claude-initial-setup

Review API design for REST conventions and best practices

Incrementally fix build errors one at a time

Create a git commit checkpoint of current progress

Review database schema, queries, and migrations

Systematic debugging process to isolate and fix issues

REST and GraphQL API design and review specialist. Use PROACTIVELY when the user creates or modifies API endpoints, defines route handlers, or designs request/response schemas. Trigger on any API-related code changes, endpoint additions, or when reviewing API contracts.

System design and architecture specialist for scalability, patterns, and technical decision-making. Use PROACTIVELY when the user faces architectural decisions, needs to choose between patterns, or is designing a new system or major module. Trigger on questions about structure, scaling, or tradeoffs.

Build and type error resolution specialist that fixes compilation failures with minimal diffs. Use PROACTIVELY when the build fails, TypeScript reports type errors, or any compilation step produces errors. Trigger immediately on build failures, type check failures, or lint errors.

Code quality, security, and maintainability reviewer. Use PROACTIVELY immediately after writing or modifying any code, before commits on modified files, during pull request reviews, and when refactoring existing code. MUST BE USED after implementing a feature or fix, before creating a commit, when reviewing PR diffs, and after any refactoring session. Trigger on any code change to catch bugs, security issues, mutation violations, and quality regressions early.

Database schema design, query optimization, and migration review specialist. Use PROACTIVELY when the user creates or modifies database schemas, writes complex queries, creates migrations, or works with ORMs. Trigger on any database-related code changes or performance issues involving data access.

Patterns for running independent tasks in parallel using multiple tool calls and Agent invocations. Use when the user has multiple independent operations, asks about fan-out/fan-in, or wants to speed up multi-step workflows.

Patterns for when and how to use Claude Code subagents via the Agent tool. Use when the user needs to delegate research, run parallel investigations, protect the main context window, or asks about subagent types like Explore or Plan.

Patterns for using TaskCreate, TaskUpdate, TaskList, and TaskGet to coordinate multi-step work. Use when the user has a complex project with multiple steps, needs progress tracking, dependency management, or multi-agent task assignment.

Patterns for inter-agent communication including message passing, shared state, event-driven architectures, pub/sub, inbox/outbox, and structured vs freeform messages. Use when the user is building systems where multiple agents need to communicate, share information, coordinate work, or pass data between processing stages.

Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage large amounts of information within limited context windows.

5 hooks across 2 events