score-length

星标8

分支1

更新时间2026年6月8日 18:16

Score the length of a given theory.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

imbue-ai

imbue-ai/catalyst

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Length Score Execution Steps

Determine theory lengths: Determine the length of the theory.md in number of words, excluding any conclusion sections and appendices, as well as any introductory sections (such as phenomenon descriptions, overviews and summary sections, statement/content tables, prior art comparisons, etc):

Extract the line numbers of all headings in the theory.md file (e.g. grep -n '^#' <CONTEXT_DIR>/theory/theory.md).
Determine the line range corresponding to the (typically contiguous) main body of the theory by scanning its markdown headings, ignoring any preceding introduction, summaries and overview sections, and any succeeding conclusions, appendices and/or supplementary sections.
Count the number of words in the main body line range using standard Unix tools (e.g. head -n 500 <CONTEXT_DIR>/theory/theory.md | tail -n +50 | wc -w).

Score Length: Calculate a length score for the theory using the formula Length Score = 1 / (1 + (words_in_main_body / STANDARD_LENGTH)**3), where words_in_main_body is the number of words in the main body of the theory. Round to two decimal places. Use ad-hoc Python code to perform this calculation, as described above.

同仓库更多 Skills

同仓库

propose-experiment

imbue-ai/catalyst

Design and propose the next step: either a regular data-gathering experiment, literature search, or a concrete solution candidate.

2026-07-098

execute-proposal

imbue-ai/catalyst

Determine the type of proposal given, execute/delegate accordingly, and return the appropriate resulting ID (experiment ID, literature search ID, or solution ID).

2026-07-078

score-theory-solutions

imbue-ai/catalyst

Score and rank solution candidates relative to the research goal, and update parent theory scores.

2026-06-308

integrate-interpretations

imbue-ai/catalyst

Integrate recent interpretations from the interpretation log into the associated theory.

2026-06-268

rank-experiments

imbue-ai/catalyst

Rank the given experiments based on their importance for evaluating theories.

2026-06-268

interpret-result

imbue-ai/catalyst

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.

2026-06-248

name	score-length
description	Score the length of a given theory.
argument-hint	the theory ID to score (e.g. T_20260414_143100_d4e5f6). Optionally, a STANDARD_LENGTH value.
user-invocable	false

Your task is to assess the length of a given theory based on its content.

Besides the theory to score, you may optionally be given a STANDARD_LENGTH value. The default STANDARD_LENGTH, if not specified, is 7000 words.

Length Score Execution Steps

Determine theory lengths: Determine the length of the theory.md in number of words, excluding any conclusion sections and appendices, as well as any introductory sections (such as phenomenon descriptions, overviews and summary sections, statement/content tables, prior art comparisons, etc):

Extract the line numbers of all headings in the theory.md file (e.g. grep -n '^#' <CONTEXT_DIR>/theory/theory.md).
Determine the line range corresponding to the (typically contiguous) main body of the theory by scanning its markdown headings, ignoring any preceding introduction, summaries and overview sections, and any succeeding conclusions, appendices and/or supplementary sections.
Count the number of words in the main body line range using standard Unix tools (e.g. head -n 500 <CONTEXT_DIR>/theory/theory.md | tail -n +50 | wc -w).

Score Length: Calculate a length score for the theory using the formula Length Score = 1 / (1 + (words_in_main_body / STANDARD_LENGTH)**3), where words_in_main_body is the number of words in the main body of the theory. Round to two decimal places. Use ad-hoc Python code to perform this calculation, as described above.