Skip to content
Agentmart
Submit a tool

taiyi-dev

TaiyiForge 第6阶段 — TDD开发执行。四端通用。

Skill by Dong90

IndexedMIT★ 859
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dong90-taiyi-dev

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

TaiyiForge 第6阶段 — TDD开发执行。四端通用。

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/taiyi-dev

What's inside

Skill name
taiyi-dev
Description
TaiyiForge 第6阶段 — TDD开发执行。四端通用。
License
MIT
Instructions
254 lines in SKILL.md · view on GitHub

Before installing

  • Instructions read files in your home folder (~/.ssh, ~/.aws…)

Files (1)

  • SKILL.md

SKILL.md (first lines)

# taiyi-dev — TDD 开发

> 进入本阶段前请优先读 `.taiyi/changes/<slug>/PHASE-CONTEXT.md`(~500 tokens),不要全量加载上游工件。

## 框架集成

本阶段使用以下框架:

| 框架 | 用途 | 何时加载 |
|------|------|---------|
| **Harness** | 阶段门禁与推进(`apply` 清单 · `status` → `continue`;legacy:`npx taiyi apply/complete`) | 全程 |
| **Superpowers** | `test-driven-development` — TDD 红→绿→重构循环 | 步骤 1(强制) |
| **Superpowers** | `systematic-debugging` — 测试失败时诊断 | 异常处理时 |
| **Superpowers** | `verification-before-completion` — 完成前验证 | 完成前 |

**GStack / OpenSpec / Spec-Kit / OMO** 在本阶段不涉及。

## 前置门禁(Pre-flight)

### 0.1 上游确认
- task 阶段已过关(`engineTruth` 确认)
- TASK.md 中无未解决的 `[depends_on: ?]`
- 当前 git 分支干净(无未提交的临时修改)

### 0.2 Profile 判定

| Profile | 开发要求 |
|---------|---------|
| `full` | 全 TDD(红→绿→重构)+ 全部 0.x 检查 + self-review(R1-R11) |
| `api/ui` | 同 full |
| `lite` | TDD 可选,0.x 检查中的 0.5(破坏性变更)必须执行 |
| `micro/spike` | 仅 0.1(grep 已有抽象)+ 0.5(破坏性变更) |
| `nano` | TDD 可选,0.5 必须执行 |

### 0.3 前置检查清单
- [ ] task 阶段已过关
- [ ] todo 列表已就绪(每个 T0X 一个 todo 项)
- [ ] 理解 TASK.md 的 verify 标准和 write_files 边界

---

## 步骤

**dev 无 json 视图**:过关证据为 `.dev-complete`(`command` + `exitCode: 0`)。实现边界仍来自 `task.json` / 渲染后的 `TASK.md`。

### 0. 上下文加载

先读 PHASE-CONTEXT.md 确认范围,再读 TASK.md 拿到任务清单。**不写不在 TASK 中的功能。**

### 0.1 沿用已有抽象 grep(强制)

写新代码前 grep 同类模式,贴入 SUMMARY:

```
# grep -rn "class.*Adapter" src/  → 找到 LLMAdapter 抽象基类
# grep -rn "from.*middleware" src/ → 找到 LoggingMiddleware 模式
```

**不 grep 直接写 = 制造重复抽象**。

### 0.2 扫 LESSONS(强制)

```
grep -rn "LESSON" .taiyi/changes/<slug>/ 2>/dev/null || echo "无 LESSONS"
```

对 active 条目声明差异。相同方案已记录失败教训 → **停手,选不同方案**。

### 0.3 UI 任务额外检查

确认 UI-DESIGN.md 存在。颜色/字体/间距从 UI-DESIGN.md 派生。**禁硬编码 hex**。

### 0.4 Schema 变更检查

生成可逆迁移(up + down)。grep 确认数据库当前结构,避免迁移冲突。

### 0.5 破坏性变更高门槛

命中任一 → **STOP,展示引用分析结果,等用户明确指示**:
- 删除 ≥ 5 行代码
- 修改公共导出(export function / export class)
- 改 API 端点签名(path / method / request body)
- 改 DB Schema 列名或类型

---

### 1. TDD 红→绿→重构(强制)

<tdd_enforcement>
STEP A — WRITE FAILING TEST ONLY
  - Write the test that defines the expected behavior. Do NOT touch business logic yet.
  - The test MUST be a real assertion (not console.log, not TODO).

STEP B — CAPTURE RED EVIDENCE(MANDATORY)
  - Run the test script. Capture the RED (failing) terminal output.
  - PASTE the failing output into .dev-complete as evidence under "RED: <test-id>".
  - DO NOT proceed to step C without RED evidence.

STEP C — IMPLEMENT GREEN
  - Write the minimum production code to make the test pass.
  - Re-run the exact same test. Capture GREEN (passing) output.
  - Paste GREEN output into .dev-complete alongside the RED evidence.

STEP D — REFACTOR
  - Optional cleanup. Tests MUST stay green.

<three_case_rule>
最低测试覆盖 (强制) — 每个新函数必须 ≥ 3 个 test case:
  1. happy case — 正常输入返回预期输出
  2. edge case — 边界输入 (空/null/0/最大值/Unicode/...)
  3. error case — 异常输入 (类型错/null/无效格式) 走 error 处理分支

禁止单 case 提交. 三个 case 缺一即视为覆盖不足.

反模式 (禁止):
  - 只测 happy path 不测边界
  - console.log / TODO 代替断言
  - 把 3 个 case 写成"复用同一断言"的循环 (虽然技术正确但语义模糊)
</three_case_rule>

From Dong90/oh-my-taiyiforge, MIT.

More from Dong90/oh-my-taiyiforge

Signals

Stars
859
Forks
22
Open issues
1
Last commit (this folder)
Jul 11, 2026 (3 months ago)
Last release
Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Dong90

Cite this page

taiyi-dev skill. Agent Mart. https://agentmart.dev/skills/dong90-taiyi-dev (last updated 2026-10-24)