firecrawl-company-directories

Extract structured company lists from startup directories using Firecrawl into JSON or CSV.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-company-directories-webdevarif
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-company-directories
Source: https://github.com/webdevarif/claude-skills/tree/main/firecrawl-company-directories
Command: npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-company-directories-webdevarif

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually copying company information from startup directories like YC, Crunchbase, or Product Hunt into spreadsheets is slow and error-prone. This Skill automates the collection of company listings into clean, structured datasets ready for CRM import or research analysis. ## Core Features & Use Cases - Directory Scraping: Collect company listings from YC, Crunchbase, Product Hunt, G2 categories, or any custom directory URL using Firecrawl browser or scrape/map modes. - Structured Extraction: Capture name, description, industry, stage, funding, location, team size, tags, profile URL, and website URL into a consistent JSON schema. - Flexible Output: Deliver results as JSON, CSV, CRM-ready lists, or Markdown research tables with deduplication and pagination tracking. - Use Case: A VC analyst needs a list of all YC W24 fintech startups with their websites and descriptions. The Skill navigates the directory, applies filters, and exports a deduplicated CSV. ## Quick Start Ask the AI to extract the first 50 companies from the YC companies directory filtered by fintech into a CSV file using your Firecrawl API key.

Frequently Asked Questions about firecrawl-company-directories

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scrape company lists from YC or Crunchbase directories?

Provide the directory URL and any filters, and the Skill uses Firecrawl to navigate listings and extract company fields into JSON or CSV. It handles pagination, infinite scroll, and profile clicks automatically.

What data fields can be extracted from company directories?

The Skill captures name, description, industry, stage, founded date, location, team size, funding, tags, profile URL, and website URL. Fields not visible on the directory are left blank rather than inferred.

Does Firecrawl directory scraping require an API key?

Yes, a FIRECRAWL_API_KEY environment variable is required for hosted Firecrawl requests. Without it, the Skill cannot execute browser or scrape operations against directories.

What happens when a directory has a login wall or CAPTCHA?

The Skill notes rate limits, login walls, and CAPTCHA blocks in the output summary rather than bypassing them. Blocked pages are reported as limitations so you know which results are incomplete.

When should I use browser mode versus scrape mode in Firecrawl?

Use Firecrawl browser mode when the directory requires filters, pagination, infinite scroll, or profile clicks. Use scrape or map mode when listings are public and statically rendered.