tdd-workflows-tdd-cycle

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Use this skill when

适用本技能的场景

Working on tdd workflows tdd cycle tasks or workflows
Needing guidance, best practices, or checklists for tdd workflows tdd cycle

处理TDD工作流、TDD循环相关任务或工作流程时
需要TDD工作流、TDD循环相关的指导、最佳实践或检查清单时

Do not use this skill when

不适用本技能的场景

The task is unrelated to tdd workflows tdd cycle
You need a different domain or tool outside this scope

任务与TDD工作流、TDD循环无关时
需要该范围之外的其他领域或工具时

Instructions

操作说明

Clarify goals, constraints, and required inputs.
Apply relevant best practices and validate outcomes.
Provide actionable steps and verification.
If detailed examples are required, open
```
resources/implementation-playbook.md
```
.

Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-green-refactor discipline:

[Extended thinking: This workflow enforces test-first development through coordinated agent orchestration. Each phase of the TDD cycle is strictly enforced with fail-first verification, incremental implementation, and continuous refactoring. The workflow supports both single test and test suite approaches with configurable coverage thresholds.]

明确目标、约束条件和所需输入。
应用相关最佳实践并验证结果。
提供可执行的步骤和验证方式。
若需要详细示例，请打开
```
resources/implementation-playbook.md
```
。

严格遵循红-绿-重构（RED-GREEN-REFACTOR）准则，执行完整的测试驱动开发（TDD）工作流：

[拓展思考：该工作流通过协调Agent编排，强制要求先编写测试再进行开发。TDD循环的每个阶段都通过“先失败验证”、“增量实现”和“持续重构”严格执行。工作流支持单测试和测试套件两种方式，并可配置覆盖率阈值。]

Configuration

配置

Coverage Thresholds

覆盖率阈值

Minimum line coverage: 80%
Minimum branch coverage: 75%
Critical path coverage: 100%

最低行覆盖率：80%
最低分支覆盖率：75%
关键路径覆盖率：100%

Refactoring Triggers

重构触发条件

Cyclomatic complexity > 10
Method length > 20 lines
Class length > 200 lines
Duplicate code blocks > 3 lines

圈复杂度 > 10
方法长度 > 20行
类长度 > 200行
重复代码块 > 3行

Phase 1: Test Specification and Design

阶段1：测试规格与设计

1. Requirements Analysis

1. 需求分析

Use Task tool with subagent_type="comprehensive-review::architect-review"
Prompt: "Analyze requirements for: $ARGUMENTS. Define acceptance criteria, identify edge cases, and create test scenarios. Output a comprehensive test specification."
Output: Test specification, acceptance criteria, edge case matrix
Validation: Ensure all requirements have corresponding test scenarios

使用Task工具，设置subagent_type="comprehensive-review::architect-review"
提示词：“分析以下需求：$ARGUMENTS。定义验收标准，识别边缘情况，创建测试场景。输出完整的测试规格说明。”
输出：测试规格说明、验收标准、边缘情况矩阵
验证：确保所有需求都有对应的测试场景

2. Test Architecture Design

2. 测试架构设计

Use Task tool with subagent_type="unit-testing::test-automator"
Prompt: "Design test architecture for: $ARGUMENTS based on test specification. Define test structure, fixtures, mocks, and test data strategy. Ensure testability and maintainability."
Output: Test architecture, fixture design, mock strategy
Validation: Architecture supports isolated, fast, reliable tests

使用Task工具，设置subagent_type="unit-testing::test-automator"
提示词：“基于测试规格说明，为$ARGUMENTS设计测试架构。定义测试结构、测试夹具、模拟对象（mocks）和测试数据策略。确保可测试性和可维护性。”
输出：测试架构、夹具设计、模拟策略
验证：架构支持隔离、快速、可靠的测试

Phase 2: RED - Write Failing Tests

阶段2：红（RED）- 编写失败的测试

3. Write Unit Tests (Failing)

3. 编写单元测试（预期失败）

Use Task tool with subagent_type="unit-testing::test-automator"
Prompt: "Write FAILING unit tests for: $ARGUMENTS. Tests must fail initially. Include edge cases, error scenarios, and happy paths. DO NOT implement production code."
Output: Failing unit tests, test documentation
CRITICAL: Verify all tests fail with expected error messages

使用Task工具，设置subagent_type="unit-testing::test-automator"
提示词：“为$ARGUMENTS编写预期失败的单元测试。测试必须初始执行失败。包含边缘情况、错误场景和正常流程。请勿实现生产代码。”
输出：预期失败的单元测试、测试文档
关键要求：验证所有测试都能输出预期错误信息并失败

4. Verify Test Failure

4. 验证测试失败状态

Use Task tool with subagent_type="tdd-workflows::code-reviewer"
Prompt: "Verify that all tests for: $ARGUMENTS are failing correctly. Ensure failures are for the right reasons (missing implementation, not test errors). Confirm no false positives."
Output: Test failure verification report
GATE: Do not proceed until all tests fail appropriately

