Token导航 LogoToken导航TokenDH.com
AI 工具只读github未标认证来源可访问clear审计通过

test-driven-development测试驱动开发

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

1,035

周安装

44

GitHub Stars

8

下载量

363
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-driven-development(测试驱动开发)
来源仓库:https://github.com/bbeierle12/skill-mcp-claude
仓库路径:skills/test-driven-development
安装命令:
npx skills add https://github.com/bbeierle12/skill-mcp-claude --skill test-driven-development
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/bbeierle12/skill-mcp-claude --skill test-driven-development

简介

遵循红绿重构循环强制先写失败测试再实现功能逻辑。

  • 适用于单元测试、端到端用例设计及回归验证流程管理。
  • 确保每次提交只包含通过的最小代码变更,杜绝冗余实现。
  • 安装后可在 Codex、Claude、Cursor、Gemini CLI 中强制执行 TDD 规则。
  • 涉及浏览器或外部服务时需区分模拟环境与真实生产行为差异。

SKILL.md

Test-Driven Development

The Iron Law of TDD

Write code before test? Delete it. Start over.

This is not negotiable. This is not optional. You cannot rationalize your way out of this.

The RED-GREEN-REFACTOR Cycle

1. RED - Write a Failing Test First

  • Write the smallest test that fails for the right reason
  • The test should fail because the feature doesn't exist yet
  • Run the test and verify it fails

2. GREEN - Make It Pass (Minimum Code)

  • Write the minimum code to make the test pass
  • Don't write more than necessary
  • Don't optimize yet
  • Don't refactor yet

3. REFACTOR - Improve the Code

  • Now you can clean up
  • Remove duplication
  • Improve naming
  • Extract methods/functions
  • All tests must still pass after refactoring

Forbidden Rationalizations

If you catch yourself thinking ANY of these, STOP:

  • "This is just a simple function" → WRONG. Simple functions need tests.
  • "I'll write tests after" → WRONG. That's not TDD.
  • "Let me just get it working first" → WRONG. Tests first.
  • "This doesn't need a test" → WRONG. Everything needs tests.
  • "I'll test it manually" → WRONG. Write automated tests.
  • "The test is obvious" → WRONG. Write it anyway.
  • "I'm just exploring" → WRONG. Explore with tests.

Test Quality Guidelines

Good Tests Are:

  • Fast - Tests should run in milliseconds
  • Isolated - No dependencies between tests
  • Repeatable - Same result every time
  • Self-validating - Pass or fail, no interpretation
  • Timely - Written before the code

Test Structure (Arrange-Act-Assert):

// Arrange - Set up the test conditions
const input = createTestInput();

// Act - Execute the code under test
const result = functionUnderTest(input);

// Assert - Verify the expected outcome
expect(result).toBe(expectedValue);

When to Use This Skill

  • Starting any new feature
  • Fixing any bug (write a test that reproduces the bug first)
  • Refactoring existing code (ensure tests exist first)
  • Any code change that could break existing functionality

YAGNI (You Aren't Gonna Need It)

Don't write code you don't need yet:

  • No speculative features
  • No "just in case" abstractions
  • No premature optimization
  • Build what's needed now, nothing more

DRY (Don't Repeat Yourself)

But only during REFACTOR phase:

  • First make it work (GREEN)
  • Then make it right (REFACTOR)
  • Duplication is okay temporarily
  • Remove it during refactor

Commit Strategy

  • Commit after each GREEN
  • Commit after each REFACTOR
  • Small, frequent commits
  • Each commit should pass all tests

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

OpenCode

29.71%
按下载量换算108

Claude Code

24.73%
按下载量换算90

Antigravity

15.94%
按下载量换算58

windsurf

11.38%
按下载量换算41

Gemini CLI

7.82%
按下载量换算28

Codex

3.51%
按下载量换算13

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