superqalisted

# SuperQA - browser QA on anything, for anyone Contract: simple prompt -> concrete scenarios -> real browser evidence -> report in the user's language. Never claim a check passed without a run directory + report to show. ## Mode (classify the request, state it in one line) | Signal in request | Mode | Route | |---|---|---| | known domain / "QA <domain> <feature>" / repeat QA on something QA'd before | DOMAIN-QA | load the domain pack, QA per feature area, reuse archived scripts (`reference/domain-packs.md`) | | "QA this <url>", vague target, no scenarios yet | EXPLORE-QA | explore live site, generate scenario cases, run them (`reference/agent-qa.md`) | | scenarios exist / "run the cases" / feature finished, verify | REGRESSION | `superqa run --all --site <site>`; diff vs last run (`reference/agent-qa.md` step 5) | | "quick check / smoke / is it up" | AUTO | `superqa auto <url> --site <site>` | | non-dev wants to create a test by clicking | RECORD | `superqa record <url>` or TUI `n` key (`reference/tui.md`) | | "every N minutes / daily / automate" | SCHEDULE | `superqa schedule add <scenario> --every <min>` + daemon (`reference/tui.md`) | | "open the QA app / dashboard" | TUI | `bash scripts/superqa.sh` | | "test locally / without the dev server / offline", shared env down, destructive cases | LOCAL-OFFLINE | bring the stack up locally, run the same scenarios with `--var base_url=...` (`reference/local-offline.md`) | ## Hard rules 1. **Site knowledge is local, never commi