Spec Driven Test

用规约驱动测试(specification-based testing)的方法对 web 应用做端到端测试。当用户说要"测试一下这个功能"、"检查一下这个功能的完整性"、"对这个项目做 E2E 测试"、"用 agent 测这个 web 应用"或者直接提到 spec-driven-test / specification-based testing 时使用这个 skill。也适用于用户希望基于代码自动生成测试规约和测试用例,然后通过浏览器自动化执行测试的场景。即使用户没有明确说"规约"或"测试用例"这些词,只要他想系统地、自动化地测试一个 web 项目的某个功能,都应该使用这个 skill。

32 stars 3 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Loveforwa/spec-test.skill --skill spec-driven-test
Manual install
git clone --depth 1 https://github.com/Loveforwa/spec-test.skill.git /tmp/spec-test.skill
mkdir -p ~/.claude/skills
cp -r /tmp/spec-test.skill/zh ~/.claude/skills/spec-driven-test

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Spec-Driven Test

用规约驱动测试的方法对 web 应用做端到端测试。
整个流程由三个 agent 协作完成:**Cartographer** 读代码生成规约和用例,**Inspector** 用方法论审用例,**Operator** 在真实浏览器执行测试。两道人类 review 把关质量。

---

## 按需加载导航(执行 skill 前先读这段)

这个 skill 是文件型 skill,你**不需要一次性读完所有 reference 文件**——按角色和阶段读对应章节,可大幅节省 token。

**确定你的角色,只读对应主文件**:

- **Cartographer 角色** → 读 `references/cartographer.md`(分阶段读章节,详见该文件顶部 TOC)
  + 阶段 0 / 1 / 2 / 2.5 / 3,只读当前阶段章节
  + 阶段 1 末尾识别匹配的场景模式后,**只读匹配的** `references/scenarios/<对应文件>.md`,不要全读
  + 写规约时读 `templates/spec-template.md`,写用例时读 `templates/test-cases-template.md`
- **Inspector 角色** → 读 `references/inspector.md`(分步骤读章节,详见该文件顶部 TOC)
  + 工作流程 §1 / 1.5 / 1.6 / 1.7 / 1.8 / 2 / 2.5 / 3 / 4
  + 选用方法论时**只读匹配的** `references/methodologies/<对应文件>.md`,不要全读
  + 输出格式时读 `templates/judge-output-template.md`
- **Operator 角色** → 读 `references/operator.md`,产出报告时读 `templates/execution-report-template.md`

**人类 review 阶段** → 读 `references/human-review-checklists.md`

**读 SKILL.md 本身只是入口**——它是导航,不是详细规则。
真正的工作规则在每个 agent 的 reference 文件里,**按需读取**才能控制 token。

---

## 整体流程
Read the full skill on GitHub

Details

Skill name
spec-driven-test
Path
zh/SKILL.md
Repo updated
24 May 2026

FAQ

What does the Spec Driven Test skill do?

用规约驱动测试(specification-based testing)的方法对 web 应用做端到端测试。当用户说要"测试一下这个功能"、"检查一下这个功能的完整性"、"对这个项目做 E2E 测试"、"用 agent 测这个 web 应用"或者直接提到 spec-driven-test / specification-based testing 时使用这个 skill。也适用于用户希望基于代码自动生成测试规约和测试用例,然后通过浏览器自动化执行测试的场景。即使用户没有明确说"规约"或"测试用例"这些词,只要他想系统地、自动化地测试一个 web 项目的某个功能,都应该使用这个 skill。

How do I install the Spec Driven Test skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Loveforwa/spec-test.skill --skill spec-driven-test. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Spec Driven Test popular?

It lives in Loveforwa/spec-test.skill, which has 32 GitHub stars and 3 forks.

Related skills

Spec Driven Test

32

Loveforwa/spec-test.skill

Use specification-based testing methodology for end-to-end testing of web applications. Use this skill when users request "test this feature", "check this feature completeness", "do E2E testing on this project", "test this web app with an agent", or directly mention spec-driven-test / specification-based testing. This skill also applies to scenarios where users want to automatically generate test specs and test cases from code, then execute tests through browser automation. Even if users don't explicitly mention "spec" or "test case", if they want to systematically and automatically test a spe

Testing & QA

Uw Unity Feature Scaffold

47

devdavv/unity-ai-workflow

Create a complete feature module with folder structure, Assembly Definition (.asmdef), test assembly, and namespace. Use when adding a new feature, system, or module to a Unity project. Triggers on requests like "create a new feature", "scaffold a module", "add a combat system", "I need a health system", "set up inventory", "create a new module for X", "add a new system", "new feature folder", or any task requiring new folders, assemblies, or namespaces for a gameplay feature — even when the user just names a system they want to build from scratch. Reads ProjectConfig.yaml for folder_strategy

Testing & QA

Uw Unity Test Runner

47

devdavv/unity-ai-workflow

Generates EditMode and PlayMode tests using NUnit, mapped from GDD Gherkin scenarios. Use when writing tests, validating features, ensuring code quality, or verifying behavior after changes. Triggers on requests like "write tests for this", "test the health system", "add unit tests", "verify this works", "add PlayMode tests", "test this feature", "write integration tests", "make sure this doesn't break", "add test coverage", "TDD this feature", or any task involving test creation, test-driven development, or quality assurance. Maps Given/When/Then scenarios directly to test methods using NUnit

Testing & QA

Injection Testing

49

mn-youssef/security-skills

Use when dynamically testing whether untrusted input reaches an interpreter — SQL/NoSQL injection (incl. blind/time-based), OS command injection, server-side template injection (SSTI), XXE, LDAP/XPath, and CRLF/header injection. Confirms on a running app what security-code-audit finds in source.

Testing & QA

Testing and Quality

49

dynamics365ninja/d365fo-cli

Write and run D365FO tests — SysTestCase unit tests, the ATL acceptance library, and the offline gates (`validate xpp`, `validate references`, `lint`) that catch defects before a build. Invoke when the user asks how to test X++, add a unit test, assert on behaviour, or check code quality without a VM.

Testing & QA26

File Upload and Ssrf

49

mn-youssef/security-skills

Use when testing file-upload handling, server-side request forgery (SSRF), and insecure deserialization — upload bypasses (type/extension/content, polyglots, path traversal), SSRF to cloud metadata and internal services, and unsafe deserialization sinks. On apps you own or are authorized to test.

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.