erne-universal 0.1.0

package/commands/learn.md

@@ -0,0 +1,56 @@
+---
+name: learn
+description: Manual skill generation — runs continuous-learning-v2 scripts to extract patterns from session
+---
+
+# /learn — Generate Skills from Session
+
+You are executing the `/learn` command. This is **script-driven** — it runs the continuous-learning-v2 pipeline directly.
+
+## What This Does
+
+Analyzes the current coding session to extract reusable patterns and save them as skills or rule amendments for future sessions. This is the manual trigger for what `PostToolUse` hooks do automatically.
+
+## Process
+
+1. **Run the extraction script:**
+
+```bash
+node .claude/hooks/scripts/extract-session-patterns.js
+```
+
+This script:
+- Scans recent tool calls and file changes
+- Identifies patterns (repeated fixes, style corrections, common architectures)
+- Compares against existing rules and skills
+- Generates candidates for new content
+
+2. **Review candidates:**
+The script outputs a list of potential learnings:
+```
+[PATTERN] Zustand store always uses immer middleware → Suggest rule amendment
+[PATTERN] All screens use SafeAreaView wrapper → Suggest coding-style rule
+[PATTERN] API calls always retry 3 times → Suggest pattern rule
+[SKILL] Complex form validation flow → Suggest skill creation
+```
+
+3. **Approve or reject each candidate:**
+For each candidate, decide:
+- **Approve** → Script writes to `.claude/rules/` or `.claude/skills/`
+- **Reject** → Skip this pattern
+- **Edit** → Modify before saving
+
+4. **Validate new content:**
+```bash
+node .claude/hooks/scripts/validate-content.js
+```
+Ensures new rules/skills have valid frontmatter and don't conflict with existing content.
+
+## When to Use
+- After a long coding session where you established new patterns
+- When you notice yourself repeatedly making the same corrections
+- After integrating a new library and establishing conventions
+- Periodically to capture accumulated project knowledge
+
+## Note
+The automatic `PostToolUse` hook (`continuous-learning-v2.cjs`) does lightweight extraction after every tool call. This `/learn` command runs a comprehensive analysis that catches patterns the real-time hook might miss.

package/commands/native-module.md

@@ -0,0 +1,51 @@
+---
+name: native-module
+description: Create native modules with sequential native-bridge-builder then code-reviewer agents
+---
+
+# /native-module — Create Native Module
+
+You are executing the `/native-module` command. Run **native-bridge-builder** first (create the module), then **code-reviewer** (review it). This is sequential, not parallel.
+
+## Phase 1: native-bridge-builder — Scaffold & Implement
+
+### Determine Module Type
+Ask the user or detect from project:
+1. **Expo Modules API** — For Expo managed projects (recommended)
+2. **Turbo Module** — For bare React Native projects (New Architecture)
+3. **Fabric Component** — For custom native views
+
+### Scaffold the Module
+Generate all required files based on module type:
+
+**Expo Module (6 files):**
+```
+modules/[module-name]/
+  expo-module.config.json     # Module configuration
+  src/[ModuleName]Module.ts   # TypeScript API definition
+  ios/[ModuleName]Module.swift # Swift implementation
+  android/src/main/java/.../[ModuleName]Module.kt  # Kotlin implementation
+  src/__tests__/[ModuleName].test.ts  # Unit tests
+  README.md                   # Usage documentation
+```
+
+### Implementation Guidelines
+- Define clear TypeScript interface first (contract)
+- Implement Swift and Kotlin to match the contract
+- Handle errors consistently (reject Promises with error codes)
+- Use `async/await` in Swift, coroutines in Kotlin
+- Include JSDoc comments on the TypeScript API
+
+## Phase 2: code-reviewer — Review the Module
+
+After module creation, automatically run code review:
+- Verify TypeScript types match native implementations
+- Check error handling on both platforms
+- Validate threading (no main thread blocking)
+- Review memory management (cleanup, listeners)
+- Check platform parity (same behavior iOS/Android)
+
+## Output
+- Scaffolded module files with implementation
+- Code review results
+- Usage example in React Native

