Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/perf-benchmarker
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.
Passed 22 of 23 test cases with the skill, and 9 of 23 without it.
and 18 more in the full report
15 fixed8 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Execute benchmark for `bin/latency-check` without specifying any time flags in the CLI arguments.
| Checked | Without skill | With skill |
|---|---|---|
| The execution duration defaults to 60 seconds. | Missed | Passed |
The instructions your model reads when the skill loads.
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
test cases passed, vs 9 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.