Agent skill

Peer Review Methodology

by jaechang-hits in jaechang-hits/SciAgent-Skills

Structured peer review of manuscripts and grants. An agent skill from jaechang-hits/SciAgent-Skills.

CC-BY-4.0Auto-check passedResearch & Science

Install Peer Review Methodology

skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill peer-review-methodology -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jaechang-hits/SciAgent-Skills peer-review-methodology --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scientific-writing/peer-review-methodology .claude/skills/peer-review-methodology && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
peer-review-methodology
GitHub stars
374
Used in
1 other repo
Token cost
~2.9k tokens
SKILL.md length
1,270 words
Files
1
Skills in repo
169
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

Structured peer review of manuscripts and grants. An agent skill from jaechang-hits/SciAgent-Skills.

  • Works in 3 steps: Review Types and Expectations → Comment Severity Levels → Reporting Standards Quick Reference
  • Tasks that involve Peer review
  • SKILL.md covers Overview, Key Concepts, Decision Framework and Best Practices, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Peer Review Methodology is an agent skill from jaechang-hits/SciAgent-Skills. Structured peer review of manuscripts and grants. 7-stage evaluation: initial assessment, section review, statistical rigor, reproducibility, figure integrity, ethics, writing. Covers CONSORT/STROBE/PRISMA and report structure. For evidence quality see scientific-critical-thinking; scoring see scholar-evaluation.

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Peer review, Reproducible research and ORMs and data access. It works with Prisma. The repository describes itself as: 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon. The licence is CC-BY-4.0.

When your agent uses it

  • Tasks that involve Peer review
  • Tasks that involve Reproducible research
  • Tasks that involve ORMs and data access

Example prompts

  • “/peer-review-methodology”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Review Types and Expectations
  2. Comment Severity Levels
  3. Reporting Standards Quick Reference

What it can do on your machine

Read from SKILL.md and the folder at commit 82c862c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • publicationethics.org
    • equator-network.org
    • authorservices.wiley.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Peer Review Methodology loads about 2.9k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 1,270 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jaechang-hits/SciAgent-Skills at commit 82c862c, republished under its CC-BY-4.0 licence (© jaechang-hits). 1,270 words, ~2,907 tokens.

Download SKILL.mdSave it as .claude/skills/peer-review-methodology/SKILL.md (or your agent's skills folder).
name
peer-review-methodology
description
Structured peer review of manuscripts and grants. 7-stage evaluation: initial assessment, section review, statistical rigor, reproducibility, figure integrity, ethics, writing. Covers CONSORT/STROBE/PRISMA and report structure. For evidence quality see scientific-critical-thinking; scoring see scholar-evaluation.
license
CC-BY-4.0

Scientific Peer Review

Overview

Peer review is a systematic process for evaluating scientific manuscripts and grant proposals. This knowhow covers the complete review cycle: from initial assessment through detailed section-by-section evaluation, statistical rigor checks, reproducibility assessment, figure integrity verification, ethical considerations, and writing quality — culminating in a structured review report with actionable feedback.

Key Concepts

1. Review Types and Expectations
Review TypeScopeTypical LengthKey Focus
Original researchFull evaluation1–3 pagesRigor, novelty, reproducibility
Review/Meta-analysisCoverage and bias1–2 pagesCompleteness, search strategy, systematic approach
Methods paperValidation1–2 pagesComparison to existing methods, reproducibility
Short communicationProportional0.5–1 pageCore findings rigor despite brevity
Grant proposalFeasibility + significance1–3 pagesInnovation, approach, team, budget justification
2. Comment Severity Levels
  • Major comments: Issues that significantly impact validity, interpretability, or significance. Must be addressed for publication. Examples: fundamental design flaws, unsupported conclusions, missing controls.
  • Minor comments: Issues that improve clarity or completeness but don't affect core validity. Examples: unclear labels, missing methods details, grammatical errors.
  • Questions for authors: Requests for clarification where the reviewer cannot evaluate without additional information.
3. Reporting Standards Quick Reference
StandardApplies toKey Check
CONSORTRandomized controlled trialsFlow diagram, randomization, blinding, ITT analysis
STROBEObservational studiesStudy design, setting, participants, variables, bias
PRISMASystematic reviews / meta-analysesSearch strategy, PICO, risk of bias, forest plots
ARRIVEAnimal researchSpecies, sample size, randomization, 3Rs
MIAMEMicroarray experimentsPlatform, normalization, data deposit (GEO/ArrayExpress)
MINSEQESequencing experimentsRead counts, mapping, QC metrics, data deposit (SRA)

