测试驱动
tdd-guide
by alirezarezvani
从需求或代码生成测试,结合覆盖率缺口分析和测试质量评分,按 TDD 红绿重构流程推进开发,兼容 Jest、Pytest、JUnit、Vitest 等框架。
想把测试驱动开发真正落地,它能自动生成测试、分析覆盖率,还兼容多种框架,明显减轻补测和重构压力。
安装
claude skill add --url github.com/alirezarezvani/claude-skills/tree/main/engineering-team/tdd-guide文档
TDD Guide
Test-driven development skill for generating tests, analyzing coverage, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, and Vitest.
Table of Contents
Capabilities
| Capability | Description |
|---|---|
| Test Generation | Convert requirements or code into test cases with proper structure |
| Coverage Analysis | Parse LCOV/JSON/XML reports, identify gaps, prioritize fixes |
| TDD Workflow | Guide red-green-refactor cycles with validation |
| Framework Adapters | Generate tests for Jest, Pytest, JUnit, Vitest, Mocha |
| Quality Scoring | Assess test isolation, assertions, naming, detect test smells |
| Fixture Generation | Create realistic test data, mocks, and factories |
Workflows
Generate Tests from Code
- Provide source code (TypeScript, JavaScript, Python, Java)
- Specify target framework (Jest, Pytest, JUnit, Vitest)
- Run
test_generator.pywith requirements - Review generated test stubs
- Validation: Tests compile and cover happy path, error cases, edge cases
Analyze Coverage Gaps
- Generate coverage report from test runner (
npm test -- --coverage) - Run
coverage_analyzer.pyon LCOV/JSON/XML report - Review prioritized gaps (P0/P1/P2)
- Generate missing tests for uncovered paths
- Validation: Coverage meets target threshold (typically 80%+)
TDD New Feature
- Write failing test first (RED)
- Run
tdd_workflow.py --phase redto validate - Implement minimal code to pass (GREEN)
- Run
tdd_workflow.py --phase greento validate - Refactor while keeping tests green (REFACTOR)
- Validation: All tests pass after each cycle
Tools
| Tool | Purpose | Usage |
|---|---|---|
test_generator.py | Generate test cases from code/requirements | python scripts/test_generator.py --input source.py --framework pytest |
coverage_analyzer.py | Parse and analyze coverage reports | python scripts/coverage_analyzer.py --report lcov.info --threshold 80 |
tdd_workflow.py | Guide red-green-refactor cycles | python scripts/tdd_workflow.py --phase red --test test_auth.py |
framework_adapter.py | Convert tests between frameworks | python scripts/framework_adapter.py --from jest --to pytest |
fixture_generator.py | Generate test data and mocks | python scripts/fixture_generator.py --entity User --count 5 |
metrics_calculator.py | Calculate test quality metrics | python scripts/metrics_calculator.py --tests tests/ |
format_detector.py | Detect language and framework | python scripts/format_detector.py --file source.ts |
output_formatter.py | Format output for CLI/desktop/CI | python scripts/output_formatter.py --format markdown |
Input Requirements
For Test Generation:
- Source code (file path or pasted content)
- Target framework (Jest, Pytest, JUnit, Vitest)
- Coverage scope (unit, integration, edge cases)
For Coverage Analysis:
- Coverage report file (LCOV, JSON, or XML format)
- Optional: Source code for context
- Optional: Target threshold percentage
For TDD Workflow:
- Feature requirements or user story
- Current phase (RED, GREEN, REFACTOR)
- Test code and implementation status
Limitations
| Scope | Details |
|---|---|
| Unit test focus | Integration and E2E tests require different patterns |
| Static analysis | Cannot execute tests or measure runtime behavior |
| Language support | Best for TypeScript, JavaScript, Python, Java |
| Report formats | LCOV, JSON, XML only; other formats need conversion |
| Generated tests | Provide scaffolding; require human review for complex logic |
When to use other tools:
- E2E testing: Playwright, Cypress, Selenium
- Performance testing: k6, JMeter, Locust
- Security testing: OWASP ZAP, Burp Suite
相关 Skills
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP 服务
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。