Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
beita6969 avatar

Peer Review

  • 17 installs
  • 869 repo stars
  • Updated June 8, 2026
  • beita6969/scienceclaw

peer-review is a skill that conducts structured peer review of scientific manuscripts, generating reviewer reports with methodological, statistical, and clarity feedback.

About

This skill conducts structured peer review of scientific manuscripts, covering methodological evaluation, statistical assessment, clarity, and constructive feedback. A researcher uses it to critique a paper or draft a referee report following a summary, major concerns, minor concerns, and recommendation template. It emphasizes actionable, specific, constructive feedback over stylistic preferences.

  • Produces structured reviewer reports with major, minor, and optional concerns
  • Evaluates methodology, statistics (p-hacking, effect sizes), and clarity
  • 9-item quality checklist enforcing a constructive tone and specific references

Peer Review by the numbers

  • 17 all-time installs (skills.sh)
  • Ranked #758 of 1,354 Code Review & Quality skills by installs in the Skillselion catalog
  • Data as of Aug 2, 2026 (Skillselion catalog sync)
At a glance

peer-review capabilities & compatibility

Capabilities
manuscript review · statistical assessment · methodology critique · structured feedback
Use cases
research · documentation
From the docs

What peer-review says it does

Conducts structured peer review of scientific manuscripts including methodological evaluation, statistical assessment, clarity analysis, and constructive feedback generation
SKILL.md
Look for signs of p-hacking or selective reporting.
SKILL.md
npx skills add https://github.com/beita6969/scienceclaw --skill peer-review

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs17
repo stars869
Last updatedJune 8, 2026
Repositorybeita6969/scienceclaw

What it does

Produce a structured, constructive reviewer report critiquing a scientific manuscript's methods, statistics, and clarity.

Who is it for?

Researchers writing referee reports or self-critiquing a manuscript before submission

Skip if: Reviewing software code; this targets scientific manuscripts, not source code

When should I use this skill?

The user asks for manuscript critique, reviewer reports, or feedback on research papers

What you get

A structured reviewer report with a summary, major and minor concerns, questions, and an overall recommendation.

  • structured reviewer report
  • major concerns list
  • minor concerns list

By the numbers

  • 9-item quality checklist
  • 7-step methodology

Files

SKILL.mdMarkdownGitHub ↗

When to Trigger

Activate this skill when the user mentions:

  • Peer review, manuscript review, referee report
  • Reviewer comments, constructive criticism, revision feedback
  • Journal submission evaluation, editorial assessment
  • Methodological critique, statistical review
  • Paper strengths and weaknesses analysis
  • Response to reviewers, rebuttal letter

Step-by-Step Methodology

1. Initial assessment - Read the full manuscript. Identify the research question, study design, key findings, and claimed conclusions. Assess whether the paper is within scope for the target journal. 2. Novelty and significance evaluation - Determine the contribution relative to existing literature. Is the advance incremental or substantial? Are similar results already published? Check for proper citation of prior work. 3. Methods evaluation - Assess study design appropriateness for the research question. Check for adequate controls, sample sizes, blinding, and randomization. Verify that methods are described with sufficient detail for replication. 4. Statistical review - Verify appropriate statistical tests for data type and design. Check for multiple comparison corrections. Assess effect sizes (not just p-values). Look for signs of p-hacking or selective reporting. Verify that assumptions of statistical tests are met. 5. Results assessment - Check that results directly address the stated aims. Verify figures and tables are accurate, well-labeled, and consistent with text. Look for cherry-picking or over-interpretation of data. 6. Discussion evaluation - Assess whether conclusions are supported by the data. Check for appropriate caveats and limitations. Evaluate whether alternative interpretations are considered. 7. Generate structured review - Organize feedback into: (a) Summary of the paper, (b) Major concerns (issues that must be addressed), (c) Minor concerns (suggestions for improvement), (d) Optional comments (stylistic or presentational). Be specific, constructive, and provide actionable suggestions.

Review Structure Template

  • Summary: 3-4 sentences describing what the paper does and finds
  • Major concerns: Numbered list of significant issues affecting validity or interpretation
  • Minor concerns: Numbered list of smaller issues and suggestions
  • Questions for authors: Specific clarifications needed
  • Overall recommendation: Accept / Minor revision / Major revision / Reject (with justification)

Output Format

  • Structured reviewer report following the template above.
  • Each concern should cite specific sections, figures, or page numbers.
  • Suggestions should be actionable ("Consider adding X" rather than "This is wrong").
  • Separate methodological, statistical, and presentational issues.

Quality Checklist

  • [ ] Full manuscript read before writing review
  • [ ] Summary accurately represents the paper's claims
  • [ ] Major concerns are truly significant (not stylistic preferences)
  • [ ] Statistical methods evaluated for appropriateness
  • [ ] Constructive tone maintained throughout (critique the work, not the authors)
  • [ ] Specific references to text, figures, and tables provided
  • [ ] Alternative approaches suggested where methods are criticized
  • [ ] Conflict of interest and bias in review self-assessed
  • [ ] Recommendation consistent with the severity of concerns raised

Related skills

FAQ

What structure does the review follow?

Summary, major concerns, minor concerns, questions for authors, and an overall recommendation.

What statistical checks does it apply?

Appropriate tests for data type, multiple-comparison corrections, effect sizes, and signs of p-hacking or selective reporting.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.