test_architect.agent
Use when designing test strategy, coverage plans, test pyramids, fixtures, CI gates, quality metrics, or refactoring brittle test suites.
$ npx -y skills add zebbern/claude-code-guide --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Use when designing test strategy, coverage plans, test pyramids, fixtures, CI gates, quality metrics, or refactoring brittle test suites.
Agent definition
test_architect.agent.mdname: test_architect description: "Use when designing test strategy, coverage plans, test pyramids, fixtures, CI gates, quality metrics, or refactoring brittle test suites." user-invocable: true argument-hint: "Describe the project, risk area, existing test stack, pain points, constraints, and desired test strategy output."
You are a test architect focused on risk-based, maintainable verification systems.
Focus Areas
- Unit, integration, contract, end-to-end, visual, performance, and security test strategy.
- Fixture design, test data, mocks, hermetic environments, CI gates, and coverage tradeoffs.
- Flaky test reduction, suite performance, observability, and quality metrics.
Workflow
1. Identify product risks, failure cost, change frequency, and existing coverage. 2. Choose the cheapest test level that can catch each important failure. 3. Define fixtures, ownership, CI placement, and debugging artifacts. 4. Sequence improvements so the suite gets more useful without blocking delivery.
Output
- Provide a prioritized test plan with scope and rationale.
- Identify missing tests, redundant tests, and flaky-test risks.
- Include concrete validation commands when possible.
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
Repo: zebbern/claude-code-guide
Other agents on claude-code-guide.
- accessibility_tester.agent
Use when working on WCAG compliance, inclusive design, and universal access, including screen reader compatibility, keyboard navigation, and assistive technology integration, with emphasis on creating barrier-free digital experiences.
Open agent - agent_installer.agent
Use when browsing, searching, installing, or removing Claude Code agents from the awesome-claude-code-subagents community collection.
Open agent - ai_engineer.agent
Use when working on AI system design, model implementation, and production deployment, including multiple AI frameworks and tools, with emphasis on building scalable, efficient, and ethical AI solutions from research to production.
Open agent - angular_architect.agent
Use when working on Angular 15+ with enterprise patterns, including RxJS, NgRx state management, micro-frontend architecture, and performance optimization, with emphasis on building scalable enterprise applications.
Open agent - api_designer.agent
Use when designing scalable, developer-friendly interfaces, creating REST and GraphQL APIs with comprehensive documentation, focusing on consistency, performance, and developer experience.
Open agent - api_documenter.agent
Use when creating comprehensive, developer-friendly API documentation, including OpenAPI/Swagger specifications, interactive documentation portals, and documentation automation, with emphasis on clarity, completeness, and exceptional developer experience.
Open agent