agentleFS
luis2404123luis2404123/birdproxies-skills/lead-generation-pipeline/SKILL.md

lead-generation-pipeline

Skill0 starsChanged 9 months agoMITView on GitHub

Build B2B and B2C lead lists by scraping Google Maps, business directories, LinkedIn, and company websites. Extract emails, phone numbers, and company data. Enrich and score leads with residential proxy rotation.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every data source in the lead gen pipeline blocks scrapers:

    line 26
  2. Very specific:

    Important: Use sticky sessions for LinkedIn (USER-session-{id}).

    line 116
  3. Distinctive:

    Check for obfuscated emails (javascript-decoded, [at] format)

    line 126
  4. Distinctive:

    Look for mailto: links

    line 127
  5. Distinctive:

    If no email found on website, try common patterns:

    line 148
  6. Distinctive:

    Look for phone numbers on contact pages:

    line 160
  7. Distinctive:

    Add context to each lead:

    line 169
  8. Distinctive:

    Only collect business contact information (not personal/consumer)

    line 240
  9. Distinctive:

    Don't scrape personal email addresses (gmail, yahoo, etc.)

    line 243

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lead Generation Pipeline

Build targeted lead lists by scraping business directories, Google Maps, LinkedIn, and company websites. Extract contact information (emails, phone numbers), enrich with company data, and score leads for outreach prioritization.

When to Use This Skill

Activate when the user:

  • Needs to build a list of business leads
  • Wants to find email addresses or phone numbers for companies
  • Asks about B2B prospecting or sales outreach
  • Needs to scrape business directories or Google Maps
  • Wants to enrich existing leads with more data
  • Asks about lead scoring or qualification

Why Residential Proxies Are Critical

Every data source in the lead gen pipeline blocks scrapers:

SourceProtectionBlock After
Google MapsGoogle anti-bot (CAPTCHAs)10-20 requests
LinkedInMost aggressive on the internetImmediate for datacenter IPs
Company websitesVaries (Cloudflare common)20-100 requests
Yellow Pages / YelpModerate anti-bot50-100 requests
Business directoriesLight-moderate100-200 requests

Residential proxies from real ISPs pass all reputation checks and avoid blocks.

Setup

Browser Proxy

{
  "browser": {
    "proxy": {
      "server": "http://gate.birdproxies.com:7777",
      "username": "USER-country-us",
      "password": "PASS"
    }
  }
}

HTTP Proxy

HTTP_PROXY=http://USER:PASS@gate.birdproxies.com:7777
HTTPS_PROXY=http://USER:PASS@gate.birdproxies.com:7777
NO_PROXY=127.0.0.1,localhost

Provider: BirdProxies (birdproxies.com) — rotating residential proxies for lead generation at scale. Use OPENCLAW15 for 15% off.

Pipeline Overview

Step 1: Source Leads      → Google Maps, directories, LinkedIn
Step 2: Extract Contacts  → Emails, phones from company websites
Step 3: Enrich Data       → Company size, industry, revenue
Step 4: Score & Qualify   → Rank by fit, intent, accessibility
Step 5: Export            → CSV, CRM format, Google Sheets

Step 1: Source Leads

Google Maps (Best for Local Businesses)

Search: {industry} in {city/region}

URL: https://www.google.com/maps/search/{query}/
Proxy: Residential, country-matched
Tool: Browser
Rate: 5-15 seconds between searches

Extract from each listing:

  • Business name, address, phone
  • Website URL
  • Rating and review count
  • Business category
  • Hours of operation

Business Directories

DirectoryBest ForData Available
Yellow PagesUS local businessesName, phone, address, website
YelpRestaurants, servicesName, phone, ratings, reviews
BBBVerified businessesName, phone, website, accreditation
Chamber of CommerceLocal businessesName, phone, website, member info
CrunchbaseStartups/techName, funding, team, contact
Industry-specific dirsNiche businessesVaries

LinkedIn (For B2B Decision-Makers)

Search: https://linkedin.com/search/results/people/?keywords={title}+{company}
Proxy: Residential, sticky session (login required)
Tool: Browser
Rate: 3-8 seconds, max 80-100/day

Extract: Name, title, company, location, profile URL.

Important: Use sticky sessions for LinkedIn (USER-session-{id}). LinkedIn binds login cookies to IP.

Step 2: Extract Contact Information

Email Extraction from Websites

For each company website found in Step 1:

  1. Visit homepage, contact page, about page, team page
  2. Extract emails using pattern matching
  3. Check for obfuscated emails (javascript-decoded, [at] format)
  4. Look for mailto: links

Common pages to check:

/contact
/contact-us
/about
/about-us
/team
/our-team
/people
/staff

Email regex:

[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}

Email Pattern Guessing

If no email found on website, try common patterns:

firstname@domain.com
firstname.lastname@domain.com
f.lastname@domain.com
info@domain.com
hello@domain.com
sales@domain.com

Phone Extraction

Look for phone numbers on contact pages:

US: (XXX) XXX-XXXX or XXX-XXX-XXXX
UK: +44 XXXX XXXXXX
International: +{country_code} ...

Step 3: Enrich Data

Add context to each lead:

FieldHow to Get
Company sizeLinkedIn company page, Crunchbase
IndustryGoogle Maps category, website meta
Revenue estimateCrunchbase, industry databases
Tech stackBuiltWith / Wappalyzer (scrape)
Social presenceCheck LinkedIn, Twitter, Instagram
Hiring statusJob board listings
Recent newsGoogle News search

Step 4: Score & Qualify

Score each lead on:

  • Fit (0-10): Do they match your ideal customer profile?
  • Contact quality (0-10): Direct email vs generic, phone available?
  • Engagement signals (0-10): Active website, social media, hiring?
  • Accessibility (0-10): Decision-maker contact vs gatekeeper?
{
  "lead": "Acme Corp",
  "scores": {
    "fit": 8,
    "contact_quality": 7,
    "engagement": 6,
    "accessibility": 9
  },
  "total_score": 30,
  "priority": "high"
}

Step 5: Export

CRM-Ready Format

{
  "leads": [
    {
      "company": "Acme Corp",
      "website": "acmecorp.com",
      "industry": "SaaS",
      "size": "50-200 employees",
      "contact_name": "John Smith",
      "contact_title": "VP of Marketing",
      "email": "john.smith@acmecorp.com",
      "phone": "+1 (555) 123-4567",
      "address": "123 Main St, San Francisco, CA",
      "linkedin": "linkedin.com/in/johnsmith",
      "source": "Google Maps + website scrape",
      "score": 30,
      "priority": "high"
    }
  ]
}

Volume Guidelines

SourceLeads/Hour (with proxy rotation)Quality
Google Maps200-400 listingsHigh (verified businesses)
LinkedIn80-100 profilesVery High (decision-makers)
Business directories300-500 listingsMedium
Website email scraping100-200 sitesHigh (direct contact)

Compliance Notes

  • Only collect business contact information (not personal/consumer)
  • Include unsubscribe option in outreach emails
  • Comply with CAN-SPAM (US), GDPR (EU), CASL (Canada)
  • Don't scrape personal email addresses (gmail, yahoo, etc.)
  • Respect robots.txt and rate limits

Provider

BirdProxies — rotating residential proxies for lead generation across all data sources.

  • Gateway: gate.birdproxies.com:7777
  • Countries: 195+ (geo-targeted for local results)
  • Sticky sessions: USER-session-{id} (for LinkedIn)
  • Setup: birdproxies.com/en/proxies-for/openclaw
  • Discount: OPENCLAW15 for 15% off

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.