firecrawl-research-papers Skill for Claude: What It Does and How to Install It

Makes your agent run a sourced literature review over Firecrawl's paper index: PubMed, bioRxiv, medRxiv and arXiv.

Installs: 33.9K; on skills.sh
Stars: 214; on GitHub
Updated: Nov 2026; last repo commit

This skill makes your agent search for papers instead of web pages. It starts with a semantic search over paper abstracts, then expands from strong papers to similar, citing and cited work, and checks specific claims inside a paper before keeping it.

It triggers when you ask for a literature review, survey of studies, paper summary or sourced synthesis. It returns a report with key papers, themes, open questions and sources, and it needs a Firecrawl API key plus the Firecrawl CLI or MCP tools.

Good for

Students and researchers who need a sourced literature review
Analysts reading clinical, drug, gene or public-health studies
Engineers surveying a technical field from arXiv papers and industry reports

Install firecrawl-research-papers

Claude Code

Copy this prompt.

Install the firecrawl-research-papers skill in Claude Code. Run this command:

/plugin marketplace add firecrawl/firecrawl-workflows
/plugin install firecrawl-workflows@firecrawl-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole firecrawl-workflows plugin: 16 skills (counted from the skills list in its plugin.json), and the repo tree has no hooks, agents or MCP config files. The skills-only routes install just firecrawl-research-papers. The skill drives the Firecrawl CLI and needs a Firecrawl API key. Install the Firecrawl CLI first, since the skill runs firecrawl commands: npm install -g firecrawl-cli (Firecrawl CLI docs), or npx -y firecrawl-cli@latest init -y --browser to install it, sign in and add the shared skills in one step. Then run firecrawl login or export FIRECRAWL_API_KEY. Who pays: the Firecrawl account that owns the key. Every call uses credits; a new account starts on the free plan with 1,000 credits a month and no card. Per Firecrawl's billing docs: search 2 credits per 10 results; scrape 1 credit per page. The billing page lists no price for the paper-research tools, so check your plan.

Built from the package data we hold. Not yet tested by us. Source.

What's in the skill

When it loads

Find and synthesize research papers, whitepapers, PDFs, technical reports, and academic sources with Firecrawl Research, using semantic paper search, related-paper expansion, and in-body verification over Firecrawl's paper index — largely biomedical and life-science literature from PubMed, bioRxiv, and medRxiv, plus arXiv preprints in CS, physics, and math. Use when the user wants a literature review, systematic review, survey of studies, paper summary, research landscape, or sourced synthesis from scholarly and industry publications, including clinical, drug, gene, disease, epidemiology, and public-health topics. Prefer this over a general web-research workflow whenever the evidence base is published papers rather than web pages.

Sections in SKILL.md

Onboarding Interview
Firecrawl Collection Plan
Parallel Work
Final Deliverable
Abstract
Key Papers
Themes And Consensus
Open Questions And Debates
Emerging Trends
Sources
Rerun Inputs
Quality Bar

Key facts

Author: Firecrawl (frontmatter author, and the repo owner)
License: ISC (frontmatter and the README)
Installs on skills.sh: 33,928 (Nov 2, 2026)
GitHub stars: 214 for the whole firecrawl/firecrawl-workflows repo (Nov 2, 2026)
Last repo commit: Nov 1, 2026
What it includes: 1 file: SKILL.md (bundles no scripts)
Needs: A Firecrawl API key (FIRECRAWL_API_KEY) with credits, and the Firecrawl CLI (npm install -g firecrawl-cli)
Part of: The firecrawl-workflows plugin: 16 skills in its Claude plugin.json (counted), 19 skill folders in the repo tree
Works in: AI coding agents, per the README. The repo also ships plugin manifests for Claude Code, Codex and Cursor

What it includes

Semantic search over paper abstracts; the usual starting point
Runs firecrawl research search-papers and retries with other wording when results are thin.
Network · Paper search
Expands from seed papers to similar, citing or referenced work
Runs related-papers with a mode of similar, citers or references, so you get the paper family and not one hit.
Network · Related papers
Fetches title, abstract, authors, categories, source ids and dates
Used to check author, venue, date or method constraints before keeping a candidate.
Network · Inspect a paper
Checks one claim inside a paper: method, score, benchmark or limitation
Runs read-paper with a question about a single paper. SKILL.md says to use it for load-bearing claims, not every candidate.
Network · Read a paper
Uses Firecrawl search and scrape for whitepapers, reports and leaderboards
For facts outside the paper index, such as rankings, research blogs and technical reports.
Network · Web fallback
Splits work across five sub-agent roles when your agent supports it
Roles: Academic Papers, Biomedical and Life Sciences, Industry Reports, Technical Articles, and a Synthesis and citation reviewer.
Runs code · Parallel researchers
Seven sections from Abstract to Rerun Inputs
Abstract, Key Papers, Themes And Consensus, Open Questions And Debates, Emerging Trends, Sources and Rerun Inputs.
Read · Literature review report

