跳到正文
cccskills
免费在 GitHub 公开

document-memory-summarize

Summarize extracted paper text into concise Markdown memory for later Stage 2 and Stage 4 background use, with fixed section headings and no fabricated claims.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md1.1 KB
  • scripts/extract_pdf_text.py1.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Document Memory Summarize

Goal

Convert extracted document text into a concise Markdown memory file that is easy to edit and reuse in later rebuttal stages.

Input

  • document_text: plain text extracted from .txt, .md, .tex, or .pdf.

Output

Return strict JSON:

{ "markdown": "..." }

Required Markdown headings

  • ## Contribution Overview
  • ## Introduction
  • ## Methods
  • ## Logic Chain
  • ## Experiments
  • ## Key Conclusions

Rules

  1. Keep the Markdown concise and scannable.
  2. Preserve the main theoretical ideas, methods, experiments, and conclusions.
  3. Ignore references, appendices, and supplementary material unless the main text clearly depends on them.
  4. Do not invent numbers, citations, experiments, or claims.
  5. If a section is weak or missing in the source, keep the heading and add a short grounded note instead of guessing.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Verification guide for citations added during rebuttal writing. Use when Stage 2 responses introduce new references, when the Area Chair asks about a cited paper, or when any citation in the rebuttal might have been AI-generated. Prevents the serious credibility damage of fabricated references in reviewer-facing documents.

中文简介正在准备中。当前显示原文说明。

runtsang/RebuttalStudio2192026年4月4日 更新

Systematic quality check for a completed rebuttal document before submission. Use after Stage 3 document compilation or after Stage 5 final remarks writing to verify completeness, tone, factual accuracy, and structural integrity. Catches common rebuttal errors before they reach reviewers.

中文简介正在准备中。当前显示原文说明。

runtsang/RebuttalStudio2192026年4月4日 更新

Systematic review response strategy guide for RebuttalStudio. Use when developing response strategies for reviewer comments, deciding how to classify concerns, or choosing between Accept/Defend/Clarify/Experiment approaches at any stage of the rebuttal pipeline.

中文简介正在准备中。当前显示原文说明。

runtsang/RebuttalStudio2192026年4月4日 更新

skills

免费

Multi-stage rebuttal analysis skill for RebuttalStudio. Use when organizing reviewer comments into stage-specific conference workflows, including stage1 breakdown, stage2 refinement, stage4 multi-round follow-up, and stage5 final remarks generation.

中文简介正在准备中。当前显示原文说明。

runtsang/RebuttalStudio2192026年4月4日 更新

Break down full ARR (ACL Rolling Review) reviewer responses into structured rebuttal units. Use when input contains ARR reviewer fields (Paper Summary, Strengths, Weaknesses, Comments/Suggestions) and numeric scores (Confidence, Soundness, Excitement, Overall Assessment, Reproducibility). Splits weaknesses and comments/suggestions into granular response items while preserving original wording for quoted issues.

中文简介正在准备中。当前显示原文说明。

runtsang/RebuttalStudio2192026年4月4日 更新

Base template for Stage1 reviewer-comment breakdown. Use when creating or extending conference-specific Stage1 skills (for example ICLR, ICML, NeurIPS, ACL) so shared extraction, splitting, and response-mapping logic stays consistent.

中文简介正在准备中。当前显示原文说明。

runtsang/RebuttalStudio2192026年4月4日 更新

查看 runtsang 的全部技能

报告此技能的问题