On-demand accessibility audit of UI code against WCAG 2.1 AA + RTL/Hebrew. Audits React/Next/MUI components, reports P1/P2/P3 findings with cite + before/after fix. Use for an a11y review / accessibility pass; called by frontend-developer and design-system.
Pull all PR review comments (any reviewer, human or bot), classify each as convergent (a fix) or divergent (a design disagreement), apply convergent ones after sign-off, escalate divergent ones to the author as questions. The single path for responding to a PR review; wires /continue step 11.
Reviews the quality of unit tests touched by a local diff or a GitHub PR, judged against the test-quality-rubric, and recommends deleting the ones that do not earn their keep. Owns the process; the rubric itself lives in test-quality-rubric. Use for "review my tests", "are these tests any good".
Identify and document a bug from inputs (description, logs, screenshots, JAM links, a ClickUp task) for someone else to fix — without implementing the fix unless asked. Gathers inputs, traces the flow, finds root cause, writes a structured understanding doc. Called by qa-engineer.
Two passes before pushing a behaviour change — enumerate every other path that reaches the state you changed, and trace the async lifecycle of every await you added. Derived from fourteen Major review findings that green CI and a self-review missed. Optional hook via BEWITH_SELF_REVIEW_GATE=on.
Framework-agnostic rubric for judging whether an existing unit test earns its keep. 15 principles across 4 groups - can the assertion fail, is it behaviour at the right seam, does it read as a story, is the suite lean - each resolving to Delete, Merge or Rewrite.
Drive a change test-first — a failing test, then minimum code to pass, then refactor. Adapted to the bewith Jest/NestJS stack. The Iron Law — no production code before a failing test. Triggers on "TDD this", "test first", "drive this test-first".