Agent Claude Code
Use this agent when the user needs to design, build, or improve API endpoints, implement authentication/authorization, add rate limiting, generate API documentation, or create developer-friendly interfaces. This includes building new FastAPI routes, designing RESTful or GraphQL APIs, implementing OAuth/JWT/API key…
Agent Claude Code
Use this agent when the user needs to set up, fix, or optimize CI/CD pipelines, deployment automation, infrastructure-as-code, or eliminate manual deployment steps. This includes configuring GitHub Actions, GitLab CI, Docker builds, cloud deployments, environment promotion, rollback strategies, and production release…
Agent Claude Code
Use this agent when you need to design, refactor, or restructure code following hexagonal/clean architecture principles. This includes designing new modules, refactoring messy codebases, planning system boundaries, defining ports and adapters, establishing dependency rules, or reviewing architectural decisions for…
Agent Claude Code
Use this agent when you need to optimize slow database queries, design schemas for scale, analyze query execution plans, add or restructure indexes, diagnose database bottlenecks, or plan migrations for growing datasets. This includes situations where queries are taking too long, tables are growing beyond current…
Agent Claude Code
Use this agent when you encounter errors, exceptions, stack traces, unexpected behavior, or failing tests that need systematic investigation and root cause analysis. This includes runtime errors, logic bugs, integration failures, performance issues, and any situation where something isn't working as expected and the…
Agent Claude Code
Use this agent when the user needs to create, extend, or refactor a design system or component library. This includes building new UI components with consistent APIs, establishing design tokens (colors, spacing, typography), creating component variants and composition patterns, writing component documentation…
Agent Claude Code
Use this agent when you want to explore unconventional solutions, experiment with cutting-edge technologies, prototype wild ideas, or evaluate emerging tools and approaches that might benefit the project. This agent thrives on the risky, creative, and experimental work that pushes boundaries.\n\nExamples:\n\n- User…
Agent Claude Code
Use this agent when the user needs to implement LLM-powered features in their application, including but not limited to: chat completions, streaming responses, prompt engineering, embeddings, RAG pipelines, function calling, structured output parsing, token management, cost optimization, or any integration with…
Agent Claude Code
Use this agent when a task is too complex for a single pass and requires decomposition into subtasks, coordination of multiple specialized agents, or synthesis of results from parallel workstreams. This includes large refactoring efforts, multi-file feature implementations, complex debugging sessions requiring…
Agent Claude Code
Use this agent when you need to identify and fix performance bottlenecks, implement caching strategies, optimize slow queries, reduce latency, improve throughput, or when users complain about slow response times. This includes database query optimization, algorithmic improvements, memory usage reduction, caching…
Agent Claude Code
Use this agent when you need to create, debug, or improve end-to-end tests using Playwright. This includes writing new test suites, fixing flaky tests, adding visual regression testing, configuring cross-browser test matrices, setting up CI/CD pipeline integration for tests, or refactoring existing tests for better…
Agent Claude Code
Use this agent when the user wants to elevate the visual quality of their interface, add polish and premium feel to components, implement animations and micro-interactions, or when any UI work would benefit from a design-forward perspective. This includes creating new UI components, redesigning existing ones, adding…
Agent Claude Code
Use this agent when you need a critical evaluation of features, product direction, or build/kill decisions. This includes when the user asks about prioritization, whether to continue or abandon a feature, what to build next, or when they want a strategic review of their codebase and product roadmap.\n\nExamples:\n\n…
Agent Claude Code
Use this agent when writing new Python code, refactoring existing Python code for quality and idiomacy, implementing async/await patterns, designing decorators or context managers, adding type hints, or ensuring PEP compliance. Also use when building scalable Python application components that need to follow best…
Agent Claude Code
Use this agent when code has been written and needs improvement in readability, performance, or maintainability. This includes cleaning up hastily written code, reducing complexity, extracting functions, improving naming, removing duplication, and applying established design patterns. It should be triggered after…
Agent Claude Code
Use this agent when you need to create, expand, or improve test suites for code in the project. This includes writing unit tests, integration tests, and end-to-end tests. Also use this agent when new functionality has been implemented and needs test coverage, when existing tests are insufficient or brittle, or when…
Agent Claude Code
Use this agent when you need to simplify user experiences, reduce complexity in user flows, minimize clicks and interactions, or make interfaces more intuitive and obvious. This includes reviewing UI code for unnecessary complexity, simplifying multi-step processes, auditing navigation patterns, and improving…