メニュー
Use before claiming any BetterMe task is done, or when verifying a change — the exact 4-gate sequence (typecheck, lint, vitest, build), Windows/PowerShell/pnpm specifics, single-test and dev-bypass usage, and what counts as evidence.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when writing or editing any user-facing Vietnamese copy — pet/companion voice lines, toasts, greetings, milestone text, or friend/garden messaging. Covers the no-guilt and no-comparison invariants, host vs guest voice, per-species tone, and the test that enforces them.
Use when editing supabase/schema.sql, RLS policies, RPCs, or the server actions in src/lib/server/** — covers owner-only RLS, SECURITY DEFINER cross-user reads, RPC-only writes, idempotent schema patterns, the append-only food ledger, and the never-throw server-action contract.
Use when working in src/lib/sync/**, on offline/local-first behavior, multi-device merge, conflict resolution, localStorage state, or upload/import — covers the merge laws (monotonic max, per-cell LWW, append-only ledgers, tombstones), seed-fiction provenance, and the derived-cache rule.
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
Comprehensive design guide for web, mobile, and desktop applications. Contains 67 styles, 161 color palettes, 57 font pairings, 99 UX guidelines, and 25 chart types across 22 technology stacks.
| name | betterme-verification |
| description | Use before claiming any BetterMe task is done, or when verifying a change — the exact 4-gate sequence (typecheck, lint, vitest, build), Windows/PowerShell/pnpm specifics, single-test and dev-bypass usage, and what counts as evidence. |
BetterMe ships as a real product. "Done" means the gates were actually run and passed, and you can quote the output. Belief is not evidence.
pnpm typecheck # tsc --noEmit — TS 5.9 strict, no unchecked domain `any`
pnpm lint # eslint . (next/core-web-vitals + next/typescript)
pnpm vitest run # full suite (jsdom); same as `pnpm test`
pnpm build # next build — the final gate
All four must be green before any commit. If you changed only docs/config outside src/
(e.g. AGENTS.md, .kiro/**), typecheck/lint/build are unaffected — say so rather than
implying you ran a full verification you didn't need.
pnpm vitest run src/path/to/file.test.tsvitest run.src/components/dashboard/pet-voice.test.ts (no-guilt /
no-comparison) and the sync merge.test.ts / dashboard-data.test.ts (economy + no-decay).head, grep, |) in shell calls — they fail in PowerShell. Use the
read/search tools instead, or PowerShell equivalents (Select-Object -First N).BETTERME_DEV_AUTH_BYPASS=true (the string "true", not
1). Under bypass, sync/social are OFF by design (localStorage-only) — not a bug.There is no live Postgres / Supabase in this environment. RLS matrices, RPC race tests,
rate-limit counting, and trigger behavior can only be validated after supabase/schema.sql is
applied to a real project (see HANDOFF.md §5). When work depends on the DB, state clearly that
DB-level verification is pending and list exactly what to test there.