What types of mental models are included in this skill?

The skill includes various models such as 10x scale tests, adversarial analysis (attacker perspective), counterfactuals, role reversals, and time-shift experiments.

How does this skill help improve software resilience?

By systematically tracing the 'blast radius' of component failures, it allows developers to proactively identify where to implement circuit breakers, timeouts, and graceful degradation.

When should I use a thought experiment instead of empirical testing?

Use it when evaluating high-risk architectural changes, exploring theoretical edge cases, or conducting security audits where empirical testing is too slow, costly, or dangerous.

What is the Thought Experiment skill for Claude Code?

It is a specialized framework that enables Claude to simulate hypothetical scenarios and mental models to test software designs and strategies without requiring live code execution.

Thought Experiment Framework

Name: Thought Experiment Framework
Author: tjboudreaux

bytjboudreaux

•

Security & Testing

Evaluates architectural decisions and system resilience through structured hypothetical scenarios and mental models.

The Thought Experiment skill empowers Claude to rigorously test ideas, architectures, and strategies using structured imagination when direct experimentation is impractical or premature. By applying frameworks like failure mode analysis, 10x scaling scenarios, and adversarial role-playing, it helps developers identify hidden edge cases, evaluate long-term consequences, and stress-test system designs before implementation. This skill is essential for high-stakes decision-making, providing a disciplined process to trace consequence chains and derive actionable insights from purely intellectual deliberation.

Key Features

01Counterfactual and time-shift exercises for long-term strategic planning

02Standardized templates for failure mode analysis and resilience verification

03Structured hypothetical scenario modeling to trace system-wide consequences

04Extreme case analysis (10x scale) to identify potential performance bottlenecks

05Adversarial role-reversal to uncover security vulnerabilities and logic flaws

067 GitHub stars

Use Cases

01Pre-build architecture evaluation to avoid costly redesigns and technical debt

02Identifying edge cases and cascading failure modes in complex distributed systems

03Stress-testing system resilience against database or microservice failures

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add tjboudreaux/cc-thinking-skills thinking-thought-experiment

For use in Claude.ai and ChatGPT

Download Skill