Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.
Runs sequential performance benchmarks with strict duration rules and mandatory warmup periods.
npx claudepluginhub agent-sh/perfThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Run sequential benchmarks with strict duration rules.
Follow docs/perf-requirements.md as the canonical contract.
const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const command = args.find(a => !a.match(/^\d+$/)) || '';
const duration = parseInt(args.find(a => a.match(/^\d+$/)) || '60', 10);
command: <benchmark command>
duration: <seconds>
warmup: <seconds>
results: <metrics summary>
notes: <anomalies or reruns>
Benchmarks MUST emit a JSON metrics block between markers:
PERF_METRICS_START
{"scenarios":{"low":{"latency_ms":120},"high":{"latency_ms":450}}}
PERF_METRICS_END
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.