package/commands/navigate.md

@@ -0,0 +1,69 @@
+---
+name: navigate
+description: Design navigation architecture using the architect agent
+---
+
+# /navigate — Navigation Design
+
+You are executing the `/navigate` command. Use the **architect** agent to design navigation structure.
+
+## Process
+
+1. **Map the screens** — List all screens and their relationships
+2. **Design the hierarchy** — Determine navigation stacks, tabs, drawers
+3. **Plan Expo Router file structure** — Map screens to file-based routes
+
+## Output: Expo Router File Structure
+
+```
+app/
+  _layout.tsx              # Root Stack
+  index.tsx                # Redirect to (tabs)
+  +not-found.tsx           # 404 screen
+  (tabs)/
+    _layout.tsx            # Tab navigator
+    index.tsx              # Home tab
+    search.tsx             # Search tab
+    profile.tsx            # Profile tab
+  (auth)/
+    _layout.tsx            # Auth stack (no tabs)
+    login.tsx
+    register.tsx
+    forgot-password.tsx
+  [entity]/
+    _layout.tsx            # Entity detail stack
+    [id].tsx               # Entity detail screen
+    [id]/edit.tsx           # Edit screen
+  modal/
+    _layout.tsx            # Modal group
+    settings.tsx           # Settings modal
+    create-post.tsx        # Create post modal
+```
+
+3. **Define navigation patterns**:
+   - Tab-to-detail: How tabs navigate to detail screens
+   - Auth flow: How unauthenticated users are redirected
+   - Deep linking: URL scheme mapping
+   - Modal presentation: Full-screen vs bottom sheet
+
+4. **Generate layout files** — Create `_layout.tsx` files with proper configuration:
+
+```tsx
+// app/(tabs)/_layout.tsx
+import { Tabs } from 'expo-router';
+
+export default function TabLayout() {
+  return (
+    <Tabs screenOptions={{ tabBarActiveTintColor: '#007AFF' }}>
+      <Tabs.Screen name="index" options={{ title: 'Home', tabBarIcon: ... }} />
+      <Tabs.Screen name="search" options={{ title: 'Search', tabBarIcon: ... }} />
+      <Tabs.Screen name="profile" options={{ title: 'Profile', tabBarIcon: ... }} />
+    </Tabs>
+  );
+}
+```
+
+## Notes
+- Reference `rules/common/navigation.md` for conventions
+- Consider deep link testing: `npx uri-scheme open [url] --ios`
+- Include typed route definitions

package/commands/perf.md

@@ -0,0 +1,68 @@
+---
+name: perf
+description: Performance profiling and optimization using the performance-profiler agent
+---
+
+# /perf — Performance Profiling
+
+You are executing the `/perf` command. Use the **performance-profiler** agent to diagnose and fix performance issues.
+
+## Diagnostic Areas
+
+### 1. Rendering Performance (FPS)
+- Check for unnecessary re-renders with React DevTools Profiler
+- Identify components re-rendering without prop changes
+- Look for missing `React.memo`, `useCallback`, `useMemo`
+- Detect inline function/object creation in render
+
+### 2. Time to Interactive (TTI)
+- Analyze app startup sequence
+- Check for heavy `useEffect` chains on mount
+- Identify blocking operations on main thread
+- Verify Hermes bytecode compilation
+
+### 3. Bundle Size
+- Run `npx react-native-bundle-visualizer`
+- Identify large dependencies
+- Check for unused imports and dead code
+- Verify tree-shaking is working
+
+### 4. Memory
+- Check for listener/subscription cleanup in `useEffect`
+- Identify large objects retained in closures
+- Look for image caching issues
+- Detect circular references
+
+### 5. Animations
+- Verify all animations use Reanimated (not Animated API)
+- Check for JS thread bottlenecks in animation callbacks
+- Identify layout thrashing during animations
+- Measure actual FPS during animations
+
+### 6. Hermes Engine
+- Verify Hermes is enabled
+- Check for unsupported JS features
+- Profile with Hermes sampling profiler
+- Analyze bytecode compilation output
+
+## Output Format
+```
+## Performance Metrics
+| Metric | Current | Target | Status |
+|--------|---------|--------|--------|
+| JS FPS | 45 | 60 | ⚠️ |
+| UI FPS | 58 | 60 | ✅ |
+| TTI | 3.2s | <2s | ❌ |
+| Bundle | 8.2MB | <5MB | ❌ |
+
+## Critical Issues
+[Issues that must be fixed]
+
+## Optimization Opportunities
+[Improvements ranked by impact]
+```
+
+## Notes
+- If agent-device is available, measure actual FPS on device
+- Reference `rules/common/performance.md` for optimization patterns
+- Profile on real devices, not simulator/emulator

