recommendation-algorithm-design
CommunityDesign recommendation systems that work
Software Engineering#embeddings#feedback-loops#recommendation-systems#exploration-exploitation#ranking-models#ann-indexing#multi-objective-optimization
Authornirholas
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It solves the challenge of building feeds and ranking engines that reliably show relevant content while avoiding echo chambers and engagement-trap failure modes.
Core Features & Use Cases
- End-to-end Recommendation Pipeline: Learn candidate generation, ranking, filtering/mixing, and final feed composition from first principles.
- Modeling & Retrieval Techniques: Understand two-tower retrieval, embedding similarity, and approximate nearest neighbor (ANN) scaling.
- Real-World Feed Engineering: Apply multi-objective ranking, diversity injection, exploration vs. exploitation (bandits), and long-term feedback metrics.
- Domain Adaptation for Crypto Feeds: Incorporate crypto/community-specific quality signals such as on-chain proof, watchlists/portfolios, and agent reputation.
Quick Start
Use this skill to design a full social recommendation pipeline by asking: "Teach me how to go from candidate generation to multi-objective ranking and diversity-aware feed delivery for a crypto community platform."
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: recommendation-algorithm-design Download link: https://github.com/nirholas/three-ui/archive/main.zip#recommendation-algorithm-design Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.