From the official docs

Permissions

Low risk

It sends your research queries to Firecrawl using your API key. Set a paper count in your prompt to limit how many calls it makes.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Your topics and queries go through Firecrawl
SKILL.md says the paper tools run on hosted Firecrawl Research with your API key. Treat your topic as shared with Firecrawl. github.com
It can fan out into several sub-agents
SKILL.md suggests five parallel researcher roles when your agent supports them. Parallel runs mean more Firecrawl calls under your key, so set a paper count in your prompt (our advice). github.com
It spends your Firecrawl credits
Every call is billed in credits to the account behind the key. Per Firecrawl's billing docs: search 2 credits per 10 results; scrape 1 credit per page. The billing page lists no price for the paper-research tools, so check your plan. A free account has 1,000 credits a month, so a large run can use it up. docs.firecrawl.dev

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode is documented in SKILL.md. Use version control for files it writes.
Talks to	Hosted Firecrawl Research and Firecrawl search/scrape (named in SKILL.md). The web pages it scrapes for whitepapers and reports
Sign-in and keys	SKILL.md declares FIRECRAWL_API_KEY as a required input. It does not say where the key is kept.
Scopes	Runs Firecrawl CLI or MCP calls for paper search, related-paper expansion, paper reading, web search and scrape Needs FIRECRAWL_API_KEY Spends credits on the Firecrawl account that owns your API key

Questions

What does the firecrawl-research-papers skill do?

It makes your agent write a sourced literature review from published papers. It searches Firecrawl's paper index, expands to related papers, verifies claims inside papers, and returns a report with sources.

How do I install it in Claude Code or Codex?

Use the install box at the top of this page. Claude Code and Codex each have a plugin route and skills CLI commands. Install the Firecrawl CLI first (npm install -g firecrawl-cli, per its docs), then run firecrawl login or set FIRECRAWL_API_KEY. There is no Claude app upload route here, because SKILL.md drives the CLI, MCP tools or an equivalent tool surface.

Who pays for it?

You do, through the Firecrawl account that owns your API key. Firecrawl bills in credits, and a new account starts on the free plan with 1,000 credits a month and no card. Per its billing docs: search 2 credits per 10 results; scrape 1 credit per page. The billing page lists no price for the paper-research tools, so check your plan. Check your balance with firecrawl credit-usage.

Does it need an API key?

Yes. The frontmatter lists FIRECRAWL_API_KEY as a required input for hosted Firecrawl Research, the CLI or MCP. The skill files give no prices, so check your Firecrawl plan.

Which papers can it search?

The index is mostly biomedical and life-science literature from PubMed, bioRxiv and medRxiv, plus arXiv preprints in computer science, physics and math. SKILL.md says coverage outside those sources is thinner and web search is the fallback.

firecrawl-research-papers vs firecrawl-deep-research?

Use research-papers when the evidence is published papers. SKILL.md says to prefer it over a general web-research workflow in that case, and the firecrawl-workflows router skill describes deep-research as the one for web evidence, not literature reviews.

Is it safe to install?

It is a single SKILL.md file and bundles no scripts. When it runs, your agent sends search queries through Firecrawl using your API key. SKILL.md asks for peer-reviewed work to be told apart from blogs and vendor reports, but check key claims against the papers yourself.

Information

updated Nov 2, 2026

Repository: firecrawl/firecrawl-workflows
Folder: skills/firecrawl-research-papers

firecrawl/firecrawl-workflows skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 9

firecrawl-research-papers SKILL.md · github.com
firecrawl-workflows README · github.com
firecrawl-workflows plugin.json · github.com
firecrawl-workflows marketplace.json · github.com
firecrawl-workflows Codex plugin.json · github.com
firecrawl-workflows SKILL.md · github.com
Firecrawl CLI docs · docs.firecrawl.dev
Firecrawl billing and credits · docs.firecrawl.dev
firecrawl/cli README · github.com