tdd-test-writer
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseTDD Test Writer
TDD测试编写器
Use this skill to complete the RED phase of TDD: define behavior with tests first, verify they fail for the right reason, then hand off implementation with objective pass criteria.
使用本技能完成TDD的红色阶段:优先通过测试定义行为,验证测试因正确原因失败,随后交付带有客观通过标准的实现任务。
When To Use
适用场景
Use this skill when the user asks for:
- test-first development
- TDD / RED-GREEN-REFACTOR workflow
- writing tests that implementation agents must satisfy
- bugfixes that need regression tests before code changes
当用户有以下需求时使用本技能:
- 测试先行开发
- TDD / 红-绿-重构工作流
- 编写实现Agent必须满足的测试
- 代码变更前需要编写回归测试的bug修复任务
Required Rules
强制规则
- Do not modify production code while running this skill.
- Use subagent role for RED-phase test authoring whenever available.
tdd_test_writer - Write behavior-focused tests, not placeholders.
- Every new/updated test must fail before handoff.
- Failures must come from missing or incorrect production behavior, not broken tests.
- Prefer deterministic, targeted test commands over full-suite runs when possible.
- For bugfix tasks, add a regression test that captures the reported failure mode.
- 运行本技能时请勿修改生产代码。
- 只要可用,就使用子Agent角色完成红色阶段的测试编写工作。
tdd_test_writer - 编写聚焦行为的测试,而非占位符。
- 所有新增/更新的测试在交付前必须处于失败状态。
- 失败必须源于生产行为缺失或不正确,而非测试本身存在问题。
- 尽可能使用确定性的、针对性的测试命令,而非运行全量测试套件。
- 对于bug修复任务,新增回归测试来复现上报的失败模式。
Workflow
工作流程
1. Define Behavior Contract
1. 定义行为契约
- Convert user request into explicit acceptance criteria.
- Identify happy path, edge cases, and negative-path expectations.
- If requirements are ambiguous, record lines in output.
ASSUMPTION:
- 将用户需求转换为明确的验收标准。
- 识别正常路径、边界场景和异常路径的预期结果。
- 如果需求存在歧义,在输出中记录行说明假设内容。
ASSUMPTION:
2. Delegate Test Authoring To tdd_test_writer
tdd_test_writer2. 委派测试编写任务给tdd_test_writer
tdd_test_writer- Spawn a subagent with task scope, target files, and acceptance criteria.
tdd_test_writer - Require the subagent to write/update tests only (no production code changes).
- Require command output proving RED-state failure for the new tests.
- If is unavailable, continue directly and note
tdd_test_writer.FALLBACK: tdd_test_writer unavailable
- 生成子Agent,提供任务范围、目标文件和验收标准。
tdd_test_writer - 要求子Agent仅编写/更新测试(不得修改生产代码)。
- 要求子Agent提供命令输出,证明新增测试处于红色失败状态。
- 如果无法使用,直接继续后续流程并备注
tdd_test_writer。FALLBACK: tdd_test_writer unavailable
3. Discover Existing Test Conventions
3. 对齐现有测试规范
- Detect framework and runner from the repo (for example ,
vitest,jest,pytest,go test).cargo test - Follow existing directory, naming, and fixture conventions.
- Reuse existing helpers instead of introducing duplicate test utilities.
- 从代码库中检测使用的测试框架和运行器(例如、
vitest、jest、pytest、go test)。cargo test - 遵循现有的目录、命名和测试夹具规范。
- 复用现有辅助工具,不要引入重复的测试工具函数。
4. Author RED-Phase Tests
4. 编写红色阶段测试
- Create or update test files that encode the behavior contract.
- Keep tests small and intention-revealing (clear names and assertions).
- Include at least one negative-path assertion where applicable.
- Avoid network/time randomness; mock or fixture external systems.
- 创建或更新测试文件,编码实现行为契约。
- 保持测试精简且意图清晰(命名和断言明确)。
- 适用场景下至少包含一个异常路径的断言。
- 避免网络/时间随机性;对外部系统进行mock或使用测试夹具。
5. Verify RED State
5. 验证红色状态
- Run the narrowest command that executes the new tests.
- Confirm they fail for the expected behavioral gap.
- If failure is caused by test syntax/setup, fix tests and rerun.
- 运行执行新增测试所需的最小范围命令。
- 确认测试因预期的行为缺口失败。
- 如果失败是由测试语法/配置导致,修复测试后重新运行。
6. Produce Implementation Handoff
6. 生成实现交付物
Return a block that implementation agents must follow. The handoff must include:
- subagent used () or explicit fallback reason
tdd_test_writer - exact test files created/updated
- exact verification command(s)
- short failure summary proving RED state
- immutable test constraint (do not edit tests unless requirement changes)
- pass criteria that define task completion
返回一个实现Agent必须遵循的代码块。交付物必须包含:
- 所用的子Agent()或明确的降级原因
tdd_test_writer - 新增/更新的具体测试文件路径
- 具体的验证命令
- 证明红色状态的简短失败摘要
- 不可变的测试约束(除非需求变更,否则不得修改测试)
- 定义任务完成的通过标准
Required Output Format
要求输出格式
markdown
TDD RED PHASE COMPLETEmarkdown
TDD RED PHASE COMPLETEAuthoring Mode
Authoring Mode
- Subagent: tdd_test_writer
- Fallback: [only if subagent unavailable]
- Subagent: tdd_test_writer
- Fallback: [only if subagent unavailable]
Test Files
Test Files
- [path]
- [path]
Verification
Verification
- Command: [exact command]
- Result: FAIL (expected)
- Failure reason: [1-2 lines tied to missing behavior]
- Command: [exact command]
- Result: FAIL (expected)
- Failure reason: [1-2 lines tied to missing behavior]
Implementation Contract (for next agent)
Implementation Contract (for next agent)
- Do not modify these tests: [paths]
- Implement production changes only in: [paths or modules]
- Completion gate: [exact command] passes with no test weakening.
- Run broader safety check: [secondary command]
- Return evidence: changed files + command output summary.
- Do not modify these tests: [paths]
- Implement production changes only in: [paths or modules]
- Completion gate: [exact command] passes with no test weakening.
- Run broader safety check: [secondary command]
- Return evidence: changed files + command output summary.
Assumptions
Assumptions
- ASSUMPTION: [only if needed]
undefined- ASSUMPTION: [only if needed]
undefinedQuality Bar
质量标准
- Tests fail before implementation and are reproducible locally.
- Assertions are specific enough to prevent false positives.
- Regression coverage is present for bugfix-driven tasks.
- Handoff is precise enough that another agent can execute without clarifications.
- 测试在实现完成前处于失败状态,且本地可复现。
- 断言足够精准,可避免误报。
- 对于bug修复驱动的任务,包含回归测试覆盖。
- 交付内容足够精准,其他Agent无需额外澄清即可执行。