メニュー
Before asserting a universal claim — always, never, all, none, guaranteed, impossible — spend one bounded search for a counterexample, starting at the edges of the quantifier's domain.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Check a deliverable against its actual consumer: who reads it, what they do next, what format and register they need, and what they will assert downstream on its basis. Activate when the deliverable has a named audience beyond the requester, or its text will be forwarded, announced, or acted on by someone absent from the conversation.
For any rule-like deliverable — code, regex, query, formula, validator, policy — enumerate the boundary inputs (empty, zero, one, max, duplicate, malformed, hostile) and actually exercise the most breakable three before shipping. Activate when the deliverable is executable or rule-like and will meet inputs the author didn't type.
State every claim at its actual evidence level — verified, inferred, assumed, guessed — and give credences only where an observable could score them; ban certainty language on unverified claims. Activate when a response makes claims about unobserved, future, or unverified state, or when the user asks how confident or likely something is.
Before intervening in a system, write the explicit causal chain from the proposed action to the intended outcome — every arrow marked verified or assumed — and check the weakest assumed arrow first. Activate when an intervention (fix, optimization, policy change, growth action) is proposed on a system whose mechanism has not been written down.
With multiple live hypotheses and a limited test budget, design the cheapest single test whose possible outcomes separate the hypotheses — with a results-to-verdict table committed before running anything. Activate when two or more competing hypotheses are on the table and the next step is choosing what test, experiment, or probe to run.
Enumerate every deliverable the request actually asked for and map each one to the work produced, so nothing asked-for is silently dropped, stubbed, or rounded up to done. Activate when a request contains multiple parts — an enumerated list, several 'and'/'also' clauses, or a spec with more than one required artifact — or before delivering a draft against such a request.
| name | counterexample-search |
| description | Before asserting a universal claim — always, never, all, none, guaranteed, impossible — spend one bounded search for a counterexample, starting at the edges of the quantifier's domain. |
| license | MIT |
Trigger (observable): The draft contains a universal quantifier or impossibility claim ('this always terminates', 'no user can reach this state', 'works for all inputs'), or the task asks whether a property holds in general.
When NOT to activate: Claims already scoped to observations ('in the 30 cases tested...'); definitional truths (tautologies, type guarantees enforced by a compiler); casual prose where the quantifier is rhetorical and nothing depends on it.
Per universal claim: the strongest counterexample candidate, the result of actually testing it, and the claim kept / weakened / withdrawn accordingly.
Known risk: Unbounded hunting — burning the session on exotic cases for low-stakes claims. Mitigation: one strongest candidate per claim, actually tested, then move on.
Max intended cost: ≤200 added output tokens plus at most one execution/trace per universal claim.
Evidence status: DESIGNED — specified from documented reasoning-failure modes; not yet executed as a packaged skill.
Lineage: Derived from a documented reasoning-failure mode — reaching a plausible answer and stopping without probing it — combined with an adversarial-probe verification pattern from the broader Piénsalo skill family.
