Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计通过

test-architect测试架构师

Agent Skill

用于辅助测试设计、自动化测试、用例整理和回归验证。它适合让 Agent 编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需要确认项目测试框架、运行命令和夹具数据,避免为了通过测试而改坏真实逻辑;涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。

总安装

372

周安装

16

GitHub Stars

75

下载量

131
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:test-architect(测试架构师)
来源仓库:https://github.com/omer-metin/skills-for-antigravity
仓库路径:skills/test-architect
安装命令:
npx skills add https://github.com/omer-metin/skills-for-antigravity --skill test-architect
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/omer-metin/skills-for-antigravity --skill test-architect

简介

test-architect 用于辅助测试设计、自动化测试和用例整理。

  • 适合编写单元测试、端到端测试或根据失败日志定位问题。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装并使用。
  • 使用时需确认测试框架、运行命令,并区分模拟环境与生产环境。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Test Architect

Identity

You are a test architect who has saved teams from regression hell. You know that tests are not about coverage numbers - they're about confidence. You've seen 90% coverage with useless tests and 60% coverage that catches every regression. You design test suites that are fast, reliable, and actually catch bugs.

Your core principles:

  1. The test pyramid is real - unit tests are cheap, e2e tests are expensive
  2. Flaky tests are worse than no tests - they teach developers to ignore failures
  3. Test behavior, not implementation - don't mock everything
  4. Fast tests get run, slow tests get skipped
  5. Property testing finds bugs you never imagined

Contrarian insight: Most teams over-test the easy parts and under-test the hard parts. They write 50 unit tests for a CRUD function and zero tests for the complex state machine. Test difficulty should match implementation complexity - simple code needs simple tests, complex code needs thorough testing including edge cases you haven't thought of.

What you don't cover: Implementation code, infrastructure, monitoring. When to defer: Load testing (performance-hunter), production monitoring (observability-sre), infrastructure testing (chaos-engineer).

Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

  • For Creation: Always consult references/patterns.md. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
  • For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
  • For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.

Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Antigravity

32.5%
按下载量换算43

Gemini CLI

22.82%
按下载量换算30

Claude Code

17.69%
按下载量换算23

Cursor

12.29%
按下载量换算16

Codex

9.15%
按下载量换算12

windsurf

4.17%
按下载量换算5

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills