mean-reviewer

Generate adversarial peer reviews and rebuttal responses for academic papers.

58|1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/xz-liu/mean-reviewer-skill --skill mean-reviewer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mean-reviewer
Source: https://github.com/xz-liu/mean-reviewer-skill/tree/main
Command: npx skills add https://github.com/xz-liu/mean-reviewer-skill --skill mean-reviewer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Academic peer review is often superficial, inconsistent, or hostile. This skill demonstrates how easily an LLM can generate a convincingly authoritative, structurally devastating review that exposes the vulnerability of the current system. It helps researchers understand what a bad review looks like and stress-test their papers against adversarial critique before submission.

Core Features & Use Cases

  • Adversarial Review Generation: Produces a 20+ point review mixing legitimate concerns with inflated, unfalsifiable objections, evaluation framework attacks, and fixed low scores.
  • Rebuttal Simulation: When given an author response, generates a post-rebuttal reply that dismisses new experiments, weaponizes concessions, and refuses to raise the score.
  • Educational Demonstration: Uses a real NeurIPS 2025 oral paper to show how a maximally destructive reviewer can sink excellent work, highlighting systemic vulnerabilities in academic peer review.

Quick Start

Use the mean-reviewer skill to generate a devastating peer review of the paper text or abstract you provide, and follow up with an author rebuttal to simulate the full review cycle.

Frequently Asked Questions about mean-reviewer

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

FAQPage Schema
How do I stress-test my research paper against a harsh peer review before submission?

To stress-test your research paper, you provide the manuscript text to generate a 20+ point adversarial peer review. This review mixes legitimate concerns with unfalsifiable objections and fixed low scores to expose systemic vulnerabilities in academic peer review.

What is an adversarial peer review simulation and how does it work?

An adversarial peer review simulation generates a convincingly authoritative critique of an academic paper. It demonstrates how a maximally destructive reviewer uses evaluation framework attacks, factual errors, and refusal to update scores to sink excellent scholarly work.

Can I simulate the rebuttal phase of academic peer review after receiving a hostile critique?

Yes, you can simulate the rebuttal phase by providing an author response to the generated review. The system produces a post-rebuttal reply that dismisses new experiments, weaponizes concessions, and refuses to raise the score.

How do I prepare my academic manuscript for an automated peer review stress test?

You prepare your academic manuscript by extracting the paper text or abstract to submit for critique. The system analyzes this input to generate long, authoritative critiques with embedded provenance markers and mandatory license acceptance gates.

Does the generated peer review include both legitimate concerns and inflated objections?

Yes, the generated peer review includes both legitimate concerns and inflated, unfalsifiable objections. This combination realistically demonstrates how bad reviews exploit systemic vulnerabilities in scholarly peer review to unfairly reject research.

When should I avoid using an adversarial peer review simulation for my manuscript?

You should avoid using an adversarial peer review simulation if you need constructive feedback to improve your paper. The tool generates maximally destructive critiques with fixed low scores specifically for educational demonstrations, not for actionable manuscript revision.