Peer Review

If you're writing actual peer reviews for journals or grants, this gives you a structured framework to work through manuscripts systematically. It walks you through initial assessment, section-by-section review (abstract through references), then digs into methodological rigor and statistical validity. The checklist approach helps you catch common issues like inappropriate statistical tests, missing controls, or overstated conclusions. It also covers reporting standards compliance for CONSORT, STROBE, and similar guidelines. The systematic workflow is honestly helpful for keeping reviews thorough and consistent, especially when you're reviewing outside your immediate subfield and need prompts on what to scrutinize.

skills.sh installs: 2.3K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill peer-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Peer Review

Support an accountable human reviewer with a rigorous, fair, actionable assessment. Treat every unpublished submission and review as confidential.

Mandatory safety boundary

Before reading or analyzing unpublished content:

Confirm the user is authorized by the publisher, editor, author, or other material owner.
Check the target venue’s review, confidentiality, co-review, retention, and AI/tool policies.
Record conflicts, competence limits, requested scope, and specialist-review needs.
Default to local-only processing.

If authorization is unclear, do not inspect or quote the manuscript. Clarify only the unresolved authorization; existing documented authorization need not be requested again. Until resolved, use only the intake validator or synthetic/public fixtures. Local processing of the manuscript also requires authorization.

Running a bundled CLI locally does not make the surrounding assistant session local. Treat any manuscript content read into a hosted assistant as external processing when evaluating venue policy and authorization.

Never:

SKILL.md on GitHub