perf-benchmarker
SkillSearchRuns performance benchmarks sequentially with enforced durations to establish baselines and check for regressions.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the perf-benchmarker skill
About this capability
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.
What this skill tells your AI
The instructions your AI receives, as published by composio-community/awesome-claude-plugins in perf/skills/benchmark/SKILL.md and read by ahel’s review.
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.
Signals
- GitHub stars
- 2k
- Forks
- 606
- Last commit
- Jul 2026
Advanced
- Catalog kind
- skill
- Gateway key
perf-benchmarker- Source
- github.com/composio-community/awesome-claude-plugins