Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

rebuttal-writing反驳写作

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

2,893

周安装

123

GitHub Stars

40

下载量

1,014
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:rebuttal-writing(反驳写作)
来源仓库:https://github.com/lingzhi227/agent-research-skills
仓库路径:skills/rebuttal-writing
安装命令:
npx skills add https://github.com/lingzhi227/agent-research-skills --skill rebuttal-writing
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lingzhi227/agent-research-skills --skill rebuttal-writing

简介

用于辅助文档、README 和内容稿件的整理与改写,提升可读性与结构清晰度。

  • 适合让 Agent 提炼章节、统一术语或检查链接,适用于对外文案与说明文。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装使用。
  • 使用时需保留已有事实,避免过度营销或夸大能力,尤其涉及对外内容时。
  • rebuttal-writing 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Rebuttal Writing

Generate structured, evidence-based rebuttals to peer review comments.

Input

  • $0 — Reviewer comments (text file, or pasted directly)
  • Optional: current paper draft for reference

References

  • Rebuttal prompts and format templates: ~/.claude/skills/rebuttal-writing/references/rebuttal-prompts.md

Workflow

Step 1: Parse Review Comments

For each reviewer:

  1. Extract individual concerns/questions/weaknesses
  2. Categorize each: major concern, minor concern, question, suggestion
  3. Identify the core issue behind each concern

Step 2: Generate Responses

For each concern:

  1. Acknowledge the reviewer's point
  2. Respond with evidence — cite specific sections, equations, experiments, or results from the paper
  3. Describe what was done (not what will be done) — "We have added...", "Our experiments show..."
  4. If additional experiments are needed, describe the new results concretely

Step 3: Format Rebuttal

Use the standard rebuttal format:

# Response to Reviewers

We thank all reviewers for their constructive feedback. We address each concern below.

## Reviewer #1

**Concern #1:** [extracted concern]
**Author Response:** [detailed response with evidence]

**Concern #2:** [extracted concern]
**Author Response:** [detailed response with evidence]

## Reviewer #2
...

Step 4: Summary of Changes

Add a brief summary at the top listing all major changes made to the paper:

  • New experiments added
  • Sections revised
  • Clarifications made

Rules

  • Reply with what was done, not what will be done — "We have conducted additional experiments" not "We will conduct..."
  • Be specific — Reference exact sections, table numbers, equation numbers
  • Be respectful — Thank reviewers, acknowledge valid concerns
  • Address every concern — Do not skip any reviewer point
  • Provide evidence — Every response should include concrete data, citations, or reasoning
  • Keep responses concise — Detailed enough to address the concern, but not padded
  • Highlight changes — When referring to modified text, use blue text or clearly mark revisions

Related Skills

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.87%
按下载量换算364

Claude

32.38%
按下载量换算328

Cursor

17.14%
按下载量换算174

Gemini CLI

9.46%
按下载量换算96

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills