AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Literature Review

Runs a systematic literature review across PubMed, arXiv, bioRxiv and Semantic Scholar, then verifies every citation and exports a publication-ready markdown/PDF.

EducationIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Walks through a seven-phase review process: scoping the question → multi-database searching → title/abstract and full-text screening → data extraction and quality appraisal → thematic synthesis → citation verification → document generation.
  • Enforces reproducibility: search strings, dates and result counts are logged, with a minimum of three databases plus preprint servers.
  • Verifies DOIs and reformats references via verify_citations.py in APA, Nature, Vancouver, Chicago or IEEE style.
  • Exports the finished review to a professional PDF with generate_pdf.py (pandoc + LaTeX) and requires at least one figure such as a PRISMA flow diagram.

Who it's for

  • Graduate students and researchers drafting the literature review chapter of a thesis or paper.
  • Teams running meta-analyses, scoping reviews or state-of-the-art surveys.
  • Biomedical, scientific and technical writers who need citation accuracy and audit trails.

Example uses

  1. "Do a PRISMA-compliant systematic review of GLP-1 agonists and cardiovascular outcomes from the last five years" → search strategy, screening counts, thematic synthesis and a PRISMA diagram.
  2. Audit 60 references in an existing draft with verify_citations.py to catch bad DOIs or author names, then reformat to Nature style.
  3. Convert the finished markdown review into a submission-ready PDF with python scripts/generate_pdf.py, pairing it with the venue-templates skill for journal-specific tone.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/literature-review/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. 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 AI 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.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/literature-review ~/.claude/skills/
  4. Install the search CLI: curl -fsSL https://parallel.ai/install.sh | bash, then authenticate with parallel-cli auth.
  5. Install the Python dependency: uv pip install requests (or pip install requests).
  6. For PDF output install pandoc and LaTeX — macOS: brew install pandoc && brew install --cask mactex; Linux: sudo apt-get install pandoc texlive-xetex.
  7. Check everything is ready: python ~/.claude/skills/literature-review/scripts/generate_pdf.py --check-deps
  8. Restart Claude Code and ask something like "run a systematic literature review on topic X". Also install the scientific-schematics skill if you want the PRISMA figures it expects.
View source on GitHub ↗License: MIT