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.).
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill literature-review --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides the agent to conduct systematic, comprehensive literature reviews across biomedical, scientific, and technical domains. It coordinates database access (e.g., PubMed, arXiv, bioRxiv, Semantic Scholar) and specialized tools for citation verification, result aggregation, and document generation in markdown and PDF formats, including professionally formatted citations in multiple styles.
How it works
The skill instructs the agent to:
- Plan the review via defined research questions, scope, and search strategy, including selecting 2-4 main concepts and forming a multi-database search plan with Boolean operators.
- Execute multi-database searches using appropriate tools (e.g., gget for PubMed/bioRxiv, bioservices for ChEMBL/KEGG, direct API access for arXiv/Semantic Scholar).
- Document search parameters for each database, including date ranges, search strings, and results counts.
- Export and aggregate results into a single file (e.g., JSON) and post-process with scripts like
python search_databases.pyto deduplicate and format outputs (e.g.,aggregated_results.md). - Perform deduplication, title/abstract/full-text screening against inclusion/exclusion criteria, and record reasons for exclusion.
- Create PRISMA-style flow diagrams and organize data by themes.
- Extract data, assess study quality with domain-appropriate tools, and synthesize findings thematically rather than study-by-study.
- Verify all DOIs with
python scripts/verify_citations.pyand format citations in a chosen style (APA, Nature, Vancouver, etc.). - Generate outputs with
python scripts/generate_pdf.py(or equivalent) and review for formatting, figure placement, and citations. - Include at least 1-2 AI-generated figures using the
scientific-schematicsskill before finalization, generated viapython scripts/generate_schematic.pyor similar described workflow.
When to use it
Use this skill when conducting systematic literature reviews, meta-analyses, research syntheses, or comprehensive literature searches that require verified citations and professional formatting across biomedical, scientific, and technical domains.
What it can touch
- Databases and tools: PubMed, bioRxiv, arXiv, Semantic Scholar, Google Scholar, gget, bioservices, datacommons-client.
- Scripting and outputs:
scripts/search_databases.py,scripts/verify_citations.py,scripts/generate_pdf.py. - Output formats: Markdown documents and PDFs; figures generated via
scientific-schematicsworkflow.
Caveats
- The skill requires access to external databases and assumes availability of the referenced scripts and tools. Specific licenses and dependencies are handled by the underlying projects; ensure compliance with each data source’s terms. Citations must be verified with
verify_citations.pybefore finalizing. - The workflow mandates creation of AI-generated schematics; outputs must include 1-2 figures created via the
scientific-schematicsprocess.
<!-- ╔══════════════════════════════════════════════════════════════╗ ║ 本文件为开源 Skill 原始文档，收录仅供学习与研究参考 ║ ║ CoPaper.AI 收集整理 | https://copaper.ai ║ ╚══════════════════════════════════════════════════════════════╝ 来源仓库: https://github.com/K-Dense-AI/claude-scientific-skills 项目名称: claude-scientific-skills 开源协议: MIT License 收录日期: 2026-04-02 声明: 本文件版权归原作者所有。此处收录旨在为社会科学实证研究者 提供 AI Agent Skills 的集中参考。如有侵权，
What does the literature-review skill do?
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.).
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill literature-review --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.