peer-review
Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill peer-review --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill provides a framework for conducting systematic peer review, guiding evaluation of methodology, statistics, design, reproducibility, ethics, figure integrity, and reporting standards for manuscripts and grant reviews across disciplines.
How it works
It outlines a staged workflow:
- Stage 1: Initial Assessment to determine scope, novelty, and overall quality, producing a brief 2-3 sentence summary.
- Stage 2: Detailed Section-by-Section Review covering Abstract, Introduction, Methods (reproducibility, rigor, ethics, statistics, validation, and critical elements like sample sizes and randomization), Results (presentation, figures, statistics, completeness, reproducibility), Discussion (interpretation, limitations, context, future directions), and References.
- Stage 3: Methodological and Statistical Rigor with checks on statistical assumptions, effect sizes, multiple testing, confidence intervals, power analysis, and design aspects like controls and blinding.
- Stage 4: Reproducibility and Transparency focusing on data availability, code and materials, and adherence to reporting guidelines.
- Stage 5: Figure and Data Presentation assessing quality and integrity of visualizations and potential manipulations.
- Stage 6: Ethical Considerations covering human/animal subjects, research integrity, authorship, conflicts of interest, and funding disclosures.
- Stage 7: Writing Quality and Clarity evaluating structure, language, accessibility, and definition of terms.
- Structuring Peer Review Reports including Summary Statement, Major Comments, Minor Comments, Specific Line-by-Line Comments (optional), and Questions for Authors, all organized to be actionable and prioritized.
- Tone and Approach emphasizing constructive, objective, and thorough feedback with best practices.
When to use it
Use this skill when conducting formal peer reviews of scientific manuscripts and grant proposals, across disciplines, to ensure rigorous evaluation of methodology, analyses, reproducibility, and reporting standards, and to produce structured feedback.
What it can touch
The skill references guidelines for evaluating data availability, code, materials, and adherence to reporting standards, and prescribes when to comment on figures, statistics, and ethical aspects. It directs the reviewer to assess whether raw data, accession numbers, and analysis code are accessible and properly documented, and whether reporting guidelines are followed.
Caveats
The material outlines comprehensive expectations for peer review but does not guarantee publication outcomes or manuscript quality. It emphasizes avoiding overstated conclusions and ensuring feedback is actionable and aligned with disciplinary guidelines. License, tool usage, and repository-specific constraints are determined by the implementing environment.
<!-- ╔══════════════════════════════════════════════════════════════╗ ║ 本文件为开源 Skill 原始文档，收录仅供学习与研究参考 ║ ║ CoPaper.AI 收集整理 | https://copaper.ai ║ ╚══════════════════════════════════════════════════════════════╝ 来源仓库: https://github.com/K-Dense-AI/claude-scientific-writer 项目名称: claude-scientific-writer 开源协议: MIT License 收录日期: 2026-04-02 声明: 本文件版权归原作者所有。此处收录旨在为社会科学实证研究者 提供 AI Agent Skills 的集中参考。如有侵权，
What does the peer-review skill do?
Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill peer-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.