Decision Framework

What are you reviewing?
├── Scientific manuscript
│   ├── Original research → Full 7-stage workflow
│   ├── Review / meta-analysis → Emphasize Stage 2 (Introduction + Methods) + Stage 4
│   ├── Methods paper → Emphasize Stage 3 (rigor) + Stage 4 (reproducibility)
│   └── Short communication → Abbreviated workflow (Stages 1, 2, 3, 7)
├── Grant proposal
│   └── Focus on: significance, innovation, approach feasibility, team qualifications
└── Not a document review
    └── Use scientific-critical-thinking for evidence evaluation
Reviewer SituationFocus AreasTime Budget
First-round journal reviewAll 7 stages, full detail4–8 hours
Revision re-reviewOnly check if previous concerns addressed1–2 hours
Internal lab feedbackStages 1–3, 7 (skip ethics, reporting standards)2–4 hours
Conference abstractStage 1 only + brief methods check30 min
Grant reviewSignificance + innovation + approach + team3–6 hours

Best Practices

  1. Read the whole manuscript once before writing any comments: Resist the urge to annotate during first reading. Your initial impression informs the summary statement and helps distinguish major from minor issues.

  2. Separate description from judgment: For each concern, first state what you observed ("The authors report p=0.04 without correction for 12 comparisons"), then state why it's problematic ("This inflates the false positive rate"), then suggest a fix ("Apply Bonferroni or FDR correction and re-evaluate significance").

  3. Number every comment for easy reference: Both major and minor comments should be sequentially numbered so authors can address each one explicitly in their response letter.

  4. State your confidence level on statistical concerns: If you are uncertain about a statistical issue, say so explicitly ("I am not certain whether the normality assumption holds here — the authors should verify with a Shapiro-Wilk test or use a non-parametric alternative").

  5. Check reporting standards compliance: Before writing the review, identify which reporting standard applies (CONSORT, STROBE, PRISMA, etc.) and use its checklist to verify completeness. Missing checklist items are legitimate major comments.

  6. Acknowledge strengths explicitly: Every review should include 2–3 specific strengths. This is not politeness — it tells editors which aspects are sound and helps authors understand what NOT to change during revision.

  7. Never request experiments beyond the study's scope: A reviewer should point out limitations, not redesign the study. "This limitation should be acknowledged in the Discussion" is appropriate. "The authors should run a new cohort with 500 patients" is not.

  8. Be concrete about figure quality: Instead of "figures need improvement," say "Figure 3A: y-axis label missing units; error bars are not defined in the legend (SD vs SEM?); color coding is not colorblind-accessible."

  9. Maintain anonymity and professionalism: In single/double-blind review, avoid self-referential comments ("In our previous work..."). Never use dismissive or condescending language. Frame all criticism constructively.

  10. Match recommendation to evidence: If your comments are all minor, don't recommend rejection. If you have unresolvable major concerns about study design, don't recommend minor revision. The recommendation must be consistent with the severity of identified issues.

Show full SKILL.md (615 more words)Show less

Common Pitfalls

  1. Reviewing what the paper should be instead of what it is: Judging the paper against your preferred experimental approach rather than evaluating whether the authors' approach is valid. How to avoid: Focus on whether the methods answer the stated research question, not on whether you would have used different methods.

  2. Conflating statistical significance with scientific importance: A paper with p=0.001 can be trivial; a paper with p=0.06 can be groundbreaking. How to avoid: Evaluate effect sizes and practical significance separately from p-values. Ask "Does this matter?" not just "Is this significant?"

  3. Scope creep in revision requests: Requesting additional experiments that constitute a new study rather than validation of the current one. How to avoid: Before writing a revision request, ask "Is this necessary to support the paper's current conclusions?" If it addresses a new question, suggest it as future work instead.

  4. Overlooking positive controls: Checking for negative controls while ignoring whether the experiment demonstrates it CAN detect the claimed effect. How to avoid: For every experiment, check both "What would happen if the effect doesn't exist?" (negative control) AND "What demonstrates the assay actually works?" (positive control).

  5. Copy-paste reviewing: Using the same boilerplate concerns across different manuscripts without engaging with the specific content. How to avoid: Every comment should reference a specific section, figure, or claim in THIS manuscript. Generic advice ("improve writing quality") is unhelpful.

  6. Ignoring supplementary materials: Many critical methods details and validation data are in supplements. How to avoid: Always read supplementary materials, especially methods and figures referenced from the main text.

  7. Asymmetric skepticism: Being more critical of findings that contradict your expectations while accepting confirmatory findings uncritically. How to avoid: Apply the same methodological scrutiny to all results regardless of whether you agree with the conclusions.

