Firecrawl Research Papers

This automates literature reviews by having Firecrawl scrape research papers, whitepapers, and technical reports from arXiv, university sites, company blogs, and industry sources. It can pull content directly from PDFs, then synthesizes findings into a structured markdown report with themes, debates, and cited sources. The workflow spins up parallel sub-agents to research academic papers, industry reports, and technical articles simultaneously. Worth noting it distinguishes between peer-reviewed work and vendor content, and flags inaccessible PDFs. Good for when you need a sourced overview of a research area without manually tracking down and reading dozens of papers yourself.

skills.sh installs: 34.1K
GitHub stars: 221
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add firecrawl/firecrawl-workflows --skill firecrawl-research-papers --agent claude-code

Installs into .claude/skills of the current project.

Files

Firecrawl Research Papers

Use this to create a sourced literature review.

Onboarding Interview

Infer the topic, source constraints, target count, and output format from context. If the topic is clear, proceed immediately.

Ask at most 1-3 concise questions only if blocked, such as the topic, target paper count, or required venue/date/method constraints.

Firecrawl Collection Plan

Use Firecrawl Research through the CLI, MCP, or equivalent Firecrawl tool surface as the primary path for paper discovery and verification. Fall back to general Firecrawl search and scrape for whitepapers, technical reports, research blogs, leaderboards, or facts outside the paper corpus.

What the paper index holds: paper abstracts, with full text reachable per paper. Its largest share is biomedical and life-science literature — PubMed journal articles plus bioRxiv and medRxiv preprints — so clinical, drug, gene, disease, epidemiology, and public-health questions are in scope. arXiv preprints cover computer science, physics, and mathematics. Coverage outside those sources is thinner, and the web tools below are the fallback there.

Core tools:

SKILL.md on GitHub