── ── Cognitive bias
Logical Fallacies
A fallacy is an argument that looks like it works but doesn't. The test is not whether the conclusion is true — it's whether the inference from premises to conclusion is valid. This skill covers two layers: the classical taxonomy (Aristotle's 13, c. 350 BCE — verbal and structural errors) and the modern cognitive map (Tversky-Kahneman 1983 — errors competent…
Run Logical Fallacies on a real problem
Bring something you're actually deciding — free, in the browser.
How it works
Run the Fallacy Audit in four passes — structure, language, cognition, rhetoric — then judge.
1. State the argument cleanly. Rewrite as premises → conclusion. If you cannot, first finding: it's an assertion dressed as an argument. 2. Structural pass. Begging the question, affirming the consequent, denying the antecedent, false cause (post hoc), hasty generalization, accident, complex question, ignoratio elenchi. 3. Linguistic pass. Equivocation (key term shifts meaning), amphiboly, composition/division (part↔whole), accent/figure of speech. 4. Cognitive pass. Conjunction fallacy (P(A∧B) > P(A) from representativeness), base-rate neglect, availability, anchoring — see anchoring. 5. Rhetorical-trap pass. Ad hominem, appeal to authority (exception: expert in own domain), appeal to popularity (weak prior only), appeal to emotion (evidence vs. substitute), false dichotomy, straw man, slippery slope, tu quoque. 6. Judge the argument, not the moves. A fallacy means the inference fails — not that the conclusion is false. 7. Fallacy-fallacy check. If you can't articulate why this instance fails, you have a dismissal, not a finding. 8. Output: for each fallacy — (a) which and where, (b) what the inference fails to establish, (c) what would actually support the conclusion.
When to use it
- someone says 'this argument feels off but I can't explain why', 'is this a real argument or just rhetoric?', 'what's wrong with this reasoning?', an argument relies entirely on authority/emotion/popularity, or you're about to decide based on a single analogy
When not to use it
the conclusion is already verifiable empirically (just check the data); casual conversation where rigor is socially expensive and stakes are low.
Worked example
Four Fallacies in the 2024–2026 AI Debate
The Linda problem shows the fallacy filter under laboratory conditions. This example runs the same Fallacy Audit on messy public discourse — the argument about artificial intelligence as it circulated across roughly 2024–2025. This is the environment the skill was built for: claims that sound authoritative, move fast, and carry high stakes, where naming the fallacy is only useful if you can also say what would actually settle the question.
Install this skill (free, MIT)
npx skills add deciqAI/knowledge-skillsUseful? Star the repo — stars help other builders find it.
Related mental models
Most leadership programs target skill acquisition.
The narrative fallacy is the tendency to construct retrospective causal stories that make past events seem inevitable — even when those events were largely random or…
Maps competitive position across four strategic dimensions: Point (one capability, easily copied) → Line (integrated pipeline, integration is the asset) → Plane (platform/ecosystem where others transact…
Positioning (April Dunford, Obviously Awesome, 2019) is the context you set so customers instantly understand why your product is great for them.