Is the Paper Red-team & Review skill free?

Yes. The skill itself is free from xf686/Meet-Reviewer-2. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Paper Red-team & Review SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Paper Red-team & Review?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Paper Red-team & Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Paper Red-team & Review

Red-team your paper before submission, or write a fair, venue-formatted review

by xf686 · xf686/Meet-Reviewer-2

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 475669b

Reviewed a planted ML abstract both with and without the skill: the bundled H1-H17 fairness firewall correctly demoted three illegitimate critiques the no-skill baseline raised ('method too simple', 'should compare to GPT-4V', 'didn't beat SOTA'), while pinning every real weakness (single-seed results, unsupported 'general and robust' claim) to its exact location. It is genuinely grounded in NeurIPS/ICLR/ACL reviewer guidelines and even ships a self-caveated ICLR-2024 weakness dataset that flags its own correlation-not-causation limits. Security scan of the full body plus three reference files was clean. One usability caveat: the SKILL.md body is written almost entirely in Chinese.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Paper Red-team & Review does

Simulates rigorous, fair academic peer review in two modes: red-team your own draft to predict reviews and get a fix list, or write a submission-ready review of someone else's paper. Triggers when a user hands over a paper (PDF, .tex, .md, arXiv link, or pasted text) and wants to predict reviews, find weaknesses, or draft a real review. Grounded in NeurIPS/ICLR/ACL reviewer guidelines with an H1-H17 illegitimate-critique firewall.

How to install Paper Red-team & Review

git clone https://github.com/xf686/Meet-Reviewer-2
mkdir -p ~/.claude/skills
cd Meet-Reviewer-2 && cp -r skills/paper-redteam ~/.claude/skills/paper-redteam

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Paper Red-team & Review

/paper-redteam Red-team your paper before submission, or write a fair, venue-formatted review

It also activates on plain-language prompts like these:

提交ICLR之前，想请你帮我把这篇论文预审一遍，预测审稿人可能会挑出哪些问题和质疑意见
我这次被分配去评审这篇论文，麻烦帮我写一份公正、有理有据、符合会议规范的正式审稿意见出来
帮我仔细找出这篇论文里审稿人真正会挑剔的薄弱环节和潜在的逻辑漏洞，麻烦讲得越具体越好

Frequently asked questions

Is the Paper Red-team & Review skill free?: Yes. The skill itself is free from xf686/Meet-Reviewer-2. SkillProof publishes the install command and an independent test verdict at no cost.
Does Paper Red-team & Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Reviewed a planted ML abstract both with and without the skill: the bundled H1-H17 fairness firewall correctly demoted three illegitimate critiques the no-skill baseline raised ('method too simple', 'should compare to GPT-4V', 'didn't beat SOTA'), while pinning every real weakness (single-seed results, unsupported 'general and robust' claim) to its exact location. It is genuinely grounded in NeurIPS/ICLR/ACL reviewer guidelines and even ships a self-caveated ICLR-2024 weakness dataset that flags its own correlation-not-causation limits. Security scan of the full body plus three reference files was clean. One usability caveat: the SKILL.md body is written almost entirely in Chinese.
What is the Paper Red-team & Review SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Paper Red-team & Review?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Paper Red-team & Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.