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.
SkillScore95Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/12/2026
What it changes
Passed 20 of 21 test cases with the skill, and 6 of 21 without it.
Without skill27%
With skill95%
Checks it passed that the model alone missed
Forbids source code modifications while benchmarking.
Mandates running benchmarks sequentially instead of in parallel.
Mandates sequential benchmark execution rather than parallel runs.
and 23 more in the full report
15 fixed6 passed either way1 still failing0 broke
Pass-rate lift
+68 pp
Tokens
-30%
Agent turns
0%
Response time
-50%
Model gemini-3.6-flashMeasured 8/12/2026v121 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
Please output performance results for our search service using XML tags <metrics> and </metrics> around the JSON payload, along with command, duration, warmup, results, and notes fields.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses PERF_METRICS_START and PERF_METRICS_END markers rather than XML tags.
Missed
Passed
Formats run information with command, duration, warmup, results, and notes keys.
Passed
Passed
case-16 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md37 linessingle file
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).