Workflow

7-Stage Peer Review Process
  1. Initial assessment (read full manuscript without annotation): Identify central question, main findings, overall soundness, venue appropriateness. Write 2-3 sentence summary capturing the manuscript's essence

  2. Section-by-section review: Evaluate each section (Abstract, Introduction, Methods, Results, Discussion, References) against specific criteria:

    • Abstract: accuracy, completeness, clarity
    • Introduction: context, rationale, novelty, literature coverage
    • Methods: reproducibility, rigor, detail, statistical justification
    • Results: presentation logic, completeness, objectivity
    • Discussion: interpretation support, limitations, context, speculation
  3. Statistical and methodological rigor: Check statistical assumptions, effect sizes, multiple testing correction, sample size justification, appropriate test selection, control adequacy, randomization, blinding

  4. Reproducibility and transparency: Verify data availability (repositories, accession numbers), code availability, reporting standards compliance (CONSORT/STROBE/PRISMA/ARRIVE), protocol detail

  5. Figure and data integrity: Check resolution, labeling, error bar definitions, color accessibility, signs of image manipulation, scale bars, data type appropriateness

  6. Ethical considerations: Verify IRB/IACUC approval, informed consent, 3Rs compliance, conflicts of interest disclosure, funding disclosure, data privacy

  7. Writing quality: Assess organization, language clarity, jargon use, narrative flow, accessibility to broad audience

Review Report Structure

After completing all stages, organize feedback into:

  • Summary statement (1-2 paragraphs): Synopsis, overall recommendation, 2-3 strengths, 2-3 weaknesses
  • Major comments (numbered): Critical validity/interpretability issues with specific suggestions
  • Minor comments (numbered): Clarity/completeness improvements with locations
  • Questions for authors: Specific clarification requests
  • Recommendation: Accept / Minor revision / Major revision / Reject (consistent with comments)

Further Reading

  • COPE Ethical Guidelines for Peer Reviewers — Committee on Publication Ethics
  • EQUATOR Network — reporting guidelines for all study types
  • Stahel & Moore (2014) "Peer review for biomedical publications: we can improve the system" — BMC Medicine 12:179
  • Lovejoy et al. (2011) "An introduction to systematic reviewing" — BMJ Open
  • How to peer review — Wiley reviewer guide
  • scientific-critical-thinking — evaluating evidence quality and logical reasoning (broader than manuscript review)
  • scientific-writing — manuscript authoring; understanding the author's perspective helps write better reviews
  • literature-review — systematic evidence gathering; complements Stage 4 (reproducibility) assessment
  • scholar-evaluation — quantitative scoring frameworks for automated manuscript assessment

© jaechang-hits, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/scientific-writing/peer-review-methodology of jaechang-hits/SciAgent-Skills.

Open the folder on GitHubat commit 82c862c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in jaechang-hits/SciAgent-Skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Peer Review Methodology next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Peer Review Methodology compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Peer Review Methodology this skilljaechang-hits/SciAgent-Skills3741 repos~2.9kAutomated safety check: PassCC-BY-4.0
G2brycewang-stanford/Auto-Empirical-Research-Skills4.6k—~4.5kAutomated safety check: PassCustom licence
Method Writingaipoch/medical-research-skills1.9k—~3.4kAutomated safety check: PassMIT
Revedres Tables Figuresbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.5kAutomated safety check: PassMIT
Revedres Transparency And Reproducibilitybrycewang-stanford/Awesome-Journal-Skills1.2k—~1.3kAutomated safety check: PassMIT
Peer ReviewK-Dense-AI/claude-scientific-writer2.4k2 repos~3.1kAutomated safety check: NotesMIT

Similar skills

  • G2

    brycewang-stanford/Auto-Empirical-Research-Skills

    Publication Specialist - Writing, Review, Pre-registration & Quality Assurance Light VS applied: Avoids template-based writing + audience-specific message design Absorbed G3 (Peer Review…

    4.6k GitHub stars~4.5k tokensUpdated 5 days ago
    Writing & ContentAuto-check passed
  • Method Writing

    aipoch/medical-research-skills

    Write and revise the Methods section of research papers to ensure reproducibility; use when preparing an IMRAD manuscript or responding to journal/reporting-guideline requirements (e.g…

    1.9k GitHub stars~3.4k tokensUpdated 24 days ago
    Research & ScienceAuto-check passed
  • Revedres Tables Figures

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when designing the PRISMA flow diagram, forest/funnel plots, and coding/evidence tables for a Review of Educational Research (RER) review or meta-analysis.

    1.2k GitHub stars~1.5k tokensUpdated 14 days ago
    DatabasesAuto-check passed
  • Revedres Transparency And Reproducibility

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when settling coding reliability, open materials, PRISMA/MARS reporting, and a reproducible meta-analysis for a Review of Educational Research (RER) manuscript.

