---
name: composio-community/perf-benchmarker
source: https://app.decimal.ai/s/composio-community-perf-benchmarker@1/SKILL.md
source_sha256: ac32080718ca
---

# perf-benchmarker

Run sequential benchmarks with strict duration rules.

Follow `docs/perf-requirements.md` as the canonical contract.

## Required Rules

- Benchmarks MUST run sequentially (never parallel).
- Minimum duration: 60s per run (30s only for binary search).
- Warmup: 10s minimum before measurement.
- Re-run anomalies.

## Output Format

```
command: <benchmark command>
duration: <seconds>
warmup: <seconds>
results: <metrics summary>
notes: <anomalies or reruns>
```

## Output Contract

Benchmarks MUST emit a JSON metrics block between markers:

```
PERF_METRICS_START
{"scenarios":{"low":{"latency_ms":120},"high":{"latency_ms":450}}}
PERF_METRICS_END
```

## Constraints

- No short runs unless binary-search phase.
- Do not change code while benchmarking.