llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
performance
Production-grade performance testing skill with k6, JMeter, load testing, stress testing, and performance optimization guidance
performance
>
performance-testing
Performance testing guidance including load testing with k6, locust, and artillery, benchmarking strategies, profiling techniques, metrics analysis, performance budgets, and bottleneck identification. Use when setting up performance tests, analyzing system behavior under load, or optimizing application performance. Trigger keywords: performance testing, load testing, k6, locust, artillery, benchmarking, profiling, latency, throughput, performance budget, bottleneck, stress testing, scalability testing.
testing-strategy-builder
Use this skill when creating comprehensive testing strategies for applications. Provides test planning templates, coverage targets, test case structures, and guidance for unit, integration, E2E, and performance testing. Ensures robust quality assurance across the development lifecycle.
performance-testing
Design and execute performance tests to measure response times, throughput, and resource utilization. Use for performance test, load test, JMeter, k6, benchmark, latency testing, and scalability analysis.
