literature-review

Conduct systematic literature reviews across academic databases with verified citations and PDF output.

Updated Aug 12, 2026
One-click install
npx skills add https://github.com/Mzane0803/latent-minds-skills-marketplace --skill literature-review-mzane0803
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: literature-review
Source: https://github.com/Mzane0803/latent-minds-skills-marketplace/tree/main/plugins/research-writing/skills/literature-review
Command: npx skills add https://github.com/Mzane0803/latent-minds-skills-marketplace --skill literature-review-mzane0803

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pandoc, parallel-cli, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Conducting a rigorous literature review requires searching multiple academic databases, deduplicating results, screening papers, verifying every citation, and formatting the output to academic standards — a slow, error-prone manual process. ## Core Features & Use Cases - Multi-Database Search: Search PubMed, arXiv, bioRxiv, Semantic Scholar, and web sources via parallel-cli, then aggregate and deduplicate results with search_databases.py. - Citation Verification & Formatting: Verify every DOI against CrossRef and generate formatted references in APA, Nature, Vancouver, Chicago, or IEEE styles. - Professional Document Generation: Convert the finished markdown review into a styled PDF with pandoc, plus AI-generated figures such as PRISMA flow diagrams. - Use Case: A researcher writing a systematic review on CRISPR therapies for sickle cell disease can search multiple databases, screen results following PRISMA, verify all citations, and produce a publication-ready PDF in one workflow. ## Quick Start Use the literature-review skill to conduct a systematic review of CRISPR gene therapy for sickle cell disease, searching PubMed and bioRxiv, verifying all citations, and generating a PDF in Nature citation style.

Frequently Asked Questions about literature-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I conduct a systematic literature review with Claude?▼

Follow the seven-phase workflow: plan with PICO criteria, search at least three databases, screen titles through full texts, extract data, synthesize thematically, verify citations with verify_citations.py, and generate the PDF with generate_pdf.py.

How to verify DOIs and citations in a research paper?▼

Run scripts/verify_citations.py on your markdown document. It extracts all DOIs, checks each one resolves correctly, retrieves metadata from CrossRef, and outputs a verification report plus properly formatted citations.

Which databases does this literature review workflow search?▼

It uses parallel-cli search for broad academic coverage, gget for PubMed and bioRxiv, bioservices for ChEMBL, KEGG, and UniProt, plus direct APIs for arXiv and Semantic Scholar. A minimum of three databases is recommended.

What citation styles are supported for PDF generation?▼

The generate_pdf.py script supports APA, Nature, Chicago, Vancouver, and IEEE styles via the --citation-style flag. It requires pandoc and xelatex installed on the system to render the final PDF.

Why does PDF generation fail for my literature review?▼

PDF generation fails when pandoc or xelatex is missing. Run python scripts/generate_pdf.py --check-deps to diagnose, then install pandoc and a LaTeX distribution such as MacTeX or texlive-xetex.

Do I need an API key to generate review figures?▼

AI-generated schematics via generate_schematic.py require an OPENROUTER_API_KEY, set as an environment variable or in a .env file. The core search, citation verification, and PDF generation steps work without it.