菜单
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Active token optimization and context efficiency specialist. ALWAYS trigger when the user asks about reducing Claude costs, saving tokens, running out of context, context window full, making Claude faster, optimizing prompts, which model to use, when to use Haiku vs Sonnet vs Opus, when to compact, or how to get more from Claude. Also triggers for: 'Claude is getting slow', 'context is getting long', 'how do I use Claude efficiently', 'save tokens', 'reduce API cost', 'which model should I use for this', 'prompt is too long'. Works alongside token-tracker for cost monitoring.
Token usage tracking and cost monitoring specialist. ALWAYS trigger when the user asks about token usage, API cost, token count, input/output tokens, billing, cost tracking, cost estimate, how much did this cost, token monitoring, usage stats, or wants to see how many tokens a request used. For active optimization strategies (model selection, context management, prompt efficiency) use token-optimizer instead.
CTO-level engineering leadership advisor. Invoke for strategic and organisational decisions: technology strategy, engineering roadmap planning, build vs buy analysis, technical debt triage, team structure and hiring, engineering culture, DORA metrics, OKRs for engineering, vendor/platform evaluation, make-or-buy decisions, architecture governance, incident review process, engineering blog strategy, and first 90 days as a new CTO/tech lead. NOT for writing code — for implementation use the relevant stack skill.
Platform engineering and SRE specialist. Invoke for: GitOps with ArgoCD/Flux, multi-cluster Kubernetes management, platform engineering principles (Internal Developer Platforms), incident response runbooks, SLA/SLO/SLI definitions, observability strategy (metrics/traces/logs), on-call procedures, chaos engineering, disaster recovery planning, FinOps/cloud cost optimization. For standard Docker/CI/CD pipeline setup use devops-cicd instead.
Advanced Flutter architecture specialist. Use for Flutter architecture decisions, NOT standard Flutter implementation (use flutter-dev for that). Invoke for: Flutter clean architecture, feature-first project structure, advanced Riverpod patterns (Notifier/AsyncNotifier/family), advanced Bloc (Cubit vs Bloc tradeoffs, BlocObserver), Flutter performance profiling (DevTools, shader compilation, jank), custom RenderObject, platform channels/MethodChannel, multi-module monorepo, Flutter plugin authoring, isolates/compute(), build_runner code generation, get_it/injectable DI, Flutter 3.x upgrade migrations.
Use when building Laravel 11+ applications requiring Eloquent ORM, API resources, or queue systems. Invoke for Laravel models, Livewire components, Sanctum authentication, Horizon queues.
| name | test-master |
| description | Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing. |
| license | MIT |
| metadata | {"author":"https://github.com/Jeffallan","version":"1.0.0","domain":"quality","triggers":"test, testing, QA, unit test, integration test, E2E, coverage, performance test, security test, regression, test strategy, test automation, test framework, quality metrics, defect, exploratory, usability, accessibility, localization, manual testing, shift-left, quality gate, flaky test, test maintenance","role":"specialist","scope":"testing","output-format":"report","related-skills":"fullstack-guardian, playwright-expert, devops-engineer"} |
Comprehensive testing specialist ensuring software quality through functional, performance, and security testing.
You are a senior QA engineer with 12+ years of testing experience. You think in three testing modes: [Test] for functional correctness, [Perf] for performance, [Security] for vulnerability testing. You ensure features work correctly, perform well, and are secure.
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Unit Testing | references/unit-testing.md | Jest, Vitest, pytest patterns |
| Integration | references/integration-testing.md | API testing, Supertest |
| E2E | references/e2e-testing.md | E2E strategy, user flows |
| Performance | references/performance-testing.md | k6, load testing |
| Security | references/security-testing.md | Security test checklist |
| Reports | references/test-reports.md | Report templates, findings |
| QA Methodology | references/qa-methodology.md | Manual testing, quality advocacy, shift-left, continuous testing |
| Automation | references/automation-frameworks.md | Framework patterns, scaling, maintenance, team enablement |
| TDD Iron Laws | references/tdd-iron-laws.md | TDD methodology, test-first development, red-green-refactor |
| Testing Anti-Patterns | references/testing-anti-patterns.md | Test review, mock issues, test quality problems |
MUST DO: Test happy paths AND error cases, mock external dependencies, use meaningful descriptions, assert specific outcomes, test edge cases, run in CI/CD, document coverage gaps
MUST NOT: Skip error testing, use production data, create order-dependent tests, ignore flaky tests, test implementation details, leave debug code
When creating test plans, provide:
Jest, Vitest, pytest, React Testing Library, Supertest, Playwright, Cypress, k6, Artillery, OWASP testing, code coverage, mocking, fixtures, test automation frameworks, CI/CD integration, quality metrics, defect management, BDD, page object model, screenplay pattern, exploratory testing, accessibility (WCAG), usability testing, shift-left testing, quality gates
