Marketing
lead-gen-pipeline avatar

lead-gen-pipeline

AI-powered lead generation pipeline: intelligent lead scoring (0-100) and context-aware follow-up generation for sales, cold outreach, and CRM integration.

Introduction

The Lead Gen Pipeline is a comprehensive sales automation skill designed to streamline the qualification and engagement process for sales teams and growth hackers. By leveraging AI to process behavioral signals—such as whitepaper downloads, pricing page engagement, and email interaction history—the skill provides a standardized 0-100 lead score. This allows teams to prioritize 'Hot' prospects for immediate action while nurturing 'Cool' leads with long-term sequences. The skill also features a robust follow-up generator capable of producing messages in professional, casual, urgent, or consultative tones across multiple channels, including email, SMS, WhatsApp, and LinkedIn.

  • Intelligent Lead Scoring: Evaluates fit, intent, engagement level, and source quality to produce a prioritized score with detailed reasoning.

  • Multi-Channel Follow-up: Generates personalized, context-aware messages tailored to specific sales stages like initial outreach, post-demo, proposal, or closing.

  • Dynamic Tone Control: Supports specialized tones such as professional, casual, urgent, friendly, and consultative to match the brand voice.

  • Flexible CRM Integration: Outputs clean JSON data, allowing for seamless integration with platforms like GoHighLevel (GHL), HubSpot, or custom pipeline management tools via API.

  • Cold Outreach Frameworks: Built-in support for AIDA (Attention, Interest, Desire, Action) frameworks for high-conversion email sequences.

  • Input requirements: Expects JSON-formatted prospect data including name, company, engagement actions, and current pipeline stage.

  • Output format: Returns structured JSON for scores and plain text for follow-up message generation.

  • Usage constraints: Requires an active OPENROUTER_API_KEY for LLM inference; ensure that CRM API webhooks are configured to handle the JSON outputs.

  • Best practices: For optimal scoring accuracy, provide detailed history of behavioral actions; use the 'revival' stage for re-engaging cold leads after long periods of inactivity.

Repository Stats

Stars
4,456
Forks
1,215
Open Issues
7
Language
Python
Default Branch
main
Sync Status
Idle
Last Synced
Apr 30, 2026, 12:38 PM
View on GitHub