메뉴
When enumerating causes, ideas, or hypotheses, generate candidates that are distinct causal mechanisms — not paraphrases of the symptom or of each other — including classes with no lexical footprint in the evidence.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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 | distinct-mechanism-generation |
| description | When enumerating causes, ideas, or hypotheses, generate candidates that are distinct causal mechanisms — not paraphrases of the symptom or of each other — including classes with no lexical footprint in the evidence. |
| license | MIT |
Trigger (observable): The task asks for multiple explanations, causes, ideas, or hypotheses ('brainstorm', 'list possible causes', 'what could explain'), or a draft candidate list exists whose items restate the input's wording.
When NOT to activate: The hypothesis space is already saturated and validated candidates await application (switch from generation to applying known results); a single known-correct answer exists; candidate count was explicitly capped at one by the user.
A numbered candidate list where each entry is a distinct one-line mechanism; top candidates carry why + falsifying test; at least one candidate has no lexical overlap with the input's wording.
Known risk: Padding with exotic mechanisms to hit distinctness while the mundane likely cause gets crowded out. Mitigation: distinctness prunes duplicates; it never mandates exotic additions.
Max intended cost: ≤400 added output tokens for the list; no tool calls required for generation itself.
Evidence status: DESIGNED — specified from documented reasoning-failure modes; not yet executed as a packaged skill.
Lineage: Derived from an evidence-backed breadth-without-depth-tax principle (adding detail to top candidates must not shrink the candidate set) and from a documented reasoning-failure mode — candidate lists that paraphrase the symptom instead of naming distinct causal mechanisms.
