recommendation-engine

Build recommendation systems with collaborative filtering, matrix factorization, hybrid approaches. Use for product recommendations, personalization, or encountering cold start, sparsity, quality evaluation issues.

0.98x

Quality

100%

Does it follow best practices?

Impact

84%

0.98x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

20%

Recommender System Evaluation Pipeline

Ranking evaluation metrics

Criteria

Without context

With context

Time-based split

100%

NDCG metric

100%

MAP or AP metric

100%

Precision@K and Recall@K

100%

No RMSE-only evaluation

100%

Catalog coverage

100%

Gini coefficient

100%

Statistical significance

100%

p-value reported

100%

Multiple K values

100%

78%

-22%

Implicit Feedback Recommendation Engine for a Retail Platform

Sparse data matrix factorization

Criteria

Without context

With context

Matrix factorization chosen

100%

ALS for implicit feedback

100%

Confidence weighting formula

100%

Excludes interacted items

100%

Sparse matrix usage

100%

Avoids dense memory-based CF

100%

Latent factors configured

100%

Regularization included

100%

75%

New User Recommendation System for a Content Discovery Platform

Cold start fallback and diversity

Criteria

Without context

With context

Fallback chain implemented

100%

Interaction threshold check

100%

Popularity fallback for cold users

100%

Diversity re-ranking applied

100%

Diversity weight parameter

100%

Explore-exploit strategy

Exploration ratio ~10%

Graceful empty-history handling

100%

Repository: secondsky/claude-skills
Commit: 90d6bd7

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Recommender System Evaluation Pipeline Implicit Feedback Recommendation Engine for a Retail Platform New User Recommendation System for a Content Discovery Platform

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.