benchmarklisted

# Benchmark (Laravel) Measure real performance baselines for a Laravel app and detect regressions by comparing before/after a change. This skill **measures** — it produces honest numbers and verdicts. For design guidance on hot paths, defer to `@skills/latency-critical-systems/SKILL.md`; to act on a regression with an optimization loop, hand off to `@skills/benchmark-optimization-loop/SKILL.md`. ## Constraints - Apply `@rules/sql/optimalize.mdc` when reading or interpreting query timing (N+1, index usage, SARGable filters). - Apply `@rules/code-testing/general.mdc` if you add or touch any benchmark test (Pest, no `describe()`). - Measure, never guess — every number must be a real readback from a running system, command, or tool. - Control for noise: separate warm vs cold, run repeats (≥5), report median plus p95, fix one variable at a time. - Same machine, same dataset, same config for before and after — note the environment so a teammate can reproduce. - Keep secrets and private payloads out of baseline JSON and logs. ## Use when - You need a performance baseline for a page, API route, build step, or query. - A change (PR, dependency bump, query rewrite, config change) may have caused a regression and you must prove it either way. - You are comparing two implementations or stack options on the same workload. - Someone claims "it's faster/slower" without a measured before/after. Do not use for live design advice (use `latency-critical-systems`) or for diagnosing one Teles