package/commands/plan.md

@@ -0,0 +1,49 @@
+---
+name: plan
+description: Design feature architecture using the architect agent
+---
+
+# /plan — Feature Architecture Design
+
+You are executing the `/plan` command. Use the **architect** agent to design a feature architecture.
+
+## Process
+
+1. **Understand the requirement** — Ask clarifying questions if the feature description is vague
+2. **Analyze existing codebase** — Read relevant files, understand current navigation structure, state management, and API patterns
+3. **Design the architecture** — Using the architect agent's process:
+   - Decompose into components and screens
+   - Plan Expo Router file structure
+   - Select state management approach (Zustand / TanStack Query / local)
+   - Design data flow and API layer
+   - Consider platform-specific requirements
+4. **Output the plan** — Use the architect agent's output format:
+
+### Architecture Output
+
+```
+## Overview
+[1-2 sentence description of the feature]
+
+## File Structure
+[New files to create with paths]
+
+## Component Design
+[Component hierarchy and responsibilities]
+
+## Data Flow
+[State management approach, API calls, caching strategy]
+
+## Navigation
+[New routes, layout changes, deep link support]
+
+## Implementation Tasks
+[Ordered list of implementation steps]
+```
+
+5. **Review with user** — Present the plan and ask for approval before implementation
+
+## Notes
+- Reference `rules/common/patterns.md` and `rules/common/navigation.md` for conventions
+- Consider whether this is Expo managed, bare RN, or has native modules
+- Include test strategy in the plan

package/commands/quality-gate.md

@@ -0,0 +1,80 @@
+---
+name: quality-gate
+description: Pre-merge quality checks using parallel code-reviewer and performance-profiler agents
+---
+
+# /quality-gate — Pre-Merge Checks
+
+You are executing the `/quality-gate` command. Run **code-reviewer** and **performance-profiler** in parallel for comprehensive pre-merge validation.
+
+## Parallel Execution
+
+### Agent 1: code-reviewer — Code Quality
+
+Run a full code review focused on merge readiness:
+
+**Correctness:**
+- Logic errors, edge cases
+- TypeScript type safety (no `any` escapes)
+- Error handling completeness
+
+**Style & Conventions:**
+- Follows project rules (check `.claude/rules/`)
+- NativeWind usage is consistent
+- Component structure matches patterns
+
+**Security:**
+- No secrets in code
+- Input validation at boundaries
+- Secure storage used for sensitive data
+
+**Testing:**
+- All new code has tests
+- Tests actually test behavior (not implementation)
+- Edge cases covered
+
+### Agent 2: performance-profiler — Performance Checks
+
+Run performance validation:
+
+**Bundle Impact:**
+```bash
+# Compare bundle size before/after changes
+npx react-native-bundle-visualizer
+```
+
+**Runtime Checks:**
+- No unnecessary re-renders introduced
+- Lists use `FlashList` with `estimatedItemSize`
+- Images are optimized (expo-image with caching)
+- Animations run on UI thread (worklets)
+
+**Memory:**
+- Event listeners and subscriptions cleaned up
+- No circular references in state
+- Large data sets paginated
+
+## Gate Result
+
+```
+## Quality Gate Result: PASS / FAIL
+
+### Code Review: PASS
+- 0 Critical issues
+- 1 Warning (TODO in checkout.tsx:45)
+- 3 Suggestions
+
+### Performance: PASS
+- Bundle size: +12KB (within threshold)
+- No new re-render issues detected
+- Memory: No leaks detected
+
+### Verdict: PASS ✓
+Ready for merge. Address 1 warning in next iteration.
+```
+
+The gate produces a binary PASS/FAIL. FAIL if:
+- Any critical code review issue
+- Bundle size increase > 50KB without justification
+- Performance regression detected
+- Missing tests for new code paths

package/commands/retrospective.md

@@ -0,0 +1,70 @@
+---
+name: retrospective
+description: Session analysis — runs evaluate-session.js to review work quality and suggest improvements
+---
+
+# /retrospective — Session Analysis
+
+You are executing the `/retrospective` command. This is **script