Fix Tests
技能 已验证 活跃Systematically fix all failing tests after business logic changes or refactoring
To ensure code stability and maintainability by systematically resolving all failing tests after changes.
功能
- Automated test failure identification
- Orchestrated agent-based test fixing
- Preserves test intent and business logic
- Iterative fixing process for remaining failures
- Supports user-specified focus on specific tests or modules
使用场景
- Automatically fix broken tests after a refactoring session.
- Ensure all regression tests pass after a dependency update.
- Systematically resolve test failures following a major code change.
非目标
- Writing new business logic or features.
- Refactoring code that is not directly related to test failures.
- Adding new tests where none existed previously.
工作流
- Read available 'sadd' skill if present.
- Discover test infrastructure (test commands, project structure).
- Run all tests to establish a baseline.
- Identify all failing test files.
- Verify single test execution can be reliably run.
- Launch 'developer' agents in parallel for each failing test file.
- Provide agents with context, target file, guidance, resources, command, and goal to fix tests.
- Verify all fixes by running the full test suite again.
- Iterate by launching new agents for remaining failures until 100% pass rate.
实践
- Test-Driven Development
- Code Quality
- Automation
先决条件
- A project with a test suite discoverable by standard commands (e.g., via package.json or README.md)
- Agents capable of understanding and executing code changes (e.g., provided by the Claude Code environment)
安装
请先添加 Marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install tdd@context-engineering-kit质量评分
已验证类似扩展
使用我的浏览器
100当工作依赖于用户实时浏览器会话或可见的渲染状态，而不是静态抓取时使用，尤其是在浏览器调试上下文或 DevTools 选择的元素或请求、登录仪表板或 CMS 流程、localhost 应用、上传、下载、媒体检查、DOM 或 iframe 检查、Shadow DOM，或看起来像软 404、身份验证墙、反机器人检查或速率限制的浏览器故障时。
Telegram Crabbox E2e Proof
100Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
Openclaw Testing
100Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
Agent Browser
100AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。
Moyu (摸鱼)
100감지된 과잉 엔지니어링 패턴: (1) 사용자가 명시적으로 요청하지 않은 코드나 파일을 수정할 때 (2) 요청되지 않은 새로운 추상화 계층(클래스, 인터페이스, 팩토리, 래퍼)을 생성할 때 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 주석을 추가할 때 (4) 요청되지 않은 새로운 종속성을 도입할 때 (5) 최소 편집 대신 파일 전체를 다시 작성할 때 (6) diff 범위가 사용자의 요청을 명백히 초과할 때 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만"과 같은 신호를 보낼 때 (8) 발생할 수 없는 시나리오에 대한 오류 처리, 유효성 검사, 방어적 코드를 추가할 때 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성할 때
Cleanup Cycles
100Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — "find circular imports", "fix dependency cycles", "untangle our module graph", "why is madge complaining".