Systematic Literature Review

Searches arXiv for papers on your topic, extracts structured metadata (research questions, methods, findings, limitations) from each one in parallel using subagents, then synthesizes themes across the full set into a proper report with consistent citations in APA, IEEE, or BibTeX. Handles 20-50 papers at a time. The workflow is explicit about query construction (use 2-3 core keywords, not full topic descriptions) and always sorts by relevance instead of date to avoid off-topic results. If you have one paper to review deeply, route to academic-paper-review instead. This is for breadth-first synthesis when you need to map out what the literature says about transformers, diffusion models, or whatever research area you're trying to get your head around.

skills.sh installs: 2.5K
GitHub stars: 85.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add bytedance/deer-flow --skill systematic-literature-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Systematic Literature Review Skill

Overview

This skill produces a structured systematic literature review (SLR) across multiple academic papers on a research topic. Given a topic query, it searches arXiv, extracts structured metadata (research question, methodology, key findings, limitations) from each paper in parallel, synthesizes themes across the full set, and emits a final report with consistent citations.

Distinct from academic-paper-review: that skill does deep peer review of a single paper. This skill does breadth-first synthesis across many papers. If the user hands you one paper URL and asks "review this paper", route to academic-paper-review instead.