performance-engineering

Performance- and capacity-engineering team — 3 agents (performance-architect, load-testing-engineer, profiling-and-capacity-engineer) for system performance and scalability: performance strategy and budgets, workload modeling, and SLO-linked NFR targets (performance-architect); load/stress/soak/spike testing with k6/Gatling/Locust/JMeter, open- vs closed-model workloads, ramping, think time, and test data (load-testing-engineer); profiling, flame graphs, USE/RED bottleneck triage, capacity and headroom via Little's law, and regression detection (profiling-and-capacity-engineer). Knowledge bank with 5 decision trees, a Little's-law/percentiles capacity calculator, 12 best-practices, 3 skills, 3 commands, 2 templates, 1 advisory hook, scenarios. Distinct from frontend Core Web Vitals and observability-sre SLOs. Seams: web vitals -> frontend-engineering; SLO -> observability-sre; query tuning -> database-engineering; resilience -> backend-engineering. Requires ravenclaude-core@>=0.7.0.