critical-thinkinglisted
Install: claude install-skill deciqAI/knowledge-skills
# Critical Thinking
## Overview
**Critical thinking** evaluates a conclusion by **explicitly testing it against alternative interpretations** — the conclusion that survives the most disconfirmation attempts is the one to act on, not the one with the most confirming examples. Operationalized by **Richards J. Heuer Jr.** (CIA, 1999) as **Analysis of Competing Hypotheses (ACH)**: a matrix marking each evidence-hypothesis pair as Consistent / Inconsistent / N/A. The hypothesis with the **fewest Inconsistencies** wins.
**Compose:** [first-principles](../first-principles/SKILL.md) (surface assumptions) · [probabilistic-thinking](../probabilistic-thinking/SKILL.md) (calibrate evidence) · [inversion](../inversion/SKILL.md) (generate alternatives). Critical thinking = *evaluation*; first-principles = *construction*; occams = *selection*; second-order = *projection*.
## When to Use
- High-stakes claim (yours or someone else's) that needs evaluation
- Multiple interpretations of the same evidence are possible
- Motivated reasoning detected — conclusion shaped by what you want to be true
- Team converging on a hypothesis too fast without seriously considering alternatives
- Evaluating an AI capability or AI-hype claim (e.g. "this benchmark proves the model reasons") where the same evidence fits several explanations (contamination, cherry-picking, teaching-to-the-eval)
**When NOT to use:** trivial/already-validated claim; only one hypothesis imaginable (use [first-principles](../fir