← ClaudeAtlas

sumo-qa-answering-testing-questionlisted

Use when the user asks a generic testing question — "how do I test this?", "what should I check for X?" — that doesn't fit a more specific QA skill. Cites a principle or technique from the loaded catalogue rather than producing generic advice.
sumithr/sumo-qa · ★ 4 · Testing & QA · score 70
Install: claude install-skill sumithr/sumo-qa
# Answering a testing question **Announce at start:** *"Answering with a cited principle and technique."* ## Before answering — check fit (Redirect discipline) FIRST step. Redirect — don't answer with catalogue principles — when the question is really: - *"Are my PR tests good enough / safe to merge / review my changes"* → `sumo-qa-reviewing-before-merge` (it inspects the diff, names risks, runs the suite, delivers a gated verdict — the right tool here, not catalogue citation). - *"plan QA for [story/ticket]"* → `sumo-qa-preparing-for-work` (lightweight) or `sumo-qa-creating-test-plan` (formal). - *"write me a failing test for [bug]"* → `sumo-qa-implementing-with-tdd`. - *"mutation flagged survivors / kill these mutants"* → `sumo-qa-strengthening-tests`. - *"where is the test data for X / validate this record"* → `sumo-qa-finding-test-data`. ONLY answer directly when the question is genuinely generic (*"what is the ISTQB principle for X?"*, *"how do boundary tests work?"*) and fits none of those. **Anti-pattern:** answering a PR-review / plan-QA / write-a-test / mutation-survivor / test-data question with catalogue principles instead of redirecting. ## Output discipline (mandatory) Inherits the global discipline from `using-sumo-qa`: **output discipline** (never surface internal taxonomy labels — say *"behaviour change in pricing"*, not *"Classification: business_logic_change"*), **output economy** (spend output on findings not framing; no preamble or self-narration; o