ComposioHQ / perf-benchmarker
Install for your project team
Run this command in your project directory to install the skill for your entire team:
mkdir -p .claude/skills/perf-benchmarker && curl -L -o skill.zip "https://fastmcp.me/Skills/Download/3499" && unzip -o skill.zip -d .claude/skills/perf-benchmarker && rm skill.zipProject Skills
This skill will be saved in .claude/skills/perf-benchmarker/ and checked into git. All team members will have access to it automatically.
Important: Please verify the skill by reviewing its instructions before using it.
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.
0 views
0 installs
Skill Content
---
name: perf-benchmarker
description: "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."
version: 1.0.0
argument-hint: "<command> [duration]"
---
# 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.