Development
Command
/test
运行测试并分析结果,失败时提供修复建议
Install
$ npx -y skills add huangjia2019/claude-code-engineering --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/test
Context preview
What this command does when you run it.
运行测试并分析结果,失败时提供修复建议
Command definition
test.mdname: test description: 运行测试并分析结果,失败时提供修复建议
用法:`/test [scope] [options]`
参数
- `scope`(可选):
- `unit` - 只运行单元测试
- `e2e` - 只运行端到端测试
- `all` - 运行全部(默认)
- `options`:
- `--fix` - 尝试自动修复失败的测试
- `--coverage` - 生成覆盖率报告
工作流程
1. 运行指定范围的测试 2. 收集测试结果 3. 对失败的测试:
- 分析失败原因
- 检查是代码 bug 还是测试过时
- 提供修复建议
4. 如果指定了 --fix,尝试自动修复
输出格式
# 测试报告
## 结果
| 指标 | 值 |
|------|------|
| 总计 | 150 |
| 通过 | 147 |
| 失败 | 3 |
| 跳过 | 0 |
| 覆盖率 | 85% |
## 失败的测试
### test_user_creation
**文件**: tests/user.test.ts:42
**错误**: AssertionError: expected 'active' but got 'pending'
**分析**: User 模型的默认状态在 commit abc123 中从 'active' 改为 'pending',但测试未更新。
**建议**: 更新测试以期望 'pending' 状态。
\`\`\`diff
- expect(user.status).toBe('active');
+ expect(user.status).toBe('pending');
\`\`\`
---
*由 team-toolkit 生成* Ships withclaude-code-engineering
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。
Get the whole plugin, auto-invoked
Other commands on claude-code-engineering.
- /commit
Quick git commit with auto-generated or specified message
Open command - /explain
Explain code in simple, beginner-friendly terms
Open command - /log
Show recent git history with summary
Open command - /status
Show git status with helpful context
Open command - /review
对代码进行全面审查,输出结构化报告
Open command - /todo
Add a TODO comment to code with optional priority and assignee
Open command

