← Back to Skills Marketplace
merjua14

Local Lead Gen

by merjua14 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
265
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install local-lead-gen
Description
Automated local business lead generation and cold outreach pipeline. Scans businesses by niche and city, scores their websites (SSL, mobile, speed, design),...
README (SKILL.md)

Local Lead Gen — Automated Business Prospecting & Outreach

Find local businesses with bad websites, score them, and auto-email personalized pitches.

Pipeline Overview

  1. Scan — Search businesses by niche + city via Brave Search API
  2. Score — Check each site: SSL, mobile-friendly, speed, design age, broken elements (0-100)
  3. Filter — Flag sites scoring \x3C40 as outreach candidates
  4. Enrich — Extract emails from contact pages using DeepCrawl or direct scraping
  5. Email — Send personalized cold emails via Resend (or any SMTP provider)
  6. Track — Log all leads to Google Sheets or CSV with status tracking

Requirements

  • Brave Search API key — for business discovery (free tier available)
  • Resend API key (or SMTP credentials) — for sending cold emails
  • DeepCrawl API key (optional) — for better contact page parsing
  • Google Sheets OAuth (optional) — for lead tracking

Quick Start

# Set environment variables
export BRAVE_API_KEY=your_key
export RESEND_API_KEY=your_key

# Run the scanner
node scripts/bad-website-hunter.js --niche "restaurants" --city "Austin TX" --limit 20

Configuration

Edit scripts/config.json to customize:

  • Target niches and cities
  • Score thresholds for outreach
  • Email templates and sender info
  • Suppression list (unsubscribed emails)

Scripts

  • scripts/bad-website-hunter.js — Main pipeline: scan → score → enrich → email
  • scripts/config.json — Pipeline configuration

Email Templates

The default cold email template pitches web design/development services. Customize in config.json:

Subject: Quick question about {business_name}'s website

Hi {first_name},

I was looking at {business_name}'s website and noticed a few things 
that might be costing you customers: {issues_found}.

I help local businesses in {city} modernize their online presence. 
Would you be open to a quick chat about what an upgrade could look like?

Best,
{sender_name}

Scaling

  • Small towns (pop 5-30K) yield the highest percentage of bad sites
  • Best niches: restaurants, auto repair, salons, contractors, law offices
  • Send 10-25 emails per day per domain to avoid spam flags
  • Rotate sending domains if scaling past 50/day
  • Add drip sequences (follow-up emails at day 3 and day 7)

References

  • See references/scoring-criteria.md for website scoring methodology
  • See references/email-best-practices.md for cold email deliverability tips
Usage Guidance
This skill appears to do what it says (scan sites, scrape contact info, and send cold emails), but take precautions before running it: - The registry metadata is incorrect: the script requires BRAVE_API_KEY and RESEND_API_KEY (and optionally DEEPCRAWL_KEY). Confirm the publisher fixes the declared requirements or be prepared to provide those keys at runtime. - Only supply API keys you control and understand. The RESEND key lets the script send email from the configured sender; revoke it if you stop using the tool. - Review and edit scripts/config.json (email templates, suppression list, thresholds) before running. Test with --dry-run to avoid accidental sends. - Be aware of legal and reputation risk: scraping emails and sending unsolicited outreach can violate laws/policies (CAN-SPAM, GDPR) and harm deliverability. The skill even advises rotating domains and warm-up tactics — that can facilitate abusive behavior. - Run the script in an isolated environment (separate sending domain/account, sandbox) and monitor outbound activity and API usage to detect unexpected behavior. - Because the source is 'unknown' and there is no homepage, prefer caution: inspect the code yourself (or have someone you trust do it), and consider alternatives from trusted publishers if you need production use. If you want to proceed, start with a dry-run, limit scope to small, consented lists, and validate suppression/unsubscribe handling before any real sending.
Capability Analysis
Type: OpenClaw Skill Name: local-lead-gen Version: 1.0.0 The skill bundle provides a legitimate automated lead generation and cold outreach pipeline as described in its documentation. The main script, `scripts/bad-website-hunter.js`, uses the Brave Search API for discovery, performs basic website analysis for scoring, and utilizes the Resend API for email delivery, all of which align with the stated purpose in `SKILL.md`. There is no evidence of data exfiltration, credential theft, or hidden malicious instructions; the tool requires user-provided API keys and includes a dry-run mode for safe testing.
Capability Assessment
Purpose & Capability
The name/description align with the included code: the script searches Brave, scores sites, scrapes/enriches contact info, and sends emails via Resend. HOWEVER the registry metadata claims no required environment variables while both SKILL.md and the script require BRAVE_API_KEY and RESEND_API_KEY (and optionally DEEPCRAWL_KEY / Google Sheets OAuth). That mismatch between declared requirements and actual runtime needs is an incoherence and should be corrected/clarified by the publisher.
Instruction Scope
The SKILL.md and script stay within the stated lead-gen/outreach scope (search → score → enrich → email). However the instructions explicitly advise operational tactics (rate limits, rotating sending domains, warm-up guidance) that facilitate evading spam/abuse detection and scaling unsolicited outreach. The script scrapes sites for emails and will transmit them to external APIs — this is expected for the use case but raises privacy and compliance concerns (CAN-SPAM, GDPR) that are not enforced by the code.
Install Mechanism
No install spec; this is instruction-only with an included Node.js script. Nothing is downloaded or installed automatically by the skill bundle — risk is limited to running the included script locally.
Credentials
Requested runtime credentials in SKILL.md and the script (BRAVE_API_KEY, RESEND_API_KEY, optional DEEPCRAWL_KEY, optional Google Sheets OAuth) are proportional to the described functionality. But the registry metadata lists zero required env vars — a visibility/control problem. The script will fail without those keys, and providing email-sending credentials grants it the ability to send messages on your behalf, so you should only use keys you control and understand.
Persistence & Privilege
The skill does not request permanent 'always' inclusion and does not modify other skills or system-wide config. It runs as a single Node.js script and does not persist beyond local files (config.json, logs you produce).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install local-lead-gen
  3. After installation, invoke the skill by name or use /local-lead-gen
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Scan local businesses, score websites, auto-email pitches to bad ones
Metadata
Slug local-lead-gen
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Local Lead Gen?

Automated local business lead generation and cold outreach pipeline. Scans businesses by niche and city, scores their websites (SSL, mobile, speed, design),... It is an AI Agent Skill for Claude Code / OpenClaw, with 265 downloads so far.

How do I install Local Lead Gen?

Run "/install local-lead-gen" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Local Lead Gen free?

Yes, Local Lead Gen is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Local Lead Gen support?

Local Lead Gen is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Local Lead Gen?

It is built and maintained by merjua14 (@merjua14); the current version is v1.0.0.

💬 Comments