peer-review
Conducts structured peer review of scientific manuscripts including methodological evaluation, statistical assessment, clarity analysis, and constructive feedback generation following journal-specific guidelines; trigger when users ask for manuscript critique, reviewer reports, or feedback on research papers.
Best use case
peer-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Conducts structured peer review of scientific manuscripts including methodological evaluation, statistical assessment, clarity analysis, and constructive feedback generation following journal-specific guidelines; trigger when users ask for manuscript critique, reviewer reports, or feedback on research papers.
Teams using peer-review should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/peer-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How peer-review Compares
| Feature / Agent | peer-review | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Conducts structured peer review of scientific manuscripts including methodological evaluation, statistical assessment, clarity analysis, and constructive feedback generation following journal-specific guidelines; trigger when users ask for manuscript critique, reviewer reports, or feedback on research papers.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
## 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 raisedRelated Skills
systematic-review
Orchestrates a systematic review and meta-analysis workflow following PRISMA 2020 guidelines, from protocol development through multi-database search, screening, data extraction, and evidence synthesis. Use when conducting evidence-based reviews, meta-analyses, or scoping reviews. NOT for single-study analysis or narrative literature surveys.
review-writing
No description provided.
literature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
asreview-screening
Screen papers for systematic reviews using ASReview active learning. Use when: user has a large set of papers to screen for inclusion/exclusion, wants to prioritize relevant papers, or needs to reduce manual screening workload. NOT for: searching papers (use literature-search) or meta-analysis (use meta-analysis).
xurl
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
writing
No description provided.
world-bank-data
World Bank Open Data API for development indicators. Use when: user asks about GDP, population, poverty, health, or education statistics by country. NOT for: real-time financial data or stock prices.
wikipedia-search
Search and fetch structured content from Wikipedia using the MediaWiki API for reliable, encyclopedic information
wikidata-knowledge
Query Wikidata for structured knowledge using SPARQL and entity search. Use when: (1) finding structured facts about entities (people, places, organizations), (2) querying relationships between entities, (3) cross-referencing external identifiers (Wikipedia, VIAF, GND, ORCID), (4) building knowledge graphs from linked data. NOT for: full-text article content (use Wikipedia API), scientific literature (use semantic-scholar), geospatial data (use OpenStreetMap).
weather
Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.
wacli
Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).