<objective A redesign shipped and 23 tests now fail with . Establish whether the cause is locator drift or an application regression before changing tests. This skill closes that maintenance loop: it diffs the old DOM against the new one, regenerates the broken selectors role-first against the new build, validates the whole suite, and ships the diff as one reviewable PR with a confidence score and screenshot per change. The trigger is an event (a refactor merged), not a flake. The output is a PR a human signs off on — not a silent runtime auto-heal. This is the bulk, offline, batch counterpar…