القائمة
Use during IMPLEMENTATION phase. Write test first, watch it fail, then write minimal code to pass. This is HOW you write code, not WHEN to start a project.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | test-driven-development |
| description | Use during IMPLEMENTATION phase. Write test first, watch it fail, then write minimal code to pass. This is HOW you write code, not WHEN to start a project. |
This is a coding technique - how to write code correctly. It is NOT a project workflow.
Project workflow: brainstorming → /workflow start feature → (implementation)
Coding technique: → test-driven-development
┌─────────────────────────────────────────────┐
│ │
│ RED ──► GREEN ──► REFACTOR ──► (repeat) │
│ │
└─────────────────────────────────────────────┘
RED: Write a failing test
GREEN: Write minimal code to pass
REFACTOR: Clean up while keeping tests green
Before any production code:
func TestUserCanLogin(t *testing.T) {
user := User{Email: "test@example.com"}
token, err := user.Login("password")
assert.NoError(t, err)
assert.NotEmpty(t, token)
}
Run test. Watch it fail. If it passes, you're not testing anything.
Write the simplest code that makes the test pass:
func (u *User) Login(password string) (string, error) {
return "token123", nil
}
Don't anticipate future requirements. Don't over-engineer. Just pass the test.
With tests green, improve the code:
func (u *User) Login(password string) (string, error) {
if !u.verifyPassword(password) {
return "", ErrInvalidPassword
}
return generateToken(u.ID), nil
}
Run tests after each change. Stay green.
| Scenario | Use TDD? |
|---|---|
| New feature | ✅ Yes |
| Bug fix | ✅ Yes - write test that reproduces bug first |
| Refactoring | ✅ Yes - tests prove behavior unchanged |
| Spike/experiment | ❌ No - throwaway code |
| One-liner fix | ⚠️ Use judgment |
| Problem | Solution |
|---|---|
| Don't know how to test | Write wished-for API first, then assertion |
| Test too complicated | Design too complicated - simplify interface |
| Must mock everything | Code too coupled - use dependency injection |
| Test setup huge | Extract helpers, or simplify design |
$ARGUMENTS
Planner-Generator-Evaluator 编排模式。GAN 启发的多 agent 动态编排，通过 ai CLI 控制子 agent 完成复杂任务的拆解-执行-验证闭环。
Code review skill using codex-rs methodology with ai CLI
为任意代码仓库构建结构化知识库（code wiki），并通过 frozen snapshot 机制启动即问即答的 expert agent。 当你需要深入理解一个大型代码仓库、构建可复用的代码知识库、或为其他 agent 提供代码专家服务时使用此技能。
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Orchestrate a real-time alternating debate between two subagents using ai serve/send. Judge controls rounds by prompting each agent in turn.
任务规划与进度追踪。当任务有 5+ 步骤、多文件改动、或长执行链时使用。 核心机制：用 checkbox 列表追踪进度，每完成一步立即更新，利用"重写列表"将完整任务清单重新注入 context。