Verified:GitHub

personalized-recommendation

Analyze customer purchase history to generate personalized product recommendations.

1|1|Updated Apr 12, 2026

Search Tags:#personalization #real-time #recommendations #ecommerce #multichannel #collaborative-filtering #purchase-history

Ready to run

npx skills add https://github.com/huifer/Shopilot --skill personalized-recommendation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: personalized-recommendation
Source: https://github.com/huifer/Shopilot/tree/main/skills/personalized-recommendation
Command: npx skills add https://github.com/huifer/Shopilot --skill personalized-recommendation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Elevates ecommerce conversions by delivering personalized product recommendations based on purchase history, collaborative filtering, and frequently bought-together patterns.

Core Features & Use Cases

Purchasing-history based recommendations (复购/升级/组合推荐)
Collaborative filtering (user-user and item-item)
Real-time and multichannel recommendations (产品页、购物车、邮件)

Quick Start

Ask the AI to generate 8 personalized product recommendations for customer 12345 based on their purchase history.

Frequently Asked Questions about personalized-recommendation

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

FAQPage Schema

How do I generate personalized product recommendations based on purchase history?▼

Personalized product recommendations based on purchase history are generated by analyzing customer records to deliver targeted suggestions for repurchases, upgrades, and frequently bought-together product combinations.

How does collaborative filtering work for ecommerce recommendations?▼

Collaborative filtering for ecommerce recommendations works by applying user-user and item-item algorithms to purchase history data, identifying behavioral patterns to suggest relevant products across multichannel touchpoints.

Can I deliver real-time recommendations across multichannel ecommerce workflows?▼

Real-time recommendations can be delivered across multichannel ecommerce workflows including product pages, shopping carts, emails, and homepage feeds with configurable algorithms and scalable ranking.

What is the best way to handle cold-start customers in a recommendation engine?▼

Handling cold-start customers in a recommendation engine involves applying configurable algorithms and evaluation metrics to generate targeted product suggestions for new users without prior purchase history.

Does this recommendation engine support co-purchase rules for frequently bought-together items?▼

The recommendation engine supports co-purchase rules by analyzing frequently bought-together patterns from purchase history to deliver precise product combinations for returning customers.

How do I evaluate the performance of personalized recommendation algorithms?▼

Evaluating personalized recommendation algorithms performance utilizes configurable evaluation metrics to measure ranking quality and scalability across collaborative filtering and purchase-history based suggestion workflows.