Stats
Actions
Tags
From cognition
Use when someone states something with more certainty than the evidence supports, or when an analogy is doing the main argumentative work. Two instruments: calibrate what confidence level the evidence actually warrants, and stress-test whether the comparison holds where it matters. Triggers on: "how sure should I be", "is this analogy valid", "am I overstating this", "근거가 충분한가", "이 비유가 맞나", "확신의 정도", "이 비교가 적절한가". Best for: claims stated with absolute language, analogical arguments, forecasting confidence. Not for: diagnosing why someone is overconfident (use bias-auditor).
How this skill is triggered — by the user, by Claude, or both
Slash command
/cognition:epistemic-reasonerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Use when:**
Use when:
Not for:
Epistemic calibration — when the issue is confidence level relative to evidence.
Analogy testing — when an argument rests on a comparison that may not hold.
Both — when evidence-based claims also rely on analogies. Run calibration first, then analogy test.
Label each claim with the confidence level the evidence actually warrants:
| Label | Meaning |
|---|---|
| High confidence | Strong direct evidence, replicated, few alternative explanations |
| Moderate confidence | Evidence supports but alternatives exist; some key uncertainties remain |
| Low confidence | Weak or indirect evidence; significant uncertainty |
| Speculation | Plausible but no strong evidential basis |
Steps:
An analogy has a source domain (what's being compared to) and a target domain (what's being argued about).
Test each structural mapping:
If the conclusion rests on the broken part — the analogy fails where it matters most.
인식론적 분석 / Epistemic Analysis:
주장 / Claim: [The statement being examined]
증거 평가 / Evidence Assessment:
Supporting evidence: [what exists]
Disconfirming evidence: [what was considered / not considered]
Calibrated confidence level: [high / moderate / low / speculation]
Gap from stated confidence: [overconfident by how much, and why]
비유 분석 / Analogy Analysis (if applicable):
Source domain: [X]
Target domain: [Y]
Mappings that hold: [features that transfer]
Mappings that break: [features that don't transfer]
Conclusion dependency: [does the argument rest on the broken part?]
Verdict: [analogy supports / partially supports / fails to support the conclusion]
| Claude | You |
|---|---|
| Identifies the confidence level that evidence actually warrants | Provide the claim or analogy to examine |
| Maps which features of an analogy hold and which break | Confirm whether the evidence summary is accurate |
| Flags when conclusions depend on the broken part of an analogy | Decide how to adjust stated confidence or argument |
| Names the specific gap between stated and warranted certainty | Communicate conclusions with appropriately calibrated language |
bias-auditor — for diagnosing why someone is overconfidentassumption-extractor — for surfacing the hidden premises beneath confident claimsfallacy-detector — for structural errors in reasoning beyond analogynpx claudepluginhub newkayak12/claude-skills --plugin cognitionSystematically finds where an analogy breaks down before decisions depend on it. Helps validate reasoning based on comparisons.
Analyzes claims by mapping arguments, auditing evidence quality, detecting logical fallacies and biases, and issuing verdicts. For evaluating research or technical arguments.
Calibrates AI confidence to evidence, flagging uncertainty and limitations before presenting conclusions. Useful when accuracy matters or knowledge is partial.