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.
npx -y skills add affaan-m/ecc --skill recsys-pipeline-architect --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
kubesphere/kubesphere
supercent-io/skills-template