Recsys Pipeline Architect

If you've ever built a feed, search ranker, or notification system, you've reinvented this pipeline shape: fetch candidates, hydrate metadata, filter the ineligible, score what's left, pick top K, log impressions async. This skill scaffolds that six-stage pattern (popularized by xAI's open-sourced X algorithm) into working code for your stack. The real value is in the trade-offs it surfaces: single score versus multi-action prediction, online versus batch, filter ordering. It won't write your ML model, but it will wrap it in proper plumbing so you're not debugging why cache writes are blocking user responses at 3am.

skills.sh installs: 4.6K
GitHub stars: 42.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add wshobson/agents --skill recsys-pipeline-architect --agent claude-code

Installs into .claude/skills of the current project.

Files

Recsys Pipeline Architect

A spec-and-scaffold skill for building composable recommendation, ranking, and feed pipelines. Encodes the six-stage pattern popularized by xAI's open-sourced For You algorithm (Apache 2.0) and applies it to any "top K for (user, context)" problem.

Overview

Most "recommendation systems" in production aren't exotic ML — they're pipelines: fetch candidates from one or more sources, enrich them with metadata, drop the ineligible, score the rest, sort and pick the top K, then fire async side effects. The pattern is universal. The scoring function and the items change; the pipeline shape doesn't.

This skill is an independent reimplementation of the pattern (MIT) — no code copied from the original.