Agent Skills › agent-sh/agentsys › perf-theory-tester

perf-theory-tester

GitHub

用于运行受控性能实验以验证假设。遵循规范，确保基线干净，每次仅应用单一变更并执行多次验证，记录指标证据后恢复基线，支持假设的接受、拒绝或不确定判定。

.kiro/skills/perf-theory-tester/SKILL.md agent-sh/agentsys

Trigger Scenarios

需要验证性能优化假设执行受控基准测试实验

Install

npx skills add agent-sh/agentsys --skill perf-theory-tester -g -y

More Options

Non-standard path

npx skills add https://github.com/agent-sh/agentsys/tree/main/.kiro/skills/perf-theory-tester -g -y

Use without installing

npx skills use agent-sh/agentsys@perf-theory-tester

指定 Agent (Claude Code)

npx skills add agent-sh/agentsys --skill perf-theory-tester -a claude-code -g -y

安装 repo 全部 skill

npx skills add agent-sh/agentsys --all -g -y

预览 repo 内 skill

npx skills add agent-sh/agentsys --list

SKILL.md

Frontmatter

{
    "name": "perf-theory-tester",
    "version": "5.1.0",
    "description": "Use when running controlled perf experiments to validate hypotheses."
}

perf-theory-tester

Test hypotheses using controlled experiments.

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

Required Steps

Confirm baseline is clean.
Apply a single change tied to the hypothesis.
Run 2+ validation passes.
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>