affaan-m avatar

Recsys Pipeline Architect

If you're building any system that needs to pick "the top K items" for a user,feeds, search reranking, RAG retrieval, notification triage,this walks you through the six-stage pipeline pattern that xAI open-sourced from their For You algorithm: Source, Hydrator, Filter, Scorer, Selector, SideEffect. It's not the original code, just a structured reimplementation that generates runnable scaffolds in TypeScript, Go, or Python. The upstream repo ships three working examples with passing tests. The real value is forcing you to think through the trade-offs: single score versus multi-action prediction, when to filter before scoring, and why side effects must never block your response. Treat it as opinionated plumbing around whatever ML model you're actually using.

skills.sh installs
5.4K
GitHub stars
300.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add affaan-m/ecc --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. It encodes the six-stage pattern — Source → Hydrator → Filter → Scorer → Selector → SideEffect — popularized by xAI's open-sourced For You algorithm (Apache 2.0). This skill is an independent reimplementation of the pattern (MIT) — no code copied from the original.

Upstream: https://github.com/mturac/recsys-pipeline-architect

When to Use

  • User wants to build any system that picks "the top K items for a user/context"
  • User asks "how should I rank X" or describes a feed/personalization problem
  • User has a scoring function and needs the pipeline plumbing around it
  • User wants to migrate from a single relevance score to multi-action prediction with tunable weights
  • User is wrapping an LLM/ML scorer and needs filters, hydrators, side-effects, and a runnable scaffold in their stack (TypeScript / Go / Python)
  • Triggers: "recommendation system", "feed algorithm", "ranking pipeline", "for you feed", "candidate pipeline", "content recommender", "pipeline architecture for recsys", "RAG retrieval reranker"

Sponsors

Details

Repository
github.com/affaan-m/ecc
Categories
DevOps & CI/CD, Code Review & Quality, AI & Agent Building, Automation & Workflows, Marketing & SEO, Sales & Marketing, Design & UI/UX
First seen
Jul 14, 2026

More from affaan-m/ecc

All 263
1forcedotcom avatardx-devops-test-failures-analyzeforcedotcom/sf-skillsAnalyzes DevOps Center test failures and Code Analyzer violations in plain language — failure category, offending file/class/method/line, rule violated, fix dir5.1Kskills.sh installs
2hashicorp avatarterraform-search-importhashicorp/agent-skillsDiscover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure unde5.1Kskills.sh installs
3recoupable avatarrecoup-platform-build-osrecoupable/skillsScaffold and run a label's self-managing "music-company OS" inside its own git repo — the full label-intelligence workspace (folders, a self-managing CLAUDE.md 5.1Kskills.sh installs
4boristane avatarlogging-best-practicesboristane/agent-skillslogging best practices5Kskills.sh installs
5affaan-m avatarkubernetes-patternsaffaan-m/eccKubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments.4.9Kskills.sh installs
6affaan-m avatarorch-build-mvpaffaan-m/eccOrchestrate bootstrapping a working MVP from a design or spec document — ingest the doc, plan thin vertical slices, scaffold the first end-to-end slice, then TD4.8Kskills.sh installs