driven▌

Write the test first. Watch it fail. Write minimal code to pass.

Framework for tackling software complexity by modeling code around the business domain. Based on a fundamental truth: the greatest risk in software is not technical failure -- it is building a model that does not reflect how the business actually works.

Dispatch fresh subagents per task with two-stage review for fast, high-quality implementation execution. \n \n Assigns one subagent per task with spec compliance review first, then code quality review, ensuring both correctness and code standards \n Keeps execution in the current session with automatic review loops that re-run when issues are found, eliminating context switches \n Subagents ask clarifying questions before implementation begins and self-review their work before handoff to reviewe

Event-Driven Architecture patterns for Spring Boot using domain events, transactional listeners, and Kafka messaging. \n \n Covers domain event design, ApplicationEventPublisher integration, and @TransactionalEventListener configuration for local event handling with AFTER_COMMIT phase guarantees \n Supports distributed messaging via Kafka and Spring Cloud Stream for inter-service communication with functional consumer beans \n Implements the transactional outbox pattern for reliable event publis

You're building an automated QA pipeline that tests a Python application end-to-end — running it the same way a real user would, with real inputs — then scoring the outputs using evaluators and producing pass/fail results via pixie test.

Write failing tests first, then minimal code to pass, then refactor while keeping tests green. \n \n Follows the red-green-refactor cycle: write one failing test, verify it fails correctly, implement minimal code to pass, verify all tests pass, then refactor safely \n Requires watching each test fail before writing implementation code; tests that pass immediately prove nothing about correctness \n Applies to all new features, bug fixes, refactoring, and behavior changes; code written before test

Compile-time state validation through type encoding, eliminating invalid states at the type level. \n \n Covers six core patterns: newtype for type-safe primitives, type state for state machines, PhantomData for variance tracking, marker traits for capability flags, builders for gradual construction, and sealed traits for closed impl sets \n Emphasizes asking \"can the compiler catch this?\" before adding runtime validation, with decision guides mapping common needs to appropriate patterns \n In

Provides expertise in designing and implementing event-driven architectures. Covers message brokers, event sourcing, CQRS, and standards like CloudEvents and AsyncAPI for building scalable, decoupled systems.

expert-driven

Model complex business domains with entities, value objects, and bounded contexts.