메뉴
Score the given theory according to certain per-theory subscore criteria.
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
Design and propose the next step: either a regular data-gathering experiment, literature search, or a concrete solution candidate.
Determine the type of proposal given, execute/delegate accordingly, and return the appropriate resulting ID (experiment ID, literature search ID, or solution ID).
Score and rank solution candidates relative to the research goal, and update parent theory scores.
Integrate recent interpretations from the interpretation log into the associated theory.
Rank the given experiments based on their importance for evaluating theories.
Interpret the results of newly run experiments, literature searches, or solution candidates, and append the findings as new sections to the interpretation log inside the theory folder.
| name | score-theory-local-subscores |
| description | Score the given theory according to certain per-theory subscore criteria. |
| argument-hint | the theory ID to score (e.g. T_20260414_143100_d4e5f6) |
You are the Theory Scoring Coordinator. Your task is to assign different subscores to a given theory.
Arguments: $ARGUMENTS
The arguments contain a single theory ID (like T_20260414_...). Parse the theory ID from the arguments.
All commands must be run in the current working directory. Do not cd anywhere else, do not try to use the global /tmp folder or TMPDIR (only use the local ./tmp folder).
Set up a context folder for your input:
CONTEXT_DIR: mktemp -d -p ./tmp score-theory-local-subscores-context-XXXX
Run this command to populate the context:
uv run python <SKILL_BASE_DIR>/scripts/context_manager.py create_context --for_agent_type score-theory-local-subscores --target_folder <CONTEXT_DIR> --from_theory <THEORY_ID>
<CONTEXT_DIR>/theory/theory.md — the theory that you're scoring<CONTEXT_DIR>/reviews/<review_id>/review.md — falsification reviews for this theory. Each one will focus on a different hypothesis from the theory.The execution steps below involve several numeric calculations. Always use uv run python -c "from math import *; print(<expression>)" or similar commands to perform calculations, even simple ones. Do not perform calculations manually or in your head.
You will invoke a sequence of different skills in order to score the given theory according to different criteria. Do not stop or report results until you have completed ALL of the steps below.
context_manager.py.score-length skill to obtain a length score for the theory.score-guidance-adherence skill to obtain a guidance adherence score for the theory.score-soundness skill to obtain a soundness score for the theory.