qalisted

# QA QA is the evidence protocol: structured assertions a merge decision can trust, not a test-writing tutorial. ## Context Read the `## verbs` config from `CLAUDE.md` or `AGENTS.md`; resolve `{learnings_dir}` (default `docs/learnings`) and search related `type: pitfall` entries using `lib/learning-format.md`. Read a matching brief from `docs/briefs/`. Bind the intent source and assign stable `AC-1`, `AC-2`, ... identifiers to its acceptance criteria. Without an issue, brief, or explicit goal, report `INTENT GAP`; behavior alone cannot prove intent. ## Plan Produce ONE numbered list of action → expected result checks: core user flows first, then error/empty/loading states, edge inputs, double submit, Escape, keyboard-only navigation, mobile viewport, and console errors. If the flows are unclear, ask what to test. ## Test Run small changes directly. Use isolated browser workers only for 3+ groups when session isolation is proven; otherwise run sequentially. Give each worker its numbered tests, the assertion protocol below, and a step budget (~25 targeted / ~40 full page / ~75 multi-page); at budget accept partial results with `STEP_SKIP`; the main agent merges and summarizes worker results, and never share a browser session. Every test step MUST emit one marker: ``` STEP_PASS|<step-id>|<evidence> STEP_FAIL|<step-id>|<expected> -> <actual> STEP_SKIP|<step-id>|<reason> ``` Use the strongest available verification in this order: deterministic evaluation, accessibility s