Skip to main content
ClaudeWave
Slash Command4.3k repo starsupdated 7d ago

rebuttal

This Claude Code slash command initiates a systematic workflow for writing professional rebuttals to academic peer review comments. Users provide reviewer feedback either by file path or direct input, and the tool analyzes comments, categorizes them by severity, develops response strategies, generates structured rebuttal text with evidence anchors, optimizes professional tone, and outputs formatted rebuttal documents. Use this when preparing responses to journal or conference review feedback.

Install in Claude Code
Copy
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/HEAD/commands/rebuttal.md -o ~/.claude/commands/rebuttal.md
Then start a new Claude Code session; the slash command loads automatically.

rebuttal.md

# /rebuttal - 审稿响应工作流

启动系统化的rebuttal撰写流程,从审稿意见分析到最终rebuttal文档生成。

## 用法

```bash
/rebuttal [review_file]
```

**参数**:
- `review_file` (可选): 包含审稿意见的文件路径
  - 如果不提供,将引导用户提供审稿意见

## 功能

此命令将启动完整的rebuttal撰写工作流:

1. **获取审稿意见** - 读取或接收审稿意见
2. **分析和分类** - 将意见拆成 atomic objections,并分类为Major/Minor/Typo/Misunderstanding
3. **制定策略** - 为每条意见选择响应策略
4. **撰写rebuttal** - 生成结构化的回复文档
5. **语气优化** - 确保专业、礼貌的表达
6. **生成输出** - 保存最终的rebuttal文档


## 工作流程

### 步骤 1: 获取审稿意见

如果提供了`review_file`参数:
- 读取文件内容
- 识别审稿人数量和意见结构

如果未提供文件:
- 引导用户粘贴或描述审稿意见
- 确认审稿人数量

### 步骤 2: 分析和分类

优先使用`review-response` skill;如果当前 runtime 提供 `rebuttal-writer` agent,可以用它辅助分析:
- 按审稿人分组意见
- 拆分每条 atomic objection
- 分类为Major/Minor/Typo/Misunderstanding
- 识别优先级

### 步骤 3: 制定响应策略

为每条意见选择策略:
- **Accept** - 接受并改进
- **Defend** - 礼貌辩护
- **Clarify** - 澄清误解
- **Experiment** - 补充实验


### 步骤 4: 撰写Rebuttal

生成结构化的回复:
- 为每条意见撰写Response和Changes
- 包含具体的位置引用
- 提供证据和理由
- 每条 response 必须包含 evidence anchor:paper location、result table、figure、analysis artifact、citation、Evidence Record ID、planned experiment status,或 `unresolved`

### 步骤 5: 语气优化

检查和优化语气:
- 确保每个回复以感谢开始
- 避免防御性或攻击性表达
- 保持专业和尊重

### 步骤 6: 生成输出

保存最终文档:
- `rebuttal.md` - 完整的rebuttal文档
- `review-analysis.md` - 审稿意见分析(可选)
- `experiment-plan.md` - 补充实验计划(如果需要补充实验)


## 输出文件

执行此命令后,将生成以下文件:

### rebuttal.md
完整的rebuttal文档,包含:
- 开场白(感谢审稿人)
- 逐条回复(Response + Changes)
- 主要修改总结

### review-analysis.md(可选)
审稿意见分析文档,包含:
- 意见分类统计
- 策略选择说明
- 需要补充的实验列表

### experiment-plan.md(可选)
补充实验计划文档,包含:
- 需要补充的实验列表
- 每个实验的目的和预期结果
- 实验的优先级和时间估计

## 使用示例

### 示例 1: 提供审稿意见文件

```bash
/rebuttal reviews.txt
```

将读取`reviews.txt`文件中的审稿意见,并启动rebuttal撰写流程。

### 示例 2: 交互式输入

```bash
/rebuttal
```

将引导你粘贴或描述审稿意见,然后启动rebuttal撰写流程。


## 注意事项

### 重要原则

1. **覆盖优先** - 可以使用人工阅读或脚本辅助统计 atomic objections;不要因为自然语言总结而漏掉具体意见
2. **保持专业语气** - 所有回复都要礼貌、尊重、有理有据
3. **提供具体证据** - 每个回复都要包含具体的位置引用和证据
4. **完整性检查** - 确保所有审稿意见都得到回应

### 参考资源

此命令会自动使用以下参考文档:
- `review-classification.md` - 意见分类标准
- `response-strategies.md` - 响应策略指南
- `rebuttal-templates.md` - 回复模板库
- `tone-guidelines.md` - 语气优化指南

### Agent调用

如果当前 runtime 提供 `rebuttal-writer` agent,可以调用它来执行 rebuttal 撰写任务。若 agent 不可用,直接按 `review-response` skill 和本命令流程完成,不要阻塞。

## 相关命令

- `/commit` - 提交修改后的论文
- `/code-review` - 审查代码质量

---

**提示**: 使用此命令前,建议先准备好审稿意见文件,并确保已经完成论文的必要修改。
code-reviewerSubagent

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

kaggle-minerSubagent

Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples:

literature-reviewerSubagent

Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples:

paper-minerSubagent

Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. The agent writes extracted knowledge into the active installed paper-miner writing memory for ml-paper-writing. It does not maintain project-specific writing memory.

rebuttal-writerSubagent

Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic rebuttal writing with professional tone and structured responses.

tdd-guideSubagent

Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.

analyze-resultsSlash Command

Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.

commitSlash Command

Commit changes following Conventional Commits format (local only, no push).