Literature Review

This is a serious academic research tool that automates systematic literature reviews across PubMed, arXiv, bioRxiv, and Semantic Scholar. It enforces a structured workflow from PICO question formulation through search strategy documentation to citation-verified PDF output. The standout requirement is mandatory AI-generated figures using the scientific-schematics skill, which means every review gets PRISMA flowcharts or thematic diagrams automatically. It leans heavily on the parallel-web skill for initial broad searches before hitting specialized databases. Built for researchers who need publication-ready lit reviews with proper methodology, not quick summaries. The output follows academic standards with multiple citation styles and full provenance tracking of search parameters.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 9
skills.sh installs: 2.5K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill literature-review --agent claude-code

Installs into .claude/skills of the current project.

Files

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.

Use discipline-appropriate bibliographic databases for the reproducible search, with parallel-web (parallel-cli search) for scoping and supplementary discovery. Ranked web results and extracted excerpts cannot establish exhaustive coverage or substitute for full-text assessment. Bundled scripts process normalized records, check DOI registration, and render documents; they do not run a complete systematic review automatically.