firecrawl-company-directories Skill for Claude: What It Does and How to Install It

Makes your agent turn a page that lists companies into a structured CSV or JSON, such as an accelerator batch or app directory.

Installs: 31.5K; on skills.sh
Stars: 214; on GitHub
Updated: Nov 2026; last repo commit

This skill makes your agent extract companies from any page or site that lists them. Examples in SKILL.md are YC, Crunchbase, Product Hunt, G2, accelerator batches, VC portfolios, member and sponsor lists, and app directories.

It uses a Firecrawl browser for filters, pagination, infinite scroll and profile clicks, and scrape or map for public static lists. It leaves fields blank when they are not visible, and needs a Firecrawl API key and the Firecrawl CLI.

Good for

Researchers building a company table from a directory
Sales and BD teams collecting accounts from member or sponsor lists
Investors scanning accelerator batches and portfolios

Install firecrawl-company-directories

Claude Code

Copy this prompt.

Install the firecrawl-company-directories 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-company-directories. 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: scrape 1 credit per page; map 1 credit per call; Interact (browser sessions) 2 to 7 credits per browser minute.

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

What's in the skill

When it loads

Extract structured company lists with Firecrawl from any page or site that lists companies: accelerator batches, VC portfolios, member and sponsor lists, marketplaces and app directories, YC, Crunchbase, Product Hunt or G2. Use when the user wants those companies as a CSV, JSON, CRM-ready list or research table, even without an explicit request to scrape.

Sections in SKILL.md

Onboarding Interview
Firecrawl Collection Plan
Extraction Fields
Final Deliverable
Summary
Companies
Sources
Rerun Inputs
JSON Shape
Quality Bar

Key facts

Author: Firecrawl (frontmatter author, and the repo owner)
License: ISC (frontmatter and the README)
Installs on skills.sh: 31,489 (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

Browser for filters, pagination, scroll or profile clicks; scrape and map for static lists
Matches the tool to how the directory loads.
Network · Choose the method
Name, description, category, stage, founded, location, team size, funding, tags and URLs
Only fields that are visible are captured. Unavailable fields stay blank and nothing is inferred.
Network · Extract visible fields
source, filters, extractedAt, totalResults and a companies list of 12 fields
Each company has name, url, description, industry, stage, founded, location, teamSize, funding, tags, profileUrl and websiteUrl.
Write · JSON output
Summary, Companies, Sources, Rerun Inputs
Outputs a table or a link to JSON, CSV or markdown.
Read · Export report
Deduplicates, tracks pagination, notes rate limits, login walls and CAPTCHA blocks
The quality bar SKILL.md ends with.
Read · Quality checks

From the official docs

Permissions

Low risk

It browses and scrapes the directories you name through Firecrawl using your API key. Set a result count and check each site's terms.

What it can do

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

Watch out for

Directories can rate-limit or block it
SKILL.md tells the agent to note rate limits, login walls and CAPTCHA blocks. Set a result count in your prompt. github.com
It acts on the directory through a browser
Filters, pagination, scrolling and profile clicks run in a Firecrawl browser. The skill does not mention the directory's terms of use, so check them yourself. github.com
It spends your Firecrawl credits
Every call is billed in credits to the account behind the key. Per Firecrawl's billing docs: scrape 1 credit per page; map 1 credit per call; Interact (browser sessions) 2 to 7 credits per browser minute. 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	Firecrawl hosted service. The directory sites you point it at
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 scrape, map and browser actions with your API key Can write a CSV or JSON of companies Spends credits on the Firecrawl account that owns your API key

Questions

What does the firecrawl-company-directories skill do?

It makes your agent turn a page that lists companies into structured data. You get a CSV, JSON or research table with fields such as name, category, stage, location and website.

How do I install it in Claude Code or Codex?

Use the install box at the top of this page. Each client has 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.

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: scrape 1 credit per page; map 1 credit per call; Interact (browser sessions) 2 to 7 credits per browser minute. Check your balance with firecrawl credit-usage.

Does it fill in missing data?

No. SKILL.md says to capture only visible fields, leave unavailable ones blank and not infer them.

firecrawl-company-directories vs firecrawl-lead-gen?

Use company-directories for a plain export of a company directory. The lead-gen SKILL.md sends that job here and keeps lead-gen for qualified prospect lists from people and company data.

What happens when a site blocks it?

SKILL.md says to note rate limits, login walls or CAPTCHA blocks in the output. It does not describe a way around them.

Is it safe to install?

It is a single SKILL.md file and bundles no scripts. When it runs, your agent drives a browser or scrapes the directory through Firecrawl with your API key. Check the directory's terms before you collect data at scale.

Information

updated Nov 2, 2026

Repository: firecrawl/firecrawl-workflows
Folder: skills/firecrawl-company-directories

firecrawl/firecrawl-workflows skills.sh

Sources

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

Show all 9

firecrawl/cli README · github.com
firecrawl-company-directories 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-lead-gen SKILL.md · github.com
Firecrawl CLI docs · docs.firecrawl.dev
Firecrawl billing and credits · docs.firecrawl.dev