使用Task工具，设置subagent_type="tdd-workflows::code-reviewer"
提示词：“验证$ARGUMENTS的所有测试是否正确失败。确保失败原因合理（缺少实现，而非测试本身错误）。确认没有假阳性结果。”
输出：测试失败验证报告
关卡要求：所有测试未按预期失败前，不得进入下一阶段

Phase 3: GREEN - Make Tests Pass

阶段3：绿（GREEN）- 使测试通过

5. Minimal Implementation

5. 最小化实现

Use Task tool with subagent_type="backend-development::backend-architect"
Prompt: "Implement MINIMAL code to make tests pass for: $ARGUMENTS. Focus only on making tests green. Do not add extra features or optimizations. Keep it simple."
Output: Minimal working implementation
Constraint: No code beyond what's needed to pass tests

使用Task工具，设置subagent_type="backend-development::backend-architect"
提示词：“编写最小化代码使$ARGUMENTS的测试通过。仅专注于让测试变绿。不要添加额外功能或优化。保持代码简洁。”
输出：可运行的最小化实现代码
约束：代码不得超出通过测试所需的范围

6. Verify Test Success

6. 验证测试通过状态

Use Task tool with subagent_type="unit-testing::test-automator"
Prompt: "Run all tests for: $ARGUMENTS and verify they pass. Check test coverage metrics. Ensure no tests were accidentally broken."
Output: Test execution report, coverage metrics
GATE: All tests must pass before proceeding

使用Task工具，设置subagent_type="unit-testing::test-automator"
提示词：“运行$ARGUMENTS的所有测试并验证是否通过。检查测试覆盖率指标。确保没有测试意外被破坏。”
输出：测试执行报告、覆盖率指标
关卡要求：所有测试通过后，方可进入下一阶段

Phase 4: REFACTOR - Improve Code Quality

阶段4：重构（REFACTOR）- 提升代码质量

7. Code Refactoring

7. 代码重构

Use Task tool with subagent_type="tdd-workflows::code-reviewer"
Prompt: "Refactor implementation for: $ARGUMENTS while keeping tests green. Apply SOLID principles, remove duplication, improve naming, and optimize performance. Run tests after each refactoring."
Output: Refactored code, refactoring report
Constraint: Tests must remain green throughout

使用Task工具，设置subagent_type="tdd-workflows::code-reviewer"
提示词：“在保持测试通过的前提下，重构$ARGUMENTS的实现代码。应用SOLID原则，消除重复代码，优化命名，提升性能。每次重构后运行测试。”
输出：重构后的代码、重构报告
约束：重构全程需保持测试通过

8. Test Refactoring

8. 测试代码重构

Use Task tool with subagent_type="unit-testing::test-automator"
Prompt: "Refactor tests for: $ARGUMENTS. Remove test duplication, improve test names, extract common fixtures, and enhance test readability. Ensure tests still provide same coverage."
Output: Refactored tests, improved test structure
Validation: Coverage metrics unchanged or improved

使用Task工具，设置subagent_type="unit-testing::test-automator"
提示词：“重构$ARGUMENTS的测试代码。消除测试重复，优化测试命名，提取通用夹具，提升测试可读性。确保测试覆盖率保持不变。”
输出：重构后的测试代码、优化后的测试结构
验证：覆盖率指标未下降或有所提升

Phase 5: Integration and System Tests

阶段5：集成与系统测试

9. Write Integration Tests (Failing First)

9. 编写集成测试（先失败）

Use Task tool with subagent_type="unit-testing::test-automator"
Prompt: "Write FAILING integration tests for: $ARGUMENTS. Test component interactions, API contracts, and data flow. Tests must fail initially."
Output: Failing integration tests
Validation: Tests fail due to missing integration logic

使用Task工具，设置subagent_type="unit-testing::test-automator"
提示词：“为$ARGUMENTS编写预期失败的集成测试。测试组件交互、API契约和数据流。测试必须初始执行失败。”
输出：预期失败的集成测试
验证：测试因缺少集成逻辑而失败

10. Implement Integration

10. 实现集成逻辑

Use Task tool with subagent_type="backend-development::backend-architect"
Prompt: "Implement integration code for: $ARGUMENTS to make integration tests pass. Focus on component interaction and data flow."
Output: Integration implementation
Validation: All integration tests pass

使用Task工具，设置subagent_type="backend-development::backend-architect"
提示词：“实现$ARGUMENTS的集成代码，使集成测试通过。专注于组件交互和数据流。”
输出：集成实现代码
验证：所有集成测试通过

Phase 6: Continuous Improvement Cycle

阶段6：持续改进循环

11. Performance and Edge Case Tests

11. 性能与边缘场景测试

Use Task tool with subagent_type="unit-testing::test-automator"
Prompt: "Add performance tests and additional edge case tests for: $ARGUMENTS. Include stress tests, boundary tests, and error recovery tests."
Output: Extended test suite
Metric: Increased test coverage and scenario coverage

