Firecrawl Company Directories
Turn YC, Crunchbase, Product Hunt, G2, or custom company directories into JSON, CSV, or CRM-ready research tables with Firecrawl.
Overview
Firecrawl Company Directories is an agent skill most often used in Idea (also Grow, Validate) that extracts structured company lists from startup and category directories into research-ready tables.
Install
npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-company-directoriesWhat is this skill?
- Supports YC, Crunchbase, Product Hunt, G2 categories, and custom directory URLs
- Chooses Firecrawl browser for filters, pagination, infinite scroll, and profile clicks; scrape/map for static listings
- Structured fields: name, description, category, stage, location, funding, tags, profile and website URLs
- Leaves missing fields blank instead of hallucinating directory metadata
- Infers directory, filters, count, and output format; asks at most 1–3 blocking questions
- Captures 8+ directory field types when visible on listings
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 filterable company list from YC, G2, or Product Hunt but copying rows by hand does not scale.
Who is it for?
Founders building competitor maps, ICP lists, or category landscapes from known directory sources.
Skip if: Scraping directories that forbid automation in their terms, or expecting private CRM fields Firecrawl cannot see on public pages.
When should I use this skill?
Extract structured company lists from directories—YC, Crunchbase, Product Hunt, G2, startup or category directories—into JSON, CSV, CRM-ready lists, or research tables.
What do I get? / Deliverables
You get a structured table or file of companies with directory-visible attributes and stable profile or website links for CRM or analysis.
- JSON or CSV company list
- CRM-ready table
- Research spreadsheet with profile and website URLs
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Idea → competitors is where directory mining answers “who else plays in this space” before validation spend. Competitors subphase matches list-building from category and startup directories rather than single-site UX walks.
Where it fits
Export all companies in a G2 category to compare positioning angles.
Pull YC batch listings into a spreadsheet for trend analysis.
Count addressable players in a directory before committing to a narrow wedge.
Build a partnership prospect list from Product Hunt launches in your vertical.
How it compares
Use this for tabular directory extraction; use demo-walkthrough when you need narrative UX flows on a single product site.
Common Questions / FAQ
Who is firecrawl-company-directories for?
Indie builders and solo founders doing market scans who want agent-driven directory extraction instead of manual copy-paste or bespoke Python scrapers.
When should I use firecrawl-company-directories?
In Idea for competitor and category research; in Validate to size a niche from directory counts; and in Grow when assembling lead or partnership lists from G2 or Product Hunt—whenever the source is a company directory, not a single app UI.
Is firecrawl-company-directories safe to install?
It uses network and browser automation against third-party sites; respect site terms and review the Security Audits panel on this page before running at scale.
Workflow Chain
Then invoke: firecrawl lead research
SKILL.md
READMESKILL.md - Firecrawl Company Directories
# Firecrawl Company Directories Use this to turn startup or company directories into structured lists. ## Onboarding Interview Infer the directory, filters, result count, and output format from context. If the source is clear, proceed immediately. Ask at most 1-3 concise questions only if blocked, such as the directory URL/name, required filters, or target result count. ## Firecrawl Collection Plan Use Firecrawl browser when the directory needs filters, pagination, infinite scroll, or profile clicks. Use scrape/map when listings are public and static. Suggested sources include YC companies, Crunchbase, Product Hunt, G2 categories, or any custom directory URL. ## Extraction Fields Capture fields that are visible: - name - description - industry/category - stage/founded/location/team size/funding when visible - tags - directory profile URL - company website URL Leave unavailable fields blank. Do not infer. ## Final Deliverable ```markdown # Company Directory Export: [Source] ## Summary [Filters, count extracted, limitations] ## Companies [Table or link to JSON/CSV] ## Sources [Directory pages and profiles used] ## Rerun Inputs workflow: firecrawl-company-directories directory: [source] filters: [criteria] max_results: [number] output: [json/csv/markdown] ``` ## JSON Shape Use `source`, `filters`, `extractedAt`, `totalResults`, and `companies[]` with `name`, `url`, `description`, `industry`, `stage`, `founded`, `location`, `teamSize`, `funding`, `tags`, `profileUrl`, and `websiteUrl`. ## Quality Bar - Deduplicate companies. - Track pagination progress. - Note rate limits, login walls, or CAPTCHA blocks.