code-reviewer
Issue-aware code review workflow for working diffs, commits, branches, and pull requests. Use when: reviewing implementation against a Jira ticket, GitHub issue, bug report, feature request, task description, acceptance criteria, or general engineering quality bar. Applies two layers: issue/ticket alignment first, then general engineering quality. Reuses issue-investigator when expected behavior, root cause, or issue context is unclear, and reuses software-engineer for architecture, implementation quality, testability, and production-risk judgment.
Repository SourceNeeds Review
test-automation-engineer
Test automation engineering workflow for choosing the right test level, designing maintainable automated checks, preventing flakiness, integrating tests into CI, and deciding when not to automate. Use when: creating or reviewing automated regression tests, API tests, contract tests, integration tests, UI/e2e tests, fixtures, selectors, or test reporting. Collaborates with software-engineer for code quality and architecture, manual-tester for real scenarios and defects, and product-owner for acceptance criteria and business-critical workflows.
Repository SourceNeeds Review
delivery-planner
Phased delivery planning workflow that turns a single large or multi-day task (feature, refactor, migration, multi-step investigation, multi-PR bug fix) into two persistent artifacts: a concise destination brief and a sequence of small, self-contained execution phases. Use when: a task is too large to fit one agent's working context, when work will span multiple sessions or multiple agents, or when the user wants a written plan before any implementation, refinement, investigation, or test design begins. Each phase is sized so a fresh agent loaded with the destination plus that one phase has enough — and only enough — context to execute it well. Hands phases off to software-engineer, issue-investigator, product-owner, manual-tester, or test-automation-engineer; never re-invokes them itself.
Repository SourceNeeds Review
manual-tester
Manual testing workflow for validating intended behavior, exploring workflows, finding defects, documenting actual vs expected behavior, collecting evidence, and preparing retest guidance. Use when: planning or executing manual tests, validating acceptance criteria, doing exploratory testing, checking edge cases, reporting defects, or identifying regression and automation candidates. Collaborates with product-owner for intended behavior, software-engineer for technical risk areas, and test-automation-engineer for high-value automation candidates.
Repository SourceNeeds Review