Literature Review

Runs a systematic, multi-database literature review (PubMed, arXiv, bioRxiv, Semantic Scholar) and outputs a formatted markdown/PDF review with verified citations.

EducationIntermediate★ 33,030⑂ 3,248AI score 7/10Last updated: Aug 9, 2026

What it does

Executes the full systematic-review methodology instead of a one-off search.

Seven-phase workflow: scoping and eligibility criteria → multi-database search → title/abstract then full-text screening → data extraction and quality appraisal → thematic synthesis → citation verification → document generation
Multi-source search: parallel-cli search as the primary engine, plus PubMed, arXiv, bioRxiv, Semantic Scholar and database skills (gget, bioservices, datacommons-client); minimum three sources
Citation verification: verify_citations.py checks DOIs and formats references in APA, Nature, Vancouver, Chicago or IEEE
Professional output: fills assets/review_template.md and renders publication-grade PDFs via generate_pdf.py (pandoc/LaTeX)
Mandatory figures: requires at least 1–2 generated diagrams (PRISMA flow, search-strategy flowchart, conceptual framework) through the scientific-schematics skill

Who it's for

Graduate students and researchers writing a literature review chapter or paper section
Anyone running a meta-analysis, scoping review, or state-of-the-art survey
Teams that must log every query and search date for reproducibility
Researchers hunting for gaps to define their next project

Examples

"Systematically review GLP-1 receptor agonists and cardiovascular outcomes since 2020; output a Vancouver-style PDF with a PRISMA diagram" → search logs, screening counts, thematic synthesis and a verified bibliography
"Survey batch-correction methods for single-cell RNA-seq and highlight research gaps" → synthesis including arXiv/bioRxiv preprints plus a gap-visualisation figure
"Verify the 40 references in my draft against their DOIs and reformat them in Nature style" → flags nonexistent or mismatched citations and normalises formatting

· · · Install guide · · ·

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/literature-review folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/literature-review/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/literature-review ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal and clone the skill repository:

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git

Create the Claude Code skills folder and copy this skill:

mkdir -p ~/.claude/skills
cp -r scientific-agent-skills/skills/literature-review ~/.claude/skills/

Install and authenticate the search CLI:

curl -fsSL https://parallel.ai/install.sh | bash
parallel-cli auth

Install the Python dependency used for citation checking:
```
uv pip install requests   # or pip install requests
```

For PDF output, install pandoc and LaTeX:

brew install pandoc && brew install --cask mactex        # macOS
sudo apt-get install pandoc texlive-xetex                # Linux

(Optional) Export OPENROUTER_API_KEY if you want the LLM-assisted steps.

Check dependencies, then restart Claude Code:

python ~/.claude/skills/literature-review/scripts/generate_pdf.py --check-deps

Ask Claude something like "Run a systematic literature review on topic X" and the skill will trigger automatically.

View source on GitHub ↗License: MIT