Agent skill
review-response
Draft point-by-point responses to peer review comments. Locates supporting evidence from workspace papers and the original manuscript. Use when the user receives reviewer feedback and needs to write a rebuttal or revision response letter.
Install this agent skill to your Project
npx add-skill https://github.com/ZimoLiao/scholaraio/tree/main/.claude/skills/review-response
SKILL.md
审稿回复
逐条回复审稿人意见,从工作区文献和原稿中定位支撑证据。
前提
用户需提供:
- 审稿意见:粘贴或文件路径
- 原稿:workspace 中的论文草稿或文件路径
- workspace:关联的文献工作区(用于检索支撑证据)
- 语言:中文 / English(回复信通常与原稿语言一致)
执行逻辑
1. 解析审稿意见
将审稿意见拆分为独立的 comment,分类标注:
- MAJOR:需要实质性修改(补实验、改方法、加分析)
- MINOR:表述修改、格式调整、补充说明
- POSITIVE:正面评价(致谢即可)
- QUESTION:需要回答的问题
2. 逐条分析
对每条意见:
- 理解审稿人的核心诉求
- 在原稿中定位相关段落
- 用
scholaraio show查看论文(已有notes.md笔记会自动展示),复用已有发现 - 在工作区文献中搜索支撑证据:
bash
scholaraio ws search <name> "<审稿人关注的关键词>" scholaraio show <paper-id> --layer 3 # 读结论找证据 scholaraio show <paper-id> --layer 4 # 必要时读全文 - 从引用图谱中找额外支撑:
bash
scholaraio refs "<id>" # 相关论文的参考文献 scholaraio usearch "<补充关键词>" # 全库搜索(工作区外)
3. 撰写回复
每条回复的结构:
> **Reviewer X, Comment N:** [原文引用]
**Response:** [回复正文]
[如有修改] **Revision:** We have revised Section X.X as follows: "..." (Page X, Line X)
回复策略:
- 同意并修改:明确说明做了什么修改、在哪里
- 部分同意:承认合理之处,解释为什么不完全采纳,提供证据
- 礼貌反驳:用数据和文献支撑,语气尊重但立场坚定
- 补充实验/分析:描述新增的内容和结果
多模态辅助:
- 审稿人质疑图表时,读取论文中的原始图(
images/)重新分析 - 审稿人质疑数值时,编写 Python 代码独立复现计算,用代码输出作为回复证据
- 审稿人质疑推导时,读取论文中的公式逐步验证
4. 输出
- 保存回复信到
workspace/<name>/response-letter.md - 必须通过 CLI 将深度分析的论文关键发现写入笔记:
bash
scholaraio show "<paper-id>" --append-notes "## YYYY-MM-DD | <workspace> | review-response - 关键发现" - 如需补充引用新论文到工作区:
bash
scholaraio ws add <name> <paper-id>
写作原则
- 逐条回复,不遗漏:每条意见都必须有明确回应
- 证据优先:能用数据和文献回答的,不用空话
- 语气专业:感谢审稿人的建设性意见,即使不同意也保持尊重
- 修改可追踪:明确标注修改位置(Section、Page、Line)
- 引用核验:提交前用
/citation-check检查回复信中新增或改动过的 author-year 引用 - 不回避弱点:如果审稿人指出的确是问题,坦诚承认并说明改进措施
示例
用户说:"审稿意见回来了,帮我写 response letter" → 解析意见,分类标注,逐条在工作区中找证据,撰写回复
用户说:"Reviewer 2 说我的方法跟 Smith (2023) 没区别,怎么回" → 在工作区中找到 Smith (2023),对比方法差异,起草有理有据的反驳
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
lammps
Use when working on classical materials simulations with LAMMPS, especially interatomic-potential selection, shock or deformation setups, thermodynamic runs, and structure analysis for solids or nanomaterials.
citations
View top-cited papers ranking and refetch citation counts from APIs. Use when the user asks about highly cited papers, citation rankings, or wants to update citation data.
paper-writing
Assist with writing sections of a research paper (Introduction, Related Work, Method, Results, Discussion, Conclusion). Leverages workspace papers for citations and evidence. Use when the user wants help drafting or revising specific paper sections.
arxiv
Use when the user wants to browse arXiv preprints, search arXiv directly, fetch a PDF by arXiv ID or URL, or send a preprint straight into the ingest pipeline.
bioinformatics
Use when working on bioinformatics toolchains such as alignment, variant calling, phylogenetics, or protein-structure analysis, especially when the agent must route across BLAST, minimap2, samtools, bcftools, MAFFT, IQ-TREE, or ESMFold.
index
Rebuild FTS5 full-text search index or FAISS semantic vector index. Use when the user wants to update or rebuild search indexes after metadata changes.
Didn't find tool you were looking for?