一键导入
test-driven-development
Use when implementing a feature, bugfix, refactor, or behavior change where a failing test can be written before production code.
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。
菜单
Use when implementing a feature, bugfix, refactor, or behavior change where a failing test can be written before production code.
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。
基于 SOC 职业分类
MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Legacy compatibility alias for task-router-lite. Keeps older codex-max references working while using a thin Phase PLAN routing model.
Thin Phase PLAN router for codex-max. Select at most one primary execution skill and one optional secondary skill from the installed local skill surface.
Use when a significant technical decision should be recorded with context, alternatives, and consequences so the reasoning survives beyond the current session.
| name | test-driven-development |
| description | Use when implementing a feature, bugfix, refactor, or behavior change where a failing test can be written before production code. |
| risk | safe |
| source | codex-max |
| origin | Antigravity-adapted |
| date_added | 2026-04-19 |
Use TDD when behavior can be captured in a test before implementation. The discipline is simple:
If you did not watch the new test fail first, you do not know whether it truly verifies the intended behavior.
Write one focused failing test that demonstrates the intended behavior.
Requirements:
Run the test and confirm:
Write the minimum production code required to make the test pass. Do not overbuild. Do not add speculative abstractions.
Run the test again and confirm it passes. Then run the relevant surrounding checks so you do not break adjacent behavior.
Only after green:
Then re-run tests to confirm behavior remains intact.
lint-and-validate after code changesverification-before-completion before claiming successbrainstorming first until the behavior is clear enough to testWhen this skill is active, report progress in terms of:
brainstorming — clarify behavior before implementation when the request is still vaguelint-and-validate — validate after code changesverification-before-completion — require fresh evidence before completion claimssystematic-debugging — use when the problem is diagnosis-first rather than implementation-first