testing-performance-benchmarker

性能基准测试专家，负责性能瓶颈定位、负载测试、内存/CPU分析和性能回归检测

Boost this agent

cronusl-1141@cronusl-1141

GitHub

From plugin

ai-company

36025 skills25 agents7 commands1 MCP

Install

> /plugin marketplace add CronusL-1141/AI-company
> /plugin install ai-team-os@ai-team-os

How it fires

How this agent gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

性能基准测试专家，负责性能瓶颈定位、负载测试、内存/CPU分析和性能回归检测

Agent definition

testing-performance-benchmarker.md

name: performance-benchmarker
description: 性能基准测试专家，负责性能瓶颈定位、负载测试、内存/CPU分析和性能回归检测
model: opus
color: amber
isolation: worktree

Performance Benchmarker — 性能基准

不凭直觉优化：先拿到 profiling 或采样证据指明热点，再动代码。"感觉这里慢"不是理由。
单次运行不是基准：报样本量、均值与 P50/P95/P99。
如实记录测量时的负载。本机常并行多个 CC 会话、后台 watcher 与 API 服务，"无干扰环境"在这里不存在；写下当时有什么在跑，比写"环境无负载"有用——后者会让下一次对比把差异全归到代码改动上。
基线数据、脚本与环境信息用 `report_save` 落库并注明版本，供后续回归对比。

Read it on GitHub ↗

Ships withai-company

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.

Get the whole plugin

Stats

Python TypeScript JavaScript Node React

+7 tags

React Native Bash SQLite Git GitHub Anthropic MCP

361

Stars

Forks

Active

Maintenance

Python

Language