skills.rest
weisberg
weisbergCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

crm-lead-scoring

Build predictive lead scoring models from CRM data with SHAP explanations.

1|Updated Mar 19, 2026
Search Tags:#lead scoring#predictive analytics#sales forecasting#segmentation#pipeline analytics#crm analytics#shap explanations
One-click install
npx skills add https://github.com/weisberg/agile_agentic_analytics --skill crm-lead-scoring
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: crm-lead-scoring
Source: https://github.com/weisberg/agile_agentic_analytics/tree/main/plugins/marketing-analytics/skills/crm-lead-scoring
Command: npx skills add https://github.com/weisberg/agile_agentic_analytics --skill crm-lead-scoring

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scikit-learn, shap, scipy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Lead qualification and prioritization in CRM often suffer from unreliable manual scoring and unclear next-best actions. This Skill provides predictive lead scoring to identify high-potential opportunities, enabling RevOps, sales, and marketing teams to focus on the most valuable leads and accelerate revenue.

Core Features & Use Cases

  • Predictive lead scoring combining firmographic, demographic, and behavioral signals to estimate conversion likelihood.
  • Pipeline analytics: track lead-to-close metrics, pipeline velocity, and win/loss factors to identify bottlenecks.
  • Segment-aware scoring and CRM integration with Salesforce and HubSpot field mappings to leverage existing data.
  • SHAP explanations for model transparency, enabling trust and actionability in decision making.

Quick Start

Ingest CRM leads and activities, train a predictive lead scoring model, and produce a ranked list of leads with their predicted conversion probabilities.

Frequently Asked Questions about crm-lead-scoring

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a predictive lead scoring model from CRM data?▼

Predictive lead scoring ingests CRM leads and activities, trains a machine learning model on firmographic, demographic, and behavioral signals, and outputs a ranked list of leads with calibrated conversion probabilities.

Can I use SHAP explanations to understand why a lead scored high?▼

SHAP explanations provide model transparency by decomposing each lead's predicted conversion probability into feature-level contributions, enabling RevOps teams to understand the specific firmographic, demographic, and behavioral factors driving each score.

Does this lead scoring approach work with Salesforce and HubSpot data?▼

Lead scoring works with Salesforce and HubSpot through native field mappings that leverage existing CRM data, allowing you to ingest leads and activities directly to train predictive models and output pipeline analytics.

What is the best way to identify high-priority leads using pipeline analytics?▼

Pipeline analytics identifies high-priority leads by tracking lead-to-close metrics, pipeline velocity, and win/loss factors to detect bottlenecks, combining these insights with predictive conversion probabilities for smarter deal prioritization.

How do I include segment membership in predictive lead scoring models?▼

Segment-aware scoring optionally enriches the predictive model with segment membership data alongside firmographic, demographic, and behavioral features to improve segmentation-aware scoring and support targeted pipeline analysis.

Do I need pandas and scikit-learn to run predictive lead scoring?▼

Predictive lead scoring requires pandas, numpy, scikit-learn, shap, and scipy to build, validate, and explain models from CRM data, producing calibrated probability estimates and pipeline metrics for RevOps decisions.

Related Skills

Explore More Marketing & Sales Skills→
Greenmamba29Greenmamba29

lead-scorer

Score inbound leads against ICP criteria and route high-priority ones to sales representatives.

Community
Advanced
tomlupotomlupo

shap

Explain model predictions by attributing outputs to input features with SHAP values.

Community
Advanced
bomberoxenviosdosruedasbomberoxenviosdosruedas

agency-pipeline-analyst

Analyze sales pipeline health and revenue forecasts using historical data and velocity metrics.

Community
Advanced
kenny589kenny589
58

lead-prioritization

Rank leads by conversion probability using weighted fit, intent, and engagement scoring.

Community
Advanced