literature-review
使用多个学术数据库（如 PubMed、arXiv、bioRxiv、Semantic Scholar 等）开展全面、系统化的文献综述。适用于系统综述、Meta 分析、研究综合，或跨生物医学、科学和技术领域的全面文献检索。可生成包含已验证引用的专业格式 Markdown 文档和 PDF，支持多种引用格式（如 APA、Nature、Vancouver 等）。
npx skills add majiayu000/claude-skill-registry --skill literature-review-victory-hugo-s2-agent-skill --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
Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats.
How it works
The skill integrates with database-access tools (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and document generation. It instructs users to perform planning, multi-database searches, deduplication, screening (title, abstract, full-text), and PRISMA-style reporting. It includes steps to export results, aggregate into a single file, run post-processing scripts (e.g., python search_databases.py combined_results.json --deduplicate --format markdown --output aggregated_results.md), and generate outputs via scripts (e.g., python scripts/generate_pdf.py my_literature_review.md --output my_review.pdf). It mandates creating PRISMA flow diagrams and organizing results by themes. It also prescribes citation verification (python scripts/verify_citations.py my_literature_review.md) and final formatting using a chosen citation style.
When to use it
Use this skill when conducting a systematic literature review for research or publication, synthesizing current knowledge across multiple sources, performing meta-analysis or scoping reviews, or preparing the literature review section of a paper or thesis. It is intended for identifying research gaps and ensuring verified citations with professional formatting.
What it can touch
The workflow references and utilizes tools and scripts such as:
ggetfor PubMed and bioRxiv searchesbioservicesfor ChEMBL, KEGG, UniProt, COSMIC, AlphaFold, PDB datadatacommons-clientfor demographic/statistical datapython scripts/generate_pdf.pyto produce PDFspython scripts/verify_citations.pyto verify DOIsscripts/search_databases.pyfor post-processingcp assets/review_template.mdto create the initial documentpython search_databases.pyfor aggregation and deduplicationpython scripts/generate_pdf.pywith--citation-styleoptions (apa, nature, chicago, vancouver, ieee) The skill also envisions usingscematic-style figures via thescientific-schematicsworkflow, described in text.
Caveats
The text specifies mandatory inclusion of AI-generated schematics and uses external tools to generate figures. It requires explicit steps for planning, searching across multiple databases, deduplication, screening, PRISMA diagram creation, data extraction, quality assessment using standard tools, thematic synthesis, and citation verification. It emphasizes verifying DOIs and consistency of citations before finalizing, and generating outputs in Markdown and PDF formats with specified citation styles. License stated as MIT.
# Literature Review ## Overview Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats. This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and document generation. ## When to Use This Skill Use this skill when: - Conducting a systematic literature review for research or publication - Synthesizing current knowledge on a specific topic across multiple sources - Performing meta-analysis or scoping reviews - Writing the literature review section of a research paper or thesis - Investigating the state of the art in a research domain - Identifying research gaps and future directions - Requiring verified citations and professional formatting ## Visual Enhancement with Scientific Schematics **⚠️ MANDATORY: Every literature review MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.** This is not optional.
- Overview
- When to Use This Skill
- Visual Enhancement with Scientific Schematics
- Core Workflow
- Phase 1: Planning and Scoping
- Phase 2: Systematic Literature Search
- Phase 3: Screening and Selection
- Phase 4: Data Extraction and Quality Assessment
- Phase 5: Synthesis and Analysis
- Phase 6: Citation Verification
- Phase 7: Document Generation
- Database-Specific Search Guidance
- PubMed / PubMed Central
- bioRxiv / medRxiv
python scripts/generate_schematic.py "your diagram description" -o figures/output.png python search_databases.py combined_results.json \ python search_databases.py results.json --deduplicate --output unique_results.json cp assets/review_template.md my_literature_review.md python scripts/verify_citations.py my_literature_review.md python scripts/generate_pdf.py my_literature_review.md \ Search PubMed gget search pubmed "CRISPR gene editing" -l 100 Search with filters Use PubMed Advanced Search Builder to construct complex queries
What does the literature-review skill do?
使用多个学术数据库（如 PubMed、arXiv、bioRxiv、Semantic Scholar 等）开展全面、系统化的文献综述。适用于系统综述、Meta 分析、研究综合，或跨生物医学、科学和技术领域的全面文献检索。可生成包含已验证引用的专业格式 Markdown 文档和 PDF，支持多种引用格式（如 APA、Nature、Vancouver 等）。
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill literature-review-victory-hugo-s2-agent-skill --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 majiayu000/claude-skill-registry, a repository with 534 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.