From perf
Guides controlled performance experiments to validate hypotheses on code changes. Enforces clean baselines, single changes, multiple runs, evidence recording, and verdict output.
npx claudepluginhub agent-sh/perf --plugin perfThis skill uses the workspace's default tool permissions.
Test hypotheses using controlled experiments.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
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>