Verified:GitHub

peer-review

Evaluate CS paper submissions for novelty, correctness, and reproducibility.

3|Updated Mar 11, 2026

Search Tags:#reproducibility #peer-review #academic-writing #evidence-quality #cs-research #paper-evaluation #review-structure

Ready to run

npx skills add https://github.com/JunMA98/Computer-science-claude-skills --skill peer-review-junma98

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: peer-review
Source: https://github.com/JunMA98/Computer-science-claude-skills/tree/main/skills/peer-review
Command: npx skills add https://github.com/JunMA98/Computer-science-claude-skills --skill peer-review-junma98

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill streamlines the CS peer-review process by providing a structured framework to evaluate submissions for novelty, correctness, reproducibility, and clarity, reducing time spent on editorial considerations and ensuring evidence-based feedback.

Core Features & Use Cases

Structured evaluation across dimensions such as novelty, technical soundness, empirical rigor, reproducibility, and clarity.
Drafting support for reviewer reports, meta-reviews, and author-facing questions.
Use Case: A conference program committee uses this skill to generate a consistent, evidence-backed review draft and a list of targeted questions for authors.

Quick Start

Draft a structured review outline for the target CS paper, highlighting strengths, weaknesses, and questions for authors.

Frequently Asked Questions about peer-review

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

FAQPage Schema

How do I write a structured peer review for a computer science paper?▼

To write a structured peer review for a CS paper, evaluate the submission across novelty, technical soundness, empirical rigor, and reproducibility. This process generates an evidence-backed review draft highlighting strengths, weaknesses, and targeted questions for the authors.

How do I evaluate reproducibility and methodological soundness in ML submissions?▼

You evaluate reproducibility and methodological soundness in ML submissions by applying an evidence-driven review framework. This approach assesses empirical rigor, clarity, and technical correctness to generate targeted questions and scoring across standard review dimensions.

Can I use an automated review framework for workshop and journal rebuttals?▼

Yes, you can use an automated review framework for workshop and journal rebuttals. The framework supports drafting structured reviewer reports and author-facing questions across various CS domains, including empirical ML, systems, theory, and tooling papers.

What is the best way to generate evidence-based scores for academic paper evaluation?▼

The best way to generate evidence-based scores for academic paper evaluation is applying a structured review framework that systematically assesses novelty, correctness, and clarity. This yields consistent, evidence-driven scoring across dimensions for conference and journal submissions.

Does this peer-review process work for artifact evaluations and meta-reviews?▼

Yes, this peer-review process works for artifact evaluations and meta-reviews. It provides structured drafting support tailored for these evaluation types, ensuring methodological soundness and evidence-based feedback across empirical ML and systems papers.

What should I include in a reviewer report for a CS systems paper?▼

A reviewer report for a CS systems paper should include structured evaluations of technical soundness, reproducibility, and clarity. The review framework helps draft evidence-backed outlines highlighting specific strengths, weaknesses, and targeted author-facing questions.