Use when running controlled perf experiments to validate hypotheses.
Runs controlled performance experiments to validate hypotheses by applying single changes and measuring deltas.
npx claudepluginhub agent-sh/perfThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Test hypotheses using controlled experiments.
Follow docs/perf-requirements.md as the canonical contract.
hypothesis: <id>
change: <summary>
delta: <metrics>
verdict: accept|reject|inconclusive
evidence:
- command: <benchmark command>
- files: <changed files>
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.