sumo-qa-triaging-test-failureslisted

# Triaging test failures Separate *why it failed* from *how to fix it*: the same red bar can mean a product regression, a wrong test, stale fixture data, a broken environment, an order/timing race, or a flaky external service, each needing a different response. Patch before naming the cause and a test bug gets "fixed" in the product, or a real regression is buried under a rerun. The output is a **cause classification plus the smallest next verification step**, never a fix first. **Announce at the start of EVERY turn while this skill is active** — triage, isolation-step, rerun-with-hypothesis, hand-off, and refusal turns all open with: *"Triaging this failure before any fix."* A turn that skips the announce has left the triage discipline. ## Output discipline (mandatory) Inherits the global discipline from `using-sumo-qa`: no internal taxonomy labels (say *"the test's own expectation is stale"*, not *"Cause: test_bug"*), findings not framing, one question per turn. <HARD-GATE> Do NOT classify a failure you have not seen. Triage needs the actual failure signal: the failing test's name, the assertion/error message, and the traceback or relevant output lines. A test name alone, or "it's flaky", is not enough. If the output is absent or too thin to ground a cause, STOP: say what you have, name exactly what you still need (the failing assertion text and the traceback OR the relevant output lines), ask for it, and do nothing else. Never invent a traceback, line number, or error