mcpField
P
perf-theory-tester

perf-theory-tester

github.com/agent-shTesting & quality1.0k85 installsUpdated today
Repository

About perf-theory-tester

A skill for testing performance hypotheses through controlled experiments. It changes one thing at a time, runs at least two validation passes, records evidence, and restores the baseline before the next experiment.

Key features

  1. 01Confirms a clean baseline
  2. 02Tests one change per experiment
  3. 03Runs at least two validation passes
  4. 04Reverts before the next experiment
  5. 05Records run evidence

Use cases

  1. 01Evaluate a performance hypothesis
  2. 02Compare a single change against a clean baseline

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agent-sh/agentsys --skill perf-theory-tester

After installing, type/perf-theory-testerin Claude Code to confirm it loaded.

Details

From the project README

perf-theory-tester

Test hypotheses using controlled experiments.

Follow docs/perf-requirements.md as the canonical contract.

Required Steps

  1. Confirm baseline is clean.
  2. Apply a single change tied to the hypothesis.
  3. Run 2+ validation passes.
  4. Revert to baseline before the next experiment.

Output Format

hypothesis: <id>
change: <summary>
delta: <metrics>
verdict: accept|reject|inconclusive
evidence:
  - command: <benchmark command>
  - files: <changed files>

Constraints

  • One change per experiment.
  • No parallel benchmarks.
  • Record evidence for each run.

Comments

Markdown supported