- QA skill: unit tests placed next to source files (co-located)
instead of src/__tests__/ directory
- CLAUDE.md: add test convention note and full test script reference
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Step 6 now writes Vitest unit tests for non-trivial hooks and utility
functions before E2E tests. Includes clear guidance on what to test
(custom hooks, pure functions, form validation) and what to skip
(presentational components, logic covered by E2E). Steps 6-9 renumbered.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Install Vitest (integration tests for API routes) and Playwright (E2E tests)
- Add vitest.config.ts, playwright.config.ts, src/test/setup.ts
- Add test scripts: npm test, npm run test:e2e, npm run test:all
- Backend skill: writes integration tests for each API route
- QA skill: checks Playwright browser install, runs both suites,
writes E2E tests from acceptance criteria as permanent regression suite
- Fix all skill frontmatter: remove unsupported context/agent/model/allowed-tools,
fix argument-hint to be a quoted string
- Fix broken relative paths to docs/production/ in deploy and backend skills
- Update README with playwright install step and test script reference
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replaces ambiguous 4-status system with 6 clear stages, one per skill:
Planned → Architected → In Progress → In Review → Approved → Deployed
- architecture: sets "Architected" (was "In Progress")
- frontend + backend: explicitly set "In Progress" with checklist items
- qa: sets "In Review" on start, "Approved" on pass (was only "In Review")
- general rules + INDEX.md: updated valid statuses and descriptions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the manual "read .claude/agents/*.md" workflow with native
Claude Code features for a more efficient, scalable development experience:
- **Skills** (.claude/skills/): 7 auto-discovered slash commands
(/requirements, /architecture, /frontend, /backend, /qa, /deploy, /help)
with forked sub-agents for heavy tasks and inline execution for interactive ones
- **Rules** (.claude/rules/): 4 modular rule files (general, frontend, backend,
security) auto-applied based on file context
- **Sub-Agents** (.claude/agents/): Lightweight configs for frontend-dev,
backend-dev, and qa-engineer with model, tool, and turn limit settings
- **Context Engineering**: Layered context loading, context isolation via
forked skills, built-in context recovery after compaction, and
"always read, never guess" rules to prevent hallucinated code references
- **CLAUDE.md**: Auto-loaded project context replacing PROJECT_CONTEXT.md
- **Feature tracking**: features/INDEX.md as persistent state across sessions
- **Production guides**: docs/production/ for error tracking, security,
performance, database optimization, and rate limiting
- **Init Mode**: /requirements detects empty PRD and bootstraps full project
setup (PRD + all feature specs) from a single project description
Removed: 6 monolithic agent files, PROJECT_CONTEXT.md, HOW_TO_USE_AGENTS.md,
TEMPLATE_CHANGELOG.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
