add SKILL

.claude/skills/write-tests/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: write-tests
+description: Write tests for a specific file — unit and integration tests with Vitest, Testing Library, accessible queries, and AAA pattern.
+disable-model-invocation: true
+argument-hint: "[file-path]"
+context: fork
+agent: test-engineer
+---
+
+# Write Tests
+
+Write comprehensive tests for `$ARGUMENTS`.
+
+## Steps
+
+1. **Read the target file** and understand:
+   - What it does (component, service, utility, API handler)
+   - Its dependencies and side effects
+   - Edge cases and error paths
+
+2. **Read project context:**
+   - Check `RECOMMENDATIONS.md` for testing stack decisions
+   - Look at existing test files for patterns and conventions
+   - Check test config (vitest.config, playwright.config)
+
+3. **Write tests following these rules:**
+
+   **Structure:**
+   - AAA pattern (Arrange → Act → Assert)
+   - Behavior-focused names: `it('displays error when API fails')`
+   - Group by concern: `describe('when user is logged in', ...)`
+   - Co-locate with source file: `Component.test.tsx` next to `Component.tsx`
+
+   **Queries (for React components):**
+   - `getByRole` → `getByLabelText` → `getByText` → `getByTestId` (last resort)
+   - Use `userEvent` over `fireEvent`
+
+   **Mocking:**
+   - MSW for HTTP APIs
+   - `vi.mock()` only for third-party services
+   - Real implementations for internal logic
+   - Deterministic test data via factories
+
+   **Coverage:**
+   - Happy path
+   - Error states
+   - Empty/loading states
+   - Edge cases (null, undefined, empty arrays, boundary values)
+   - Accessibility: keyboard interaction, ARIA states
+
+4. **No arbitrary waits** — use `waitFor`, `findBy`, or proper async handling.
+
+5. **Output:** working test file, ready to run with `vitest`.