surface-assumptions

사용 방법

설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.

npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill surface-assumptions

시작 전 확인

설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.

원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Purpose

Enumerate explicit and implicit assumptions in a claim, model, method, decision, or design and expose their evidential status.

Input contract

yaml

required: [artifact, claim_or_decision, context]
optional: [causal_claims, evidence, stakeholder_views, assumption_taxonomy]
constraints: [separate explicit from implicit assumptions; preserve the artifact's wording; attach evidence strength and criticality to each assumption]

Procedure

Parse the artifact into claims, dependencies, conditions, and unstated background requirements.
Enumerate assumptions and classify each as explicit or implicit and by type.
Attach supporting or contradicting evidence and rate assumption strength and criticality.
Mark assumptions whose failure would change the conclusion and return the assumption register.

Output contract

yaml

produces: [assumption_register, evidence_assessments, critical_assumptions, dependency_notes]
delta_fields: [findings, evidence_updates, uncertainties, recommended_jumps]

Quality gates

Every assumption has a type, explicit/implicit status, evidence assessment, and criticality rating.
The register distinguishes load-bearing assumptions from decorative assumptions and preserves interaction effects when supplied.
Do not replace enumeration with a generic risk paragraph.

Parameterization

The caller must provide the artifact or claim, the context and intended conclusion, any known causal claims, the assumption taxonomy, evidence sources, and the rating scale for strength and criticality.

Failure and counterexamples

Reject when the artifact or conclusion is missing, assumptions are asserted without relation to the claim, or contradictory evidence is silently omitted.