Skip to content
Agentmart
Submit a tool

taiyi-test

TaiyiForge 第7阶段 — 测试验证,TEST.md。四端通用。

Skill by Dong90

IndexedMIT★ 859
Write a review

Chalk Labs

Need help deploying taiyi-test?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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-test

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7阶段 — 测试验证,TEST.md。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-test

What's inside

Skill name
taiyi-test
Description
TaiyiForge 第7阶段 — 测试验证,TEST.md。四端通用。
License
MIT
Instructions
230 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# taiyi-test — 测试验证

> 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(`status` → `continue`;legacy:`npx taiyi complete`) | 全程 |
| **GStack** | `browse` — 用于 E2E 浏览器测试和截图验证 | Round 5(E2E 轮) |
| **Superpowers** | `verification-before-completion` — 完成前全量验证 | 完成前 |

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

## 前置门禁(Pre-flight)

### 0.1 上游确认
- dev 阶段已过关(`.taiyi/changes/<slug>/.dev-complete` 存在且 `exitCode: 0`)
- 实现代码已通过 TDD 红→绿循环

### 0.2 Profile 判定

| Profile | TEST.md 要求 |
|---------|------------|
| `full` | 完整覆盖:5 rounds + 6 维回归测试 + 新 file GREP 填空 + Traceability |
| `api/ui` | 同 full |
| `lite` | 简化版:跳过 round 4-5,6 维回归可选 |
| `spike/micro` | 跳过本阶段 |
| `nano` | 跳过 |

### 0.3 前置检查清单
- [ ] .dev-complete 存在且有 GREEN 证据
- [ ] 明确项目的测试命令(npm test / pytest / cargo test 等)

---

## 步骤

### 工件契约

| 层 | 路径 | 职责 |
|----|------|------|
| **语义真源** | `test.json` | Zod(`src/schemas/test.ts`) |
| **生成视图** | `TEST.md` | hbs(`src/templates/test.hbs`) |
| **流程** | 本 Skill | 5 轮 AC 覆盖、6 维回归、Traceability |

**工作流**:实跑测试 → 更新 json 证据 → `scripts/taiyi-forge.sh render <slug> test` → `status` → `continue`。

详见 [`docs/taiyi/artifact-contract.md`](../../docs/taiyi/artifact-contract.md)。

### json 字段(Zod 摘要)

| 字段 | 要求 |
|------|------|
| `title` | 测试计划标题 |
| `test_plan` | ≥1 用例;`id` / `description` / `status`(passed/failed/pending) |
| `unit_framework` / `unit_coverage_target` | 可选 |
| `edge_cases` / `performance_tests` / `security_checks` | 可选 |
| `regression_plan` / `regression_items` | 可选;6 维回归仪表盘内容 |
| `mocking_boundaries` | 可选;哪些层可 mock |
| `summary` / `coverage` | 可选;执行摘要 |
| `evidence` | 有 `passed` 时推荐填真跑命令 |

### 写作指引(填入 json,render 生成 TEST.md)

### 1. TEST.md 全局结构

```
# TEST: <slug 标题>

## Overview
| AC | Round | Type | Status |
|----|-------|------|--------|
```

### 2. 按 AC 的 5 轮测试

每轮一个 table,AC 编号来自 REQUIREMENT.md:

```
### Round 1: 功能正确性(AC 正向)
| AC | PR | Test | Priority | Key Assertions |
|----|----|------|----------|----------------|

### Round 2: 边界条件(AC 负面 + 边值)
| AC | PR | Test | Priority | 边界值 |
|----|----|------|----------|--------|

### Round 3: 错误处理(AC 异常路径)
| AC | PR | Test | Priority | Error Handling |
|----|----|------|----------|---------------|

### Round 4: 集成(跨组件)
| AC | PR | Test | Priority | Endpoint / Interaction |
|----|----|------|----------|-----------------------|

### Round 5: 端到端(关键路径 / 用户流程)
| AC | PR | Test | Priority | Flow |
|----|----|------|----------|------|
```

### 3. 6 维回归测试仪表盘

每个维度用 3 态表示:✅ 通过 / ❌ 未通过 / ⬜ 不适用

```
### Regression Dashboard (pre-landing)

| Dimension | Status | Notes |
|-----------|--------|-------|
| D1 完整功能 | ✅ | 21/21 AC passed |
| D2 边界值 | ✅ | null/empty/long/edge |
| D3 性能 | ⬜ | 无性能要求 |
| D4 并发 | ✅ | 新建不冲突 |
| D5 安全 | ⬜ | 无认证逻辑 |
| D6 回滚 | ✅ | 向下兼容 |
```

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

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get taiyi-test running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying taiyi-test?

CallGet help
Cite this page

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