使用Task工具，设置subagent_type="unit-testing::test-automator"
提示词：“为$ARGUMENTS添加性能测试和额外边缘场景测试。包含压力测试、边界测试和错误恢复测试。”
输出：扩展后的测试套件
指标：提升测试覆盖率和场景覆盖率

12. Final Code Review

12. 最终代码评审

Use Task tool with subagent_type="comprehensive-review::architect-review"
Prompt: "Perform comprehensive review of: $ARGUMENTS. Verify TDD process was followed, check code quality, test quality, and coverage. Suggest improvements."
Output: Review report, improvement suggestions
Action: Implement critical suggestions while maintaining green tests

使用Task工具，设置subagent_type="comprehensive-review::architect-review"
提示词：“对$ARGUMENTS进行全面评审。验证是否遵循TDD流程，检查代码质量、测试质量和覆盖率。提出改进建议。”
输出：评审报告、改进建议
操作：在保持测试通过的前提下，实施关键改进建议

Incremental Development Mode

增量开发模式

For test-by-test development:

Write ONE failing test
Make ONLY that test pass
Refactor if needed
Repeat for next test

Use this approach by adding

--incremental

flag to focus on one test at a time.

针对逐测试用例开发：

编写一个预期失败的测试用例
仅实现使该测试用例通过的代码
如有需要进行重构
为下一个测试用例重复上述步骤

添加

--incremental

参数即可启用该模式，专注于逐个处理测试用例。

Test Suite Mode

测试套件模式

For comprehensive test suite development:

Write ALL tests for a feature/module (failing)
Implement code to pass ALL tests
Refactor entire module
Add integration tests

Use this approach by adding

--suite

flag for batch test development.

针对全面测试套件开发：

为某个功能/模块编写所有预期失败的测试用例
实现代码使所有测试用例通过
重构整个模块
添加集成测试

添加

--suite

参数即可启用该模式，进行批量测试开发。

Validation Checkpoints

验证检查点

RED Phase Validation

红阶段验证

All tests written before implementation
All tests fail with meaningful error messages
Test failures are due to missing implementation
No test passes accidentally

所有测试在实现前编写完成
所有测试输出有意义的错误信息并失败
测试失败原因是缺少实现
无测试意外通过

GREEN Phase Validation

绿阶段验证

All tests pass
No extra code beyond test requirements
Coverage meets minimum thresholds
No test was modified to make it pass

所有测试通过
无超出测试要求的额外代码
覆盖率达到最低阈值
未修改测试用例使其通过

REFACTOR Phase Validation

重构阶段验证

Coverage Reports

覆盖率报告

Generate coverage reports after each phase:

Line coverage
Branch coverage
Function coverage
Statement coverage

每个阶段后生成覆盖率报告：

行覆盖率
分支覆盖率
函数覆盖率
语句覆盖率

Failure Recovery

故障恢复

If TDD discipline is broken:

STOP immediately
Identify which phase was violated
Rollback to last valid state
Resume from correct phase
Document lesson learned

若违反TDD准则：

立即停止当前操作
确定违反了哪个阶段的要求
回滚到上一个有效状态
从正确的阶段恢复执行
记录经验教训

TDD Metrics Tracking

TDD指标跟踪

Track and report:

Time in each phase (Red/Green/Refactor)
Number of test-implementation cycles
Coverage progression
Refactoring frequency
Defect escape rate

跟踪并报告以下指标：

每个阶段的耗时（红/绿/重构）
测试-实现循环次数
覆盖率提升进度
重构频率
缺陷逃逸率

Anti-Patterns to Avoid

需避免的反模式

Writing implementation before tests
Writing tests that already pass
Skipping the refactor phase
Writing multiple features without tests
Modifying tests to make them pass
Ignoring failing tests
Writing tests after implementation

先实现代码再编写测试
编写原本就会通过的测试
跳过重构阶段
未编写测试就开发多个功能
修改测试用例使其通过
忽略失败的测试
实现代码后再编写测试

Success Criteria

成功标准

100% of code written test-first
All tests pass continuously
Coverage exceeds thresholds
Code complexity within limits
Zero defects in covered code
Clear test documentation
Fast test execution (< 5 seconds for unit tests)

100%的代码遵循“先测试后编写”原则
所有测试持续保持通过状态
覆盖率超过阈值
代码复杂度在限制范围内
已覆盖的代码零缺陷
测试文档清晰明了
测试执行速度快（单元测试耗时<5秒）

Notes

注意事项

Enforce strict RED-GREEN-REFACTOR discipline
Each phase must be completed before moving to next
Tests are the specification
If a test is hard to write, the design needs improvement
Refactoring is NOT optional
Keep test execution fast
Tests should be independent and isolated

TDD implementation for: $ARGUMENTS

严格执行红-绿-重构（RED-GREEN-REFACTOR）准则
每个阶段必须完成后才能进入下一个阶段
测试即规格说明
若某个测试难以编写，说明设计需要优化
重构不是可选步骤
保持测试执行速度
测试应独立且相互隔离

针对$ARGUMENTS的TDD实现