stdd-agents

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.

Use when writing acceptance tests or adding scenarios to spec.yaml. Defines Given/When/Then format and acceptance test patterns.

Use when creating or modifying skills. Defines skill file structure, naming conventions, and integration patterns.

Use when creating or updating agent evaluation suites. Defines eval structure, rubrics, and validation patterns.

Use when adding project dependencies. Defines dependency management rules and language-specific patterns.

Use when running pre-commit hooks manually (e.g. before committing or after implementing). This project uses prek, not pre-commit. Defines the correct commands for running hooks.

Use during REFACTOR phase of TDD (after GREEN), when logic is duplicated, or when locality of behavior is violated. Defines search-first workflow, duplication detection, locality principles, and safe refactoring practices.

Use when user requests new features or functionality. Defines complete workflow from specification through testing to implementation.

Use when writing or updating spec.yaml files. Defines requirement format and user story structure.

Use when writing tests or implementing code. Defines RED-GREEN-REFACTOR cycle and test execution workflow.

Use when updating existing pinned dependencies. Defines unpin-resolve-repin workflow with test verification and rollback on failure.

Use when creating git commits. Defines conventional commit format and message structure guidelines.