Role | What It Addresses |\n|-------|------|-------------------|\n| | | |\n\n## Analysis\n\n### Model 1: [Name]\n[Analysis using this model]\nKey insight: [What this uniquely revealed]\n\n### Model 2: [Name]\n[Analysis using this model]\nKey insight: [What this uniquely revealed]\n\n### Model 3: [Name]\n[Analysis using this model]\nKey insight: [What this uniquely revealed]\n\n## Synthesis\n\n### Convergence\nWhere models agree: [Common conclusions]\n\n### Divergence\nWhere models differ: [Conflicting conclusions]\nResolution: [How to resolve conflicts]\n\n### Unique Contributions\n| Model | Unique Insight |\n|-------|----------------|\n| | |\n\n## Combined Conclusion\n[Synthesis that incorporates all models]\n\n## Confidence Assessment\nConfidence in conclusion: [High/Medium/Low]\nWhat would change my mind: [Key uncertainties]\n```\n\n## Verification Checklist\n\n- [ ] Each model has a clear, distinct role\n- [ ] Combination pattern is explicit\n- [ ] Models are compatible or deliberately adversarial\n- [ ] Synthesis addresses convergence and divergence\n- [ ] Not using more models than necessary\n- [ ] Clear combined conclusion emerges\n\n## Key Questions\n\n- \"What does each model contribute that others don't?\"\n- \"How do these models relate to each other?\"\n- \"Where do the models agree? Disagree?\"\n- \"Am I adding models for insight or just thoroughness?\"\n- \"What's the simplest combination that addresses the problem?\"\n- \"How do I synthesize if models conflict?\"\n\n## Munger's Wisdom (Extended)\n\n\"I've long believed that a certain system—which almost any intelligent person can learn—works way better than the systems most people use. What you need is a latticework of mental models in your head.\"\n\n\"You may have noticed students who just try to remember and pound back what is remembered. Well, they fail in school and in life. You've got to hang experience on a latticework of models in your head.\"\n\nThe latticework isn't just having models—it's the connections between them. Combination is how you weave the lattice. Individual models are threads; combination creates the fabric that catches reality's complexity.\n"},"import":{"commit_sha":"a31e22d4445ad8fef7cd771d32af537aebb68c49","imported_at":"2026-05-22T21:14:39Z","license_text":"MIT License\n\nCopyright (c) 2025 TJ Boudreaux\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n","owner":"tjboudreaux","repo":"tjboudreaux/cc-thinking-skills","source_url":"https://github.com/tjboudreaux/cc-thinking-skills/tree/a31e22d4445ad8fef7cd771d32af537aebb68c49/skills/thinking-model-combination"}},"content_hash":[63,199,164,208,124,116,223,11,183,104,146,143,67,60,93,115,151,81,207,149,176,20,9,211,204,142,241,91,147,224,182,160],"trust_level":"unsigned","yanked":false}