rebuttal

Name: rebuttal
Availability: InStock
Author: Chanw-research

Atomize reviewer concerns into atomic items and map them to wiki claims.

38|3|Updated May 7, 2026

Search Tags:#peer-review #review-analysis #rebuttal #claim-mapping #wiki-integration #evidence-check #llm-stress-test

Ready to run

npx skills add https://github.com/Chanw-research/claude-code-paper-writing --skill rebuttal-chanw-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rebuttal
Source: https://github.com/Chanw-research/claude-code-paper-writing/tree/main/empirical-research-notes/empirical-wiki/.claude/skills/rebuttal
Command: npx skills add https://github.com/Chanw-research/claude-code-paper-writing --skill rebuttal-chanw-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates transforming reviewer feedback into structured rebuttals by atomizing concerns, mapping them to wiki claims, checking supporting evidence, and generating both plain-text and rich-text responses.

Core Features & Use Cases

Atomize weaknesses into atomic concerns (RvX-Cy) and map them to wiki claims
Verify that evidence supports each claim with traceable wiki experiments
Run a Review LLM stress-test to simulate reviewer questions and scoring
Produce formal (plain-text) and rich-text rebuttals
Include safety checks to prevent fabrication, overpromising, or incomplete coverage

Quick Start

Feed in the reviewer feedback and the wiki context, then run the end-to-end rebuttal workflow to generate both formal and rich-text responses.

Frequently Asked Questions about rebuttal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I structure peer-review feedback into a formal rebuttal?▼

To structure peer-review feedback into a formal rebuttal, the skill atomizes each reviewer concern into individual items, maps them to wiki claims, and generates both plain-text and rich-text responses with traceable evidence.

How does claim-mapping verify evidence for reviewer concerns?▼

Claim-mapping verifies evidence by linking each atomized reviewer concern directly to supporting wiki claims, ensuring that all rebuttals rely on traceable wiki experiments rather than unsupported assertions.

What is the best way to anticipate reviewer questions before submitting a rebuttal?▼

The best way to anticipate reviewer questions is to run a Review LLM stress-test, which simulates reviewer scoring and queries against your mapped claims to identify gaps before generating the final rebuttal.

Can I generate both plain-text and rich-text rebuttals from reviewer comments?▼

Yes, you can generate both plain-text and rich-text rebuttals from reviewer comments by feeding the review text and wiki context into the end-to-end workflow, which outputs both formats simultaneously.

What do I need to provide to automate my peer-review rebuttal workflow?▼

You need to provide the reviewer feedback text and the relevant wiki context to run the automated rebuttal workflow, as the system requires these inputs to map concerns to evidence and generate responses.

How are safety checks applied to prevent fabrication in generated rebuttals?▼

Safety checks prevent fabrication by verifying that every mapped claim has traceable supporting evidence from the wiki context, ensuring the generated rebuttals avoid over-promising or incomplete coverage of reviewer concerns.