Stats
Actions
Tags
From perf
Enforces sequential performance benchmarks with 60s min runs (30s binary search), 10s warmup, JSON metrics output, and anomaly reruns. For baselines and regressions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/perf:benchmarkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run sequential benchmarks with strict duration rules.
Run sequential benchmarks with strict duration rules.
Follow docs/perf-requirements.md as the canonical contract.
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
npx claudepluginhub composiohq/awesome-claude-plugins --plugin perfUse when a backpressured loop needs to run benchmarks on a performance-sensitive project and decide whether a change is a regression, an improvement, or a wash — per-iteration sanity checks and the full pre-done run.
Creates and runs reliable benchmarks to measure code change impacts on performance, including latency, throughput. Supports Node.js (vitest, tinybench), Python (pytest-benchmark), frontend (Lighthouse CI), with warmup, stats.
Designs structured benchmarks comparing algorithms, models, or implementations with metrics, test cases, hardware context, and tradeoff analysis to produce reproducible performance reports.