Firecrawl Research Papers
Run a sourced literature review on a topic by finding papers, PDFs, whitepapers, and technical reports with Firecrawl and summarizing the landscape.
Overview
Firecrawl Research Papers is an agent skill most often used in Idea (also Validate, Build) that finds and synthesizes papers and PDFs into a sourced literature review via Firecrawl.
Install
npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-research-papersWhat is this skill?
- Onboarding: infer topic and constraints; ask at most 1–3 questions only if blocked
- Firecrawl search plus direct PDF scrape when URLs are available
- Target sources: arXiv, university pages, ACM/IEEE where accessible, whitepapers, research blogs
- Parallel collection plan: academic papers, industry reports, and technical tracks
- Requires FIRECRAWL_API_KEY for hosted Firecrawl requests
- At most 1–3 onboarding questions when topic is unclear
- Inputs require FIRECRAWL_API_KEY for hosted requests
Adoption & trust: 11.8k installs on skills.sh; 29 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need credible papers and reports on a topic but manual search across arXiv, PDFs, and vendor whitepapers does not scale in one agent session.
Who is it for?
Founders doing market or technical due diligence, or agents preparing evidence-backed specs and content.
Skip if: Quick factual lookups that need no PDF depth, or workflows without a Firecrawl API key and network access.
When should I use this skill?
User wants a literature review, paper summary, research landscape, or sourced synthesis from PDFs and scholarly or industry publications.
What do I get? / Deliverables
You get a structured, Firecrawl-backed collection of sources plus synthesis suitable for a literature review or scoped research memo.
- Sourced literature review or synthesis document
- Collected paper, PDF, and report references with URLs
- Optional parallel sub-researcher outputs by source type
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Most users invoke this while still exploring what to build or what the field already knows, which maps to Idea research on the journey shelf. Paper discovery and synthesis is research work—competitor and audience skills are adjacent but this skill targets academic and industry sources.
Where it fits
Map prior work on retrieval-augmented agents before committing to a niche.
Collect industry reports to decide whether your differentiation claim is already crowded.
Gather citable papers for an architecture decision record or public technical post.
Source authoritative studies for AI-search-friendly thought leadership content.
How it compares
Firecrawl-backed multi-source research workflow—not a single-site scraper skill or generic web search without PDF extraction.
Common Questions / FAQ
Who is firecrawl-research-papers for?
Solo builders and agents who need literature reviews, paper summaries, or research landscapes with traceable URLs and PDFs.
When should I use firecrawl-research-papers?
In Idea research for landscape scans; in Validate when scoping features against prior art; in Build docs when citing academic or industry sources; when the user asks for a literature review or paper summary.
Is firecrawl-research-papers safe to install?
It calls hosted Firecrawl with your API key; review the Security Audits panel on this page and treat scraped content and keys as sensitive.
SKILL.md
READMESKILL.md - Firecrawl Research Papers
# 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 Search for papers, PDFs, whitepapers, technical reports, and research blogs. Scrape PDF URLs directly when available; Firecrawl can extract PDFs. Target source types: - academic papers from arXiv, university sites, ACM/IEEE pages where accessible - industry reports and whitepapers - company research blogs - technical articles and conference summaries ## Parallel Work If appropriate, use sub-agents or equivalent parallel task runners: - Academic Papers researcher - Industry Reports researcher - Technical Articles researcher - Synthesis and citation reviewer ## Final Deliverable ```markdown # Literature Review: [Topic] ## Abstract [2-3 paragraph summary] ## Key Papers [Title, authors, source URL, key findings, methodology, relevance] ## Themes And Consensus [What sources agree on] ## Open Questions And Debates [Disagreements and unresolved questions] ## Emerging Trends [Recent developments] ## Sources [Organized by paper/report/article] ## Rerun Inputs workflow: firecrawl-research-papers topic: [topic] target_count: [number] output: [markdown/brief] ``` ## Quality Bar - Every major claim should trace to a source. - Note inaccessible or failed PDFs. - Distinguish peer-reviewed work from blogs and vendor reports.