Agent skill · software engineering · secondsky
recommendation-system
Deploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency serving, or encountering cache invalidation, experiment tracking, quality monitoring issues.
Why this skill is useful
Adds a complete executable recommendation API with caching and monitoring that the AI cannot generate on its own.
What it needs
Requires docker, fastapi, prometheus-client, redis installed locally. About 6k tokens when loaded. Last updated 2026-08-06. 204 stars on the source repository.
What this skill does
Recommendation System Production-ready architecture for scalable recommendation systems with feature stores, multi-tier caching, A/B testing, and comprehensive monitoring. When to Use This Skill Load this skill when: Building Recommendation APIs: Serving personalized recommendations at scale Implementing Caching: Multi-tier caching for sub-millisecond latency Running A/B Tests: Experimenting with recommendation algorithms Monitoring Quality: Tracking CTR, conversion, diversity, coverage Optimizing Performance: Reducing latency, increasing throughput Feature Engineering: Managing user/item features with feature stores Quick Start: Recommendation API in 5 Steps Result: Working recommendation API with caching in under 5 minutes. System Architecture Core Components 1. Feature Store Centralized storage for user and item features: 2. Model Serving Serve multiple models for A/B testing: 3. Caching Layer Multi-tier caching for low latency: Key Metrics Metric Description Target -------- ------------- -------- CTR Click-through rate >5% Conversion Rate Purchases from recs >2% P95 Latency 95th percentile response time <200ms Cache Hit Rate % served from cache >80% Coverage % of catalog recommended >50% Diversity Variety in recommendations >0.7 Known Issues Prevention 1. Cold Start for New Users Problem: No recommendations for users without history, poor initial experience. Solution: Use popularity-based fallback: 2. Cache Invalidation on User Actions Problem: User makes purchase, cache still shows purchased item in recommendations. Solution: Invalidate cache on relevant actions: 3. Thundering Herd on Cache Expiry Problem: Many users' caches expire simultaneously, overload database/model. Solution: Add random jitter to TTL: 4. Poor Diversity = Filter Bubble Problem: Recommendations too similar, users only see same category. Solution: Implement diversity constraint: 5. No Monitoring = Silent Degradation Problem: Recommendation quality drops, nobody notices until users complain. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills secondsky/recommendation-system