菜单
Forces the strict Red-Green-Refactor development cycle. Requires writing a failing test and running it in the terminal before writing any implementation code.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/tranhieutt/software_development_department --skill test-driven-development命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Turns real agent failures, repeated prompts, team-specific workflows, and durable project lessons into better SDD skills or memory entries. Use when the user asks to create/update/refine skills, extract reusable lessons, improve skill routing, encode team process, or save patterns for future sessions.
Provides the vendored agent-style v0.3.5 prose rule pack as a portable Claude skill. Use when installing, syncing, applying, or auditing SDD Agent-Style support in another project, or when a style-review workflow needs the bundled rules.
Reviews Markdown prose against the pinned agent-style v0.3.5 rules and optionally writes a polished copy beside the source. Use for specs, ADRs, PR bodies, release notes, and technical docs when prose quality or evidence discipline matters.
基于 SOC 职业分类
正在显示 SKILL.md
| name | test-driven-development |
| type | workflow |
| description | Forces the strict Red-Green-Refactor development cycle. Requires writing a failing test and running it in the terminal before writing any implementation code. |
| argument-hint | [task-description-or-file] |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep, RunCommand |
| context | fork |
| effort | 3 |
| agent | lead-programmer |
| when_to_use | When implementing ANY approved feature, bug fix, algorithmic logic, or when executing atomic tasks generated by the planning phase. |
TDD acts as the ultimate truth verifier. It prevents Agents from blindly inserting implementation code based on assumptions. By strictly enforcing the RED-GREEN-REFACTOR cycle, we guarantee that all code changes are demonstrably functional and logically sound before moving on to the next task.
ABSOLUTE DIRECTIVE: Under NO circumstances are you allowed to write the final implementation logic before a test has explicitly failed in the terminal environment.
*.test.ts, *_test.go, test_*.py) to assert the expected behavior.Your final response to the user MUST contain the evidence of your execution in the following format:
# 🧪 TDD Execution: [Feature/Task Name]
## 🔴 RED Phase Evidence
- **Test added**: `[test_function_name]`
- **Terminal Output**:
```bash
[Insert the failing test output trace here - do not fake this]
[file_name][Insert the passing test output trace here]
Status: ✅ Code verified. Awaiting next command.
---
## Anti-Rationalizations
Be aware of lazy logic that an Agent typically uses to skip testing. If a thought on the left occurs, YOU MUST apply the rebuttal on the right:
| Excuse (Agent's Lazy Rationalization) | Rebuttal & Correct Action |
| :--- | :--- |
| "I'll just write the implementation first because it's super easy, and add the tests after." | **CRITICAL REJECTION.** Writing code before a test guarantees brittle code and untested edge cases. You MUST write the failing test first. No exceptions. |
| "The project doesn't seem to have a test framework set up, so I will just skip TDD and do a console.log." | **REJECTED.** `console.log` is not an automated test. If a test runner (Jest, PyTest, Go test, Vitest) is missing, STOP working and ask the User for permission to install and configure one immediately. |
| "I don't need to run the final terminal command to check if it's green. I can read the logic and I know it works." | **REJECTED.** Code does not exist until the compiler/test-runner proves it exists. You cannot hallucinate terminal outputs. Run the actual command. |
---
## Verification Gates
Do not conclude the turn unless you have:
- [ ] Executed the test runner during the **RED** phase and captured a definitive FAILING state log.
- [ ] Executed the test runner during the **GREEN** phase and captured a PASSING log.
- [ ] Displayed both terminal outputs (Red & Green) as indisputable evidence to the User.
---
## Edge Cases
- **[UI / Canvas Rendering]**: If the task involves purely visual UI CSS updates that cannot be easily unit tested, fallback to structured visual DOM tests (e.g., Testing Library query checks) or explicit manual testing steps listed for the user. Do not skip testing entirely.
---
## Related Skills
- `planning-and-task-breakdown` — TDD is the engine used to execute the tasks planned by this skill.
- `spec-driven-development` — TDD uses the spec as its single source of truth for what tests need to be written.