Firecrawl Deep Research

When you need more than a few Google results, this skill orchestrates Firecrawl to run actual multi-source research. It searches from different angles, scrapes 5 to 25+ pages depending on depth, and synthesizes findings into a sourced report with an executive summary, key findings, contrarian views, and open questions. The template pushes for primary sources and flags uncertainty instead of pretending everything is settled. It can spin up parallel sub-agents by research angle if your task supports it. Best for technical investigations, market research, or any time you need citations and synthesis rather than raw links. Built by the Firecrawl team.

skills.sh installs: 35.9K
GitHub stars: 221
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Firecrawl Deep Research

Use this only for report-scale research: a rigorous, cited synthesis the user explicitly wants delivered as a formal written report. If the request is a product pick, a top-N list, a quick lookup, or anything answerable with a short search, stop; do not use this skill, let the request be handled the standard way.

This skill gathers its evidence from the open web. If the evidence base is the published literature — a literature review, or a biomedical, clinical, or other scientific topic where the answer lives in papers — use firecrawl-research-papers instead; it queries Firecrawl's paper index rather than searching websites.