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    DatabasesAuto-check passed
  • Peer Review

    K-Dense-AI/claude-scientific-writer

    Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.

    2.4k GitHub starsUsed in 2 repos~3.1k tokens
    Research & ScienceAuto-check: notes
  • Scientific Writing

    neflibata-feng/MyArxiv-Agent

    Core skill for the deep research and writing tool. An agent skill from neflibata-feng/MyArxiv-Agent.

    126 GitHub starsUsed in 18 repos~8.4k tokens
    Research & ScienceAuto-check: notes

More from jaechang-hits/SciAgent-Skills

All 169 skills in this repo
  • Neb Irc Activation Energy

    jaechang-hits/SciAgent-Skills

    NEB-IRC activation energy pipeline for reaction barriers using GFN2-xTB and pysisyphus.

    374 GitHub stars~4k tokensUpdated 12 days ago
    Auto-check passed
  • Molecular Visualization 3dmol

    jaechang-hits/SciAgent-Skills

    3Dmol.js WebGL molecular visualization emitted as self-contained HTML.

    374 GitHub stars~3.2k tokensUpdated 12 days ago
    Auto-check passed
  • Cobrapy Metabolic Modeling

    jaechang-hits/SciAgent-Skills

    Constraint-based (COBRA) analysis of genome-scale metabolic models: FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, media optimization.

    374 GitHub starsUsed in 1 repo~4.9k tokens
    Auto-check passed
  • Rdkit Chemdraw Cdxml

    jaechang-hits/SciAgent-Skills

    Read, write, and edit ChemDraw CDX/CDXML files with RDKit's rdkit.Chem.rdChemDraw plus direct XML editing, always paired with a rendered PNG.

    374 GitHub stars~6.9k tokensUpdated 12 days ago
    Auto-check passed
  • Pubmed Database

    jaechang-hits/SciAgent-Skills

    Programmatic PubMed access via NCBI E-utilities REST API. An agent skill from jaechang-hits/SciAgent-Skills.

    374 GitHub starsUsed in 1 repo~4.4k tokens
    Auto-check passed
  • Sciagent Skill Creator

    jaechang-hits/SciAgent-Skills

    Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.

    374 GitHub stars~2.3k tokensUpdated 12 days ago
    Auto-check passed

Works with

Questions about Peer Review Methodology

What does Peer Review Methodology do?

Structured peer review of manuscripts and grants. An agent skill from jaechang-hits/SciAgent-Skills. Peer Review Methodology is an agent skill from jaechang-hits/SciAgent-Skills. Structured peer review of manuscripts and grants.

When should I use Peer Review Methodology?

Peer Review Methodology fits situations like: tasks that involve Peer review; tasks that involve Reproducible research; tasks that involve ORMs and data access.

How do I install Peer Review Methodology in Claude Code?

Run `npx skills add jaechang-hits/SciAgent-Skills --skill peer-review-methodology -a claude-code`. Or copy the skill folder (skills/scientific-writing/peer-review-methodology in jaechang-hits/SciAgent-Skills) into .claude/skills/peer-review-methodology in your project. Claude Code loads it when a task matches its description.

How do I install Peer Review Methodology in Codex?

Run `npx skills add jaechang-hits/SciAgent-Skills --skill peer-review-methodology -a codex`. Or copy the skill folder (skills/scientific-writing/peer-review-methodology in jaechang-hits/SciAgent-Skills) into .agents/skills/peer-review-methodology in your project. Codex loads it when a task matches its description.

Can I use Peer Review Methodology in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jaechang-hits/SciAgent-Skills --skill peer-review-methodology -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/peer-review-methodology, .gemini/skills/peer-review-methodology, .github/skills/peer-review-methodology and .opencode/skills/peer-review-methodology in your project.

What does Peer Review Methodology need to run?

SKILL.md names no scripts, command-line tools or credentials: Peer Review Methodology is instructions for the agent only.

Does Peer Review Methodology access the network?

SKILL.md names 3 domains. As links in the text: publicationethics.org, equator-network.org and authorservices.wiley.com. This is read from the text; nothing was executed.

Is Peer Review Methodology safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Peer Review Methodology use?

Peer Review Methodology is published under the CC-BY-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Peer Review Methodology use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Peer Review Methodology?

Skills that share tags, products or a category with Peer Review Methodology: G2 (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Method Writing (aipoch/medical-research-skills, 1.9k stars), Revedres Tables Figures (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars) and Revedres Transparency And Reproducibility (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Peer Review Methodology?

jaechang-hits (a GitHub user) maintains it in jaechang-hits/SciAgent-Skills, which has 374 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 29, 2026.

Source: jaechang-hits/SciAgent-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.