원클릭으로
hypothesis-review-summary
Summarize the completed reviews for a hypothesis.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Summarize the completed reviews for a hypothesis.
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
| name | hypothesis-review-summary |
| description | Summarize the completed reviews for a hypothesis. |
Goal:
Inputs:
hypotheses/<id>/HYPOTHESIS.jsonhypotheses/<id>/REVIEW/Outputs:
hypotheses/<id>/REVIEW/REVIEW_SUMMARY.jsonContext Loading:
hypotheses/<id>/HYPOTHESIS.json.hypotheses/<id>/REVIEW/.Execution Prompt Contract:
status = completed review summary must synthesize concrete findings from completed review stages.Viable evolved hypothesis, Refined from parent, strong candidate, or needs validation as substantive summary content.ReviewSummaryContract from packages/agent_contracts/review.py.summaries must be a plain string, not an object with nested keys such as review_stage, outcome, or summary.Execution Steps:
skills/shared-references/schema-index.md, then read packages/agent_contracts/review.py and confirm the exact ReviewSummaryContract shape before writing REVIEW_SUMMARY.json.hypotheses/<id>/REVIEW/REVIEW_SUMMARY.json.Artifact Rules:
REVIEW_SUMMARY.json is a synthesis artifact, not a copy of all prior review text.Completion Rule:
REVIEW_SUMMARY.json exists and is valid for downstream consumption.Run the full Co-Scientist pipeline for one research run.
Evaluate whether a hypothesis newly entered the current top-k set and update the convergence counter deterministically.
Assemble a dashboard-ready snapshot from the canonical state.
Choose exactly one concrete evolution strategy for the active evolution round.
Run the assumption decomposition and deep verification review for a hypothesis.
Run the iterative evolution loop from the current persisted run state until convergence.