39 Mental Models and Frameworks for Critical Thinking in Claude Code
A comprehensive collection of thinking skills for Claude Code that enhance AI-assisted problem solving, decision making, and strategic analysis. These skills provide structured frameworks based on proven mental models from leaders in systems thinking, cognitive science, and strategic analysis.
- 39 Thinking Frameworks - Comprehensive mental models for better decision-making
- Battle-Tested - Based on proven frameworks from cognitive science and systems thinking
- Claude Code Native - Designed specifically for Claude Code's skill system
- Quality Scripts - Tools to validate and enhance skill quality
- Zero Configuration - Just install and invoke with skill names
Install directly in Claude Code using the plugin system:
# Add the marketplace
/plugin marketplace add tjboudreaux/cc-thinking-skills
# Install the plugin
/plugin install thinking-skills@thinking-skills-marketplaceClone and copy skills directly:
# Clone the repository
git clone https://github.com/tjboudreaux/cc-thinking-skills.git
# Copy skills to your global Claude Code config
cp -r cc-thinking-skills/skills/* ~/.claude/skills/
# Or copy to a specific project
cp -r cc-thinking-skills/skills/* /path/to/your/project/.claude/skills/For testing or development:
claude --plugin-dir ./cc-thinking-skillsOnce installed, invoke any skill by name in Claude Code:
> Use first-principles thinking to analyze this architecture decision
> Apply the pre-mortem framework to this project plan
> Help me use Bayesian reasoning to evaluate this hypothesis
> Use the theory of constraints to find our bottleneck
| Skill | Description | Best For |
|---|---|---|
thinking-first-principles |
Break problems into fundamental truths | Innovation, challenging assumptions |
thinking-second-order |
Think beyond immediate consequences | Strategic decisions, policy changes |
thinking-inversion |
Approach problems by identifying paths to failure | Risk identification, planning |
thinking-pre-mortem |
Imagine failure and work backward | Project kickoffs, risk assessment |
thinking-kepner-tregoe |
Systematic rational process for complex analysis | High-stakes decisions, root cause analysis |
thinking-reversibility |
Classify decisions by reversibility (Type 1/2) | Commitment sizing, risk assessment |
thinking-regret-minimization |
Project to future self to test decisions | Career choices, major life decisions |
thinking-opportunity-cost |
Evaluate choices by what you give up | Resource allocation, prioritization |
| Skill | Description | Best For |
|---|---|---|
thinking-bayesian |
Update beliefs based on evidence | Probability estimation, uncertainty |
thinking-debiasing |
Identify and counteract cognitive biases | Major decisions, high stakes |
thinking-dual-process |
Recognize when to trust intuition vs. analysis | Speed vs. accuracy tradeoffs |
thinking-bounded-rationality |
Make good-enough decisions under constraints | Time pressure, satisficing |
thinking-socratic |
Systematic questioning framework | Requirements, debugging, coaching |
thinking-probabilistic |
Calibrated probability estimation | Forecasting, uncertainty quantification |
thinking-steel-manning |
Argue the strongest opposing position | Debate, decision validation |
| Skill | Description | Best For |
|---|---|---|
thinking-systems |
Analyze interconnected systems | Complex debugging, architecture |
thinking-feedback-loops |
Identify reinforcing and balancing loops | Growth design, organizational dynamics |
thinking-archetypes |
Recognize recurring system patterns | Organizational problems, recurring issues |
thinking-ooda |
Rapid decision-making for dynamic situations | Incident response, competitive scenarios |
thinking-leverage-points |
Find where small changes have big effects | System optimization, intervention design |
thinking-theory-of-constraints |
Identify and manage bottlenecks | Performance optimization, throughput |
thinking-cynefin |
Classify problems by complexity domain | Methodology selection, approach matching |
| Skill | Description | Best For |
|---|---|---|
thinking-occams-razor |
Prefer simpler explanations | Debugging, architecture decisions |
thinking-map-territory |
Recognize limits of mental models | Expectation mismatches, abstractions |
thinking-circle-of-competence |
Know the boundaries of expertise | Delegation, learning decisions |
thinking-triz |
Resolve technical contradictions | Engineering design, innovation |
thinking-five-whys-plus |
Enhanced root cause analysis with bias guards | Debugging, incident postmortems |
thinking-scientific-method |
Hypothesis-driven investigation | Debugging, A/B testing, experimentation |
thinking-thought-experiment |
Structured imagination for exploration | Architecture, edge cases, philosophy |
| Skill | Description | Best For |
|---|---|---|
thinking-fermi-estimation |
Order-of-magnitude calculations | Quick sizing, feasibility checks |
thinking-margin-of-safety |
Build in buffers for uncertainty | Risk management, system design |
thinking-lindy-effect |
Older things likely to last longer | Technology selection, durability |
thinking-via-negativa |
Improve by removing, not adding | Simplification, robustness |
thinking-red-team |
Attack your own plans adversarially | Security review, plan validation |
| Skill | Description | Best For |
|---|---|---|
thinking-jobs-to-be-done |
Understand the job customers hire products for | Product development, feature design |
thinking-effectuation |
Start with means, not goals | Startups, innovation, uncertainty |
| Skill | Description | Best For |
|---|---|---|
thinking-model-router |
START HERE - Route to the right model by domain | Entry point for all thinking skills |
thinking-model-selection |
Choose the right model for the problem | New problems, approach selection |
thinking-model-combination |
Combine multiple models for richer analysis | Complex problems, high-stakes decisions |
This collection includes scripts to maintain and improve skill quality:
Check all skills against quality criteria:
node scripts/validate-skills.jsOutputs a report showing:
- Required sections present/missing
- Quality metrics (examples, tables, checklists)
- Overall score per skill
- Skills needing attention
Get specific improvement suggestions for a skill:
# Single skill
node scripts/enhance-skill.js thinking-first-principles
# All skills summary
node scripts/enhance-skill.jsCreate prompts for Claude to enhance skills:
node scripts/generate-improvement-prompt.js thinking-bayesianThis generates a detailed prompt you can use with Claude Code to systematically improve any skill.
Strip away assumptions to reveal fundamental truths, then rebuild solutions from basics. Championed by Elon Musk and rooted in Aristotle's philosophy.
When to use:
- Conventional approaches have failed
- You're told something is "impossible"
- Need innovation, not incremental improvement
Update beliefs systematically based on new evidence. Provides a framework for thinking about probability and uncertainty.
When to use:
- Estimating probabilities or likelihoods
- Interpreting test results or metrics
- Making decisions with incomplete information
View problems as part of interconnected wholes with feedback loops and emergent properties. Essential for debugging complex distributed systems.
When to use:
- Debugging spans multiple components
- Fix in one place breaks another
- Behavior seems emergent or unexpected
Every system has exactly one constraint limiting throughput. Optimizing anything else is wasted effort. Based on Eliyahu Goldratt's work.
When to use:
- Performance optimization
- Process improvement
- Resource allocation
- Identifying bottlenecks
Classify problems by the relationship between cause and effect: Clear, Complicated, Complex, or Chaotic. Each domain requires a different approach.
When to use:
- Choosing methodologies
- Understanding why approaches fail
- Crisis management
Customers don't buy products—they hire them to do jobs. Understanding the job unlocks innovation.
When to use:
- Product development
- Feature prioritization
- Understanding customer behavior
Attack your own plans before adversaries do. The best defense is knowing your weaknesses.
When to use:
- Security review
- Pre-launch preparation
- Plan stress-testing
We welcome contributions! See CONTRIBUTING.md for guidelines.
- Create a new directory under
skills/with the formatthinking-{name} - Add a
SKILL.mdfile with YAML frontmatter:
---
name: thinking-your-skill-name
description: Brief description under 200 chars (used by Claude Code for skill matching)
----
Write comprehensive documentation with:
- Overview and core principle
- When to use decision flow
- Step-by-step process
- At least 2 practical examples
- Reusable template
- Verification checklist
- Key questions
-
Validate your skill:
node scripts/validate-skills.jsclaude-code claude anthropic ai skills mental-models critical-thinking decision-making problem-solving systems-thinking first-principles bayesian-reasoning cognitive-bias strategic-thinking frameworks triz ooda pre-mortem socratic-method theory-of-constraints cynefin jobs-to-be-done red-team fermi-estimation
- Claude Code Documentation
- Charlie Munger's Mental Models
- Thinking in Systems - Donella Meadows
- Thinking, Fast and Slow - Daniel Kahneman
- The Goal - Eliyahu Goldratt
MIT License - see LICENSE for details.
Created by TJ Boudreaux
Found this useful? Give it a star and share with others who could benefit from better thinking frameworks in Claude Code.