Use when writing or optimizing performance-critical code — batch processing, concurrent/parallel systems, async pipelines, GPU computing, scientific computing, or any code where throughput, latency, or resource efficiency matters. Also trigger when the user mentions "performance", "optimize", "scale", "concurrency", "make it faster", "speed up", "throughput", "latency", "GPU", "memory bound", "CPU bound", "checkpoint", "resume", "断点续传", "中断恢复", "idempotent", or asks about resource usage or making long-running tasks resumable. This skill encodes universal performance principles distilled from real systems — resource-aware parallelism, async pipeline design, GPU acceleration, interruption-tolerant computation, lock-free data structures, and progressive validation.
2026-05-13