peer-review
Conduct thorough academic peer reviews with structured feedback using load_pdf and arxiv_to_prompt
Best use case
peer-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Conduct thorough academic peer reviews with structured feedback using load_pdf and arxiv_to_prompt
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/prismer-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?
Conduct thorough academic peer reviews with structured feedback using load_pdf and arxiv_to_prompt
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.
SKILL.md Source
# Peer Review Skill ## Description Conduct thorough academic peer reviews with structured, constructive feedback. ## Tools Used - `load_pdf` - Load PDF papers in the workspace viewer (auto-switches to PDF reader) - `arxiv_to_prompt` - Convert arXiv papers to readable text for analysis - `update_notes` - Write review reports to the Notes editor ## Capabilities ### Paper Analysis - Extract and summarize main contributions - Identify methodology and approach - Evaluate experimental design - Assess writing quality ### Comparative Analysis - Find related prior work - Identify novelty claims - Check citation completeness - Verify originality ### Feedback Generation - Structured review reports - Specific, actionable comments - Line-by-line annotations - Summary recommendations ## Review Process ### Phase 1: Initial Read 1. Read abstract and introduction 2. Understand claimed contributions 3. Skim methodology and results 4. Form initial impression ### Phase 2: Detailed Analysis 1. Carefully read methodology 2. Evaluate experimental design 3. Check result validity 4. Assess reproducibility ### Phase 3: Comparative Check 1. Search for related work 2. Verify novelty claims 3. Check citation coverage 4. Identify missing references ### Phase 4: Report Writing 1. Summarize paper 2. List strengths 3. Detail weaknesses 4. Provide recommendations ## Feedback Templates ### Major Issue ``` [MAJOR] Section X, Page Y Issue: [Clear description] Impact: [Why this matters] Suggestion: [How to address] ``` ### Minor Issue ``` [MINOR] Section X Observation: [Description] Suggestion: [Improvement] ``` ### Question ``` [QUESTION] Section X The authors claim [X]. Could you clarify: - [Specific question] - [Related concern] ``` ## Review Report Structure ```markdown # Paper Review: [Title] ## Summary [2-3 sentence overview] ## Strengths 1. [Strength with explanation] 2. [Strength with explanation] ## Weaknesses ### Major Issues 1. [Issue with suggestion] ### Minor Issues 1. [Issue with suggestion] ## Questions for Authors 1. [Question] ## Detailed Comments [Section-by-section feedback] ## Recommendation [ ] Accept [ ] Minor Revision [ ] Major Revision [ ] Reject Confidence: [1-5] ``` ## Best Practices 1. **Be Constructive**: Focus on improvement, not criticism 2. **Be Specific**: Point to exact locations and issues 3. **Be Fair**: Acknowledge strengths before weaknesses 4. **Be Thorough**: Cover all major aspects 5. **Be Timely**: Complete reviews within deadlines
Related Skills
Review Writing — 学术综述逐节写作方法论
Use this skill when the user asks to write a literature review, review article, or 综述 based on an outline. Trigger keywords: "写综述", "write review", "综述写作", "按大纲写", "逐节写", "review section", "写第N节". This skill orchestrates the ENTIRE review writing process from outline to finished manuscript.
manuscript-review-revise
AI-powered manuscript review and revision system inspired by APRES (ICLR 2026). Evaluates scientific manuscripts using ScholarEval 8-dimension rubric plus citation-predictive heuristics, then performs targeted revisions while preserving core scientific claims. Outputs before/after comparison with improvement metrics. Use when the user says "/review", "帮我审一下", "review my manuscript", "improve this paper", "polish this draft", or provides a manuscript for quality improvement. Also triggered by "审稿", "修改论文", "润色".
Literature Search & Review
## Overview
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
Academic Writing
## Overview
scientific-visualization
## Overview
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
uniprot-database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.