Skip to main content
skill CX Codex

rebuttal-writing — Claude Code skill: point-by-point reviewer replies

Turns reviewer comments on a paper into a structured, point-by-point rebuttal backed by evidence from the manuscript.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add lingzhi227/agent-research-skills --skill rebuttal-writing -a claude-code
Open on GitHub

What rebuttal-writing does

The skill takes a file of reviewer comments and splits it into individual concerns, questions and suggestions. Each one gets a category — major concern, minor concern, question, suggestion — plus a note on the core issue behind the wording.

Then it drafts a reply for every point: acknowledge the reviewer, cite the specific sections, equations, tables or experiments that answer the concern, and phrase everything as work already done rather than work promised. Where new experiments are needed, the response describes their results concretely. The output follows a standard format with a section per reviewer and a short summary of changes at the top.

Run it once the reviews are in. Input is the comments file, and you can attach the current draft so the replies point at real sections. Response templates and the format live in ~/.claude/skills/rebuttal-writing/references/rebuttal-prompts.md.

What it helps with

  • split reviewer feedback into individual concerns
  • draft an evidence-backed reply to each concern
  • describe new experiments as already completed
  • assemble replies into one document grouped by reviewer
  • add a summary of changes at the top

Example prompts for the agent

  • parse the reviewer comments in reviews.txt and write a point-by-point response
  • draft a rebuttal to reviews.txt, citing sections and tables from the paper
  • build the reviewer response from reviews.txt with a summary of changes up front

How to install rebuttal-writing

1Skills CLI (Vercel)

npx skills add lingzhi227/agent-research-skills --skill rebuttal-writing -a claude-code

2Manually: put the files in place

~/.claude/skills/rebuttal-writing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/rebuttal-writing/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about rebuttal-writing

How do I install rebuttal-writing in Claude?

Run npx skills add lingzhi227/agent-research-skills --skill rebuttal-writing -a claude-code. The skill then sits at ~/.claude/skills/rebuttal-writing/SKILL.md.

What does rebuttal-writing do?

It breaks reviewer comments into separate concerns and writes an evidence-based reply to each, then formats everything into a structured rebuttal document grouped by reviewer.

What input does the skill need?

A file of reviewer comments, either as text or pasted in directly. You can attach the paper draft for reference so replies cite actual sections and results.

Similar skills

Everything for Science and research →

From the same set23

github-research Finds open-source repositories matching research topics, inspects their codebases, and produces an integration blueprint. Useful when tracking down implementations of algorithms. CX Codex +1 1,800installs paper-writing-section A skill that drafts or reworks a single section of an academic paper, from abstract to conclusion. Useful when the research is done but the prose is not. CX Codex +1 1,800installs novelty-assessment Runs a research idea through literature search and returns a verdict: novel or not. Useful before you commit to a direction. CX Codex +1 1,800installs idea-generation A skill that generates research ideas, refines them over several rounds and checks novelty against the literature. Useful before you commit to a paper topic. CX Codex +1 1,800installs code-debugging Structured error analysis for ML experiments and research code. It categorizes tracebacks, limits retry cycles, and explains fixes line by line. CX Codex +1 1,700installs symbolic-equation Discovers scientific equations from numerical datasets using LLM-guided evolutionary search. Useful for symbolic regression and extracting interpretable physical laws. CX Codex +1 1,600installs experiment-code Writes and iterates on ML experiment code for a research paper: training, evaluation, debugging, plots. Useful when you need a batch of runs and a comparison. CX Codex +1 1,600installs paper-to-code Turns an ML research paper into a runnable code repository. Useful when reproducing published experiments and models without manual scaffolding. CX Codex +1 1,600installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor