Recommendation Engine

This is a solid foundation for building product or content recommenders with collaborative filtering, matrix factorization (SVD), and hybrid approaches. You get practical code for handling the usual pain points: cold start problems with fallback chains, data sparsity using dimensionality reduction instead of naive similarity, and popularity bias through diversity re-ranking. The evaluation section covers precision@k, recall@k, and NDCG for measuring recommendation quality. What I like is the realistic approach to production issues, like always filtering already-interacted items and implementing graceful degradation when personalization fails. If you're building a recommendation system from scratch or fixing one that only shows bestsellers, this gives you the patterns that actually matter.

skills.sh installs: 437
GitHub stars: 248
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add secondsky/claude-skills --skill recommendation-engine --agent claude-code

Installs into .claude/skills of the current project.

Files

Recommendation Engine

Build recommendation systems for personalized content and product suggestions.

Recommendation Approaches

Approach	How It Works	Pros	Cons
Collaborative	User-item interactions	Discovers hidden patterns	Cold start
Content-based	Item features	Works for new items	Limited discovery
Hybrid	Combines both	Best of both	Complex

Collaborative Filtering

import numpy as np
from scipy.sparse import csr_matrix
from sklearn.metrics.pairwise import cosine_similarity

class CollaborativeFilter:
    def __init__(self):
        self.user_similarity = None
        self.item_similarity = None

    def fit(self, user_item_matrix):
        # User-based similarity
        self.user_similarity = cosine_similarity(user_item_matrix)
        # Item-based similarity
        self.item_similarity = cosine_similarity(user_item_matrix.T)

SKILL.md on GitHub