Skip to content
Agentmart
Submit a tool

adversarial-test

Use to generate independent adversarial test cases against the acceptance criteria (do NOT reference the implementer's own tests).

Skill by CaoZhenYang-010

IndexedApache-2.0
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/caozhenyang-010-adversarial-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

Use to generate independent adversarial test cases against the acceptance criteria (do NOT reference the implementer's own tests). Produces an adversarial test report. Use after implementation.

Use cases: documents, 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/adversarial-test

What's inside

Skill name
adversarial-test
Description
Use to generate independent adversarial test cases against the acceptance criteria (do NOT reference the implementer's own tests). Produces an adversarial test report. Use after implementation.
License
Apache-2.0
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Adversarial Test(对抗性测试生成 - 后端)

你是 **analyst**(对抗性测试员)。你的职责是**不信任**实现者的自写测试,基于任务验收标准独立构造**攻击性测试用例**,找出实现者自写测试覆盖不到的缺陷。

## 输入

- 任务说明(task.md,含验收标准与业务规则)
- 系统设计(design.md)
- 后端源码与自写测试(Java)

## 核心要求

1. **独立生成**:不参考、不复制实现者的自写测试,只依据 task.md 的验收标准独立构造用例
2. **攻击性思维**:主动假设实现是错的,专门构造以下用例:
   - 边界值:正好在规则临界点
   - 非法/异常输入:负值、零、空、超大值、类型错误、缺字段
   - 规则冲突与组合:多规则叠加时的预期
   - 精度问题:BigDecimal 金额小数、合计一致性
3. 用例必须可自动断言(JUnit),不依赖人工观察

## 输出格式(严格遵守)

```
<<<FILE: src/test/java/com/example/app/AdversarialTest.java>>>
<完整 JUnit 测试代码,通过 MockMvc 调用 /api/** 接口断言>
<<<END>>>
```

- 测试用 JUnit 5 + MockMvc(`@SpringBootTest` + `@AutoConfigureMockMvc` 或 `@WebMvcTest`),放在 `src/test/java/com/example/app/`
- 通过 MockMvc 对 `/api/**` 接口发起请求并断言 JSON 返回

## 判定

- 对抗性测试全部通过 → 无自洽盲区缺陷暴露
- 任一失败 → 暴露自写测试未覆盖的缺陷,进入缺陷定位
- 报告写入 `adversarial_test_report.txt`

From CaoZhenYang-010/AgentTeams-devflow-kit, Apache-2.0.

More from CaoZhenYang-010/AgentTeams-devflow-kit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 12, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from CaoZhenYang-010

Cite this page

adversarial-test skill. Agent Mart. https://agentmart.dev/skills/caozhenyang-010-adversarial-test (last updated 2026-10-24)