Skills Plugins MCP Prompt Model 博客 我的中心

review-response

Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=galaxy-dawn-claude-scholar-skills-review-response-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name review-response description Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates. tags ["Research","Academic","Rebuttal","Paper Writing"] version 0.1.0 Review Response A systematic review response workflow that helps researchers efficiently and professionally reply to reviewer comments. Core Features Review Analysis - Parse and classify reviewer comments (Major/Minor/Typo/Misunderstanding) Response Strategy - Develop response strategies for different comment types (Accept/Defend/Clarify/Experiment) Rebuttal Writing - Write structured, professional rebuttal documents Tone Management - Optimize tone to maintain professionalism, respect, and evidence-based arguments Workflow Receive reviewer comments -> Parse and classify -> Develop strategy -> Write responses -> Tone check -> Final rebuttal When to Use Use this skill when you need to: "Help me write a rebuttal" "How to respond to reviewer comments" "Analyze these review comments" "Develop a review response strategy" Usage Steps Provide reviewer comments - Share the reviewer comments text or file with Claude Analysis and classification - Claude automatically parses and classifies the comments Strategy recommendations - Receive response strategy suggestions for each comment Write rebuttal - Generate a structured rebuttal document based on the strategy Optimize tone - Review and optimize the professionalism and politeness of responses Core Principles Professionalism - Maintain an academically professional tone and expression Respectfulness - Respect the reviewers' opinions and time Evidence-based - Support every response with sufficient reasoning and evidence Completeness - Ensure all reviewer comments receive a response Success Factors (Based on ICLR Spotlight Paper Analysis) Key lessons extracted from successful rebuttal cases: 1. Acknowledge Strengths, Respond Positively to Criticism Reviewers will first acknowledge the paper's strengths (novelty, impact, practical applicability) Even spotlight papers receive constructive criticism Strategy : Thank reviewers for acknowledged strengths first, then address criticism specifically 2. Provide Clarity and Intuitive Understanding Even high-quality papers may have clarity issues Need to provide intuition and detailed explanations for readers with different backgrounds Strategy : Expand key sections, move technical details to appendix, add step-by-step walkthroughs 3. Thorough Justification of Experimental Setup Need to justify experimental setup choices Consider and discuss alternative metrics Provide comprehensive experiments to support claims Strategy : Add ablation studies, explain why specific experimental setups were chosen 4. Emphasis on Ethical Considerations For research involving privacy, security, and other sensitive topics, ethical considerations are crucial Reviewers pay special attention to ethical implications Strategy : Proactively discuss ethical considerations, even if reviewers don't explicitly request it 5. Highlight Practical Application Value Reviewers value practical applicability and scalability of methods "Easily applicable" and "scalable" are important strengths Strategy : Emphasize practical benefits and scalability in the rebuttal Integration with active installed writing memory When the rebuttal task involves: tone calibration, rebuttal phrasing, clarification language, structuring multi-point responses, or learning from strong prior paper/review writing, read the active installed writing memory before drafting: ~/.claude/skills/ml-paper-writing/references/knowledge/paper-miner-writing-memory.md on Claude Code installs the equivalent installed skill-home path on Codex/OpenCode branches otherwise skip this optional memory and continue with the local review-response references Default read order for rebuttal work reviewer comments and paper context optional paper-miner-writing-memory.md if available references/response-strategies.md references/rebuttal-templates.md references/tone-guidelines.md Read narrowly: start with How this helps our writing , then inspect Reusable phrasing , then inspect Venue-specific signals if the rebuttal is venue-sensitive, use Writing patterns mined only when the response needs stronger rhetorical structure. Do not quote the memory mechanically. Use it to improve structure, clarity, restraint, and professionalism. Evidence anchor rule Every response row must include one of: paper location, result table / figure / analysis artifact, citation / Evidence Record ID, planned experiment with status, unresolved if no evidence exists yet. Do not claim "we added experiments" or "the results show" without naming the artifact. If an objection has multiple atomic points, split it and cover each point separately. Reference Documents For detailed guides, refer to: references/review-classification.md - Review comment classification criteria references/response-strategies.md - Response strategy library references/rebuttal-templates.md - Rebuttal templates and examples references/tone-guidelines.md - Tone and expression guidelines Related Tools Agent : rebuttal-writer - Dedicated agent for rebuttal writing and optimization Command : /rebuttal <review_file> - Quick-start the rebuttal workflow
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。