literature-review

This skill facilitates rigorous, systematic literature reviews for researchers, scientists, and students requiring high-quality academic synthesis. By automating the search across major databases including PubMed, arXiv, bioRxiv, and Semantic Scholar, it enables the rapid discovery and ingestion of scholarly material. The skill is designed to support various review types, including scoping reviews, meta-analyses, and comprehensive state-of-the-art investigations, ensuring that findings are synthesized thematically and presented with professional formatting.

• Multi-database integration using parallel-web (parallel-cli search), gget, and bioservices to aggregate cross-disciplinary research.

• Automated citation verification and formatting support for major academic styles including APA, Nature, and Vancouver.

• Mandatory scientific visualization requirement, utilizing the scientific-schematics skill to generate publication-quality figures, PRISMA flow diagrams, and conceptual framework illustrations.

• Structured workflow management based on PICO frameworks, guiding the user from initial research scoping to final document generation in Markdown or PDF.

• Advanced filtering capabilities for study design, publication dates, and source types to ensure high-quality evidence selection.

• Utilize the parallel-web skill as the primary entry point for broad scoping before narrowing down to specialized databases.

• The skill mandates the inclusion of at least one AI-generated scientific schematic to ensure clarity and professional-grade visual documentation.

• Users should define clear inclusion and exclusion criteria at the start to ensure the reproducibility of the literature review process.

• Ensure all retrieved content from web-based searches is verified against the targeted academic databases for accuracy and peer-review status.

• The generated outputs are designed for direct use in research papers, theses, and grant applications, requiring minimal manual adjustment for publication.