Firecrawl Workflows
Route Firecrawl to outcome-focused workflows that ship research reports, SEO audits, lead lists, design systems, and other structured web artifacts instead of one-off scrapes.
Overview
Firecrawl Workflows is an agent skill most often used in Idea (also Validate, Launch, Grow) that routes Firecrawl jobs to outcome-focused workflows producing reports, audits, lists, and design-system docs—not bare page s
Install
npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-workflowsWhat is this skill?
- Orchestrates sibling Firecrawl workflow skills (design clone, deep research, SEO audit, lead research) from one entry po
- Targets finished business, marketing, product, and creative deliverables—not embedding Firecrawl API calls in applicatio
- Requires FIRECRAWL_API_KEY for hosted CLI/API runs
- Outcome-focused routing aligned with Firecrawl’s workflow repo and authoring references
- Pairs with specialized workflow skills rather than replacing low-level scrape/map tools
- Routes to multiple named sibling workflows (design clone, deep research, SEO audit, lead research)
Adoption & trust: 11.5k installs on skills.sh; 29 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need a structured web-data deliverable for business or marketing work, but you only know how to scrape a URL or paste API snippets into code.
Who is it for?
Solo builders running Firecrawl-hosted workflows who want router guidance to the right deliverable-oriented skill before deeper implementation.
Skip if: Teams that only need a single-page scrape inside app code or who lack a Firecrawl API key and hosted workflow path.
When should I use this skill?
User wants Firecrawl to complete a business, marketing, product, or creative workflow that yields a deliverable—not merely scrape a page or integrate API calls into code.
What do I get? / Deliverables
Your agent selects and runs the matching Firecrawl workflow skill so you get a finished artifact (report, audit, list, or DESIGN.md) ready to share or feed the next planning step.
- Routed workflow run
- Structured report, audit, list, or DESIGN.md per chosen child skill
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Idea → research because the router’s default deliverables are sourced market and web intelligence before you commit to build or launch tactics. Research subphase fits deep research, directory mining, and competitive web synthesis—the workflows users pick when they need evidence, not raw HTML.
Where it fits
Spin up deep-research workflow to compile a sourced market report before choosing a niche.
Pull structured competitive web signals into a scope doc without hand-copying directory pages.
Delegate to the SEO audit workflow for on-page and SERP structure before shipping landing pages.
How it compares
Use this workflow router when you want packaged deliverables; use raw Firecrawl scrape/map skills when you are integrating extraction into your own backend.
Common Questions / FAQ
Who is firecrawl-workflows for?
Indie and solo builders using Claude Code, Cursor, or similar agents who rely on Firecrawl for research, SEO, leads, or design extraction and want one skill to pick the right finished workflow.
When should I use firecrawl-workflows?
Use it during Idea research for deep reports and directories, during Validate when you need structured competitive or market evidence, at Launch for SEO audits, and in Grow when producing lead lists or marketing artifacts—whenever the goal is a named deliverable, not a code integ
Is firecrawl-workflows safe to install?
It declares a required Firecrawl API key and network-backed hosted requests; review the Security Audits panel on this page and rotate keys if you run untrusted prompts.
Workflow Chain
Then invoke: firecrawl deep research, firecrawl seo audit
SKILL.md
READMESKILL.md - Firecrawl Workflows
# Firecrawl Workflows Use this when the user wants a finished deliverable powered by Firecrawl, not only raw web extraction and not product-code integration. ## Choose The Workflow - Use [firecrawl-website-design-clone](../firecrawl-website-design-clone/SKILL.md) to extract a website's colors, fonts, spacing, components, and layout patterns into an agent-ready `DESIGN.md`. - Use [firecrawl-deep-research](../firecrawl-deep-research/SKILL.md) for sourced multi-source research reports. - Use [firecrawl-seo-audit](../firecrawl-seo-audit/SKILL.md) for site structure, on-page SEO, keyword, and SERP audits. - Use [firecrawl-lead-research](../firecrawl-lead-research/SKILL.md) for pre-meeting company/person intelligence briefs. - Use [firecrawl-qa](../firecrawl-qa/SKILL.md) for live-site QA testing and bug reports. - Use [firecrawl-competitive-intel](../firecrawl-competitive-intel/SKILL.md) for recurring pricing, feature, and changelog monitoring. - Use [firecrawl-company-directories](../firecrawl-company-directories/SKILL.md) for directory extraction into company lists. - Use [firecrawl-dashboard-reporting](../firecrawl-dashboard-reporting/SKILL.md) for dashboard metrics extraction. - Use [firecrawl-knowledge-base](../firecrawl-knowledge-base/SKILL.md) for LLM-ready docs, RAG chunks, training data, or docs mirrors. - Use [firecrawl-knowledge-ingest](../firecrawl-knowledge-ingest/SKILL.md) for auth-gated or JS-heavy docs portal ingestion. - Use [firecrawl-lead-gen](../firecrawl-lead-gen/SKILL.md) for prospect list generation. - Use [firecrawl-market-research](../firecrawl-market-research/SKILL.md) for market, financial, and industry research. - Use [firecrawl-research-papers](../firecrawl-research-papers/SKILL.md) for literature reviews from papers, PDFs, and whitepapers. - Use [firecrawl-demo-walkthrough](../firecrawl-demo-walkthrough/SKILL.md) for product flow walkthroughs and UX teardown reports. - Use [firecrawl-shop](../firecrawl-shop/SKILL.md) for product research and shopping recommendations. If no existing workflow fits, use this generic process and produce a reusable pattern that could become a new skill. ## Required Intake Infer the workflow, inputs, audience, and output format from the user's request and surrounding context. If enough is clear, start immediately. Ask at most 1-3 concise clarifying questions only when a missing input would block the work, such as: - the URL, company, topic, or source to analyze - the desired deliverable or output format - a constraint that would materially change the workflow Use the host agent's normal way to ask clarifying questions. Do not depend on a harness-specific function name. ## Default Process 1. Confirm the workflow and final artifact. 2. Collect web evidence with Firecrawl through the CLI or equivalent Firecrawl tool surface. 3. Save or cite source evidence so the final claims are traceable. 4. Run independent research units in parallel when available. 5. Synthesize findings into the requested deliverable. 6. Include a short "rerun inputs" block when the workflow could be automated. ## Parallel Work If appropriate, use sub-agents or equivalent parallel task runners for independ