Business lead data scraping

Skill thirdwatch-dev/scraping-skills/skills/business-lead-data-scraping

Use when you need B2B leads or company data — business listings with contact info, supplier directories, company/people enrichment, KYB/verification, or trade data. Covers Google Maps (local listings), IndiaMart and JustDial (supplier/business directories), LinkedIn (company employees and candidate finder), GST Verification (India KYB), UN Comtrade (trade data), and Product Hunt (launches). Triggers on "lead generation", "B2B leads", "find businesses", "company data", "supplier directory", "KYB", "due diligence", "market sizing", "sales prospecting".From its SKILL.md

Install

npx -y skills add thirdwatch-dev/scraping-skills --skill business-lead-data-scraping

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

4 things to look at

reads credentialsReads from 1 credential source: `YOUR_APIFY_TOKEN`.
3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 1 command, including `curl -X POST "https://api.apify.com/v2/acts/thirdwatch~google-maps-scraper/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" -H "Content-Type: application/json" -d '{"search": "marketing agencies in `.
fetches URLsInstructs the agent to fetch 1 URL, including https://api.apify.com/v2/acts/thirdwatch~google-maps-scraper/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.0 KB, 860 tokens by cl100k_base, as published. Nobody here has run it

Business & Lead Data Scraping

Getting B2B leads and company data off the web. Two kinds of sources matter here:

Business listings & directories (Google Maps, IndiaMart, JustDial) give you the prospecting basics: company name, phone, website, category, location, rating. Best for building local lead lists and supplier shortlists.
Registry / verification sources (GST Verification, UN Comtrade) are authoritative — they confirm a legal entity, its status, or its trade activity. Best for KYB/due-diligence and market sizing.

The fields that carry a lead: company, contact (phone/website), category, location — plus a verification or enrichment field (GSTIN, employee roster, HS-code trade volume) when you need to qualify it.

Ready-made scrapers

Each is a maintained Thirdwatch actor on the Apify Store, billed pay-per-result.

Target	Scraper	From	Notes
Google Maps	Google Maps	$0.002/result	name/phone/website/rating/GPS/hours by query + location
IndiaMart	IndiaMart Supplier	$0.002/result	B2B suppliers, contact, GST, MOQ
JustDial	JustDial Business	$0.002/result	India local listings + contact + reviews
LinkedIn Company Employees	LinkedIn Company Employees	$0.003/result	team rosters by company, filter by title/location
LinkedIn Candidate Finder	LinkedIn Candidate Finder	$0.003/result	people by role/skills/location
GST Verification India	GST Verification India	$0.01/result	verify GSTIN → legal/trade name, status, jurisdiction
UN Comtrade Trade Data	UN Comtrade Trade Data	$0.0015/result	bilateral import/export by HS code, 200+ countries
Product Hunt	Product Hunt	$0.003/result	launches/products/leaderboard, votes

Run one

Each actor returns JSON rows. Call it from the command line:

curl -X POST "https://api.apify.com/v2/acts/thirdwatch~google-maps-scraper/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"search": "marketing agencies in Austin", "maxResults": 50}'

Get a free token at console.apify.com. Exact input fields are on each actor's Store page.

Build your own

No maintained scraper for your source, or need something custom? Start with the engineering skills:

web-scraping-playbook — the build-vs-buy decision and the cost-first technique ladder.
anti-bot-scraping — bypassing Cloudflare, DataDome, Akamai, and friends.
apify-actor-builder — package and monetize your scraper as a deployable Apify Actor.

Compliance

Contact and personal data is regulated (GDPR, CCPA, India DPDP, CAN-SPAM): have a lawful basis to process it, honor opt-outs, don't spam, and scrape only publicly accessible business data.

Maintained by Thirdwatch. 70+ ready-made scrapers on the Apify Store.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most sales audience skills give in 860 tokens

Counted across 401 of the 401 authors here whose files we hold, read 2026-08-07

Read product marketing context before asking questionsin 21 of 401, across 11 files
Acknowledge competitor strengths honestlyin 18 of 401, across 7 files
Start every page with a summaryin 15 of 401, across 4 files
Use a single, low-friction call to actionin 15 of 401, across 7 files
Create a single source of truth for each competitorin 14 of 401, across 3 files
Make each follow-up email add new valuein 11 of 401, across 5 files
Cut any sentence that does not drive a replyin 10 of 401, across 4 files
Tie personalization directly to the problemin 10 of 401, across 4 files
Write paragraph comparisons for each dimensionin 9 of 401, across 3 files
Link between related competitor pagesin 9 of 401, across 3 files
Keep subject lines short and lowercasein 9 of 401, across 3 files
Define ideal customer profile from top customersin 9 of 401, across 3 files

Said here and by no other author read

match target source to maintained scraper
call scraper via command line
retrieve json rows from actor
start with engineering skills for custom sources
maintain lawful basis to process data
honor opt-outs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.