recsys-system-design
Design an industrial recommendation system or subsystem with explicit scale, latency, freshness, consistency, availability, privacy, cost, degradation, observability, and rollout constraints.
SKILL.md.agents/skills/recsys-system-design/SKILL.md
GitHubRecommendation system design
- Resolve objective, QPS, P99, corpus and feature scale, freshness, consistency, runtime, deployment, availability, privacy, and cost. Ask only when alternatives materially differ.
- Run
python3 tools/recsys_agent.py design "<system>" key=value ...and close all relevant missing constraints. - Search the released PDFs and read the cited pages.
- Reuse a runnable template;
[MOCK]dependencies are teaching substitutes. - Produce request/data flows, interfaces, capacity and latency budgets, version contract, overload/degradation, metrics, rollout, rollback, and validation.
- Separate
本书依据,工程实现,验证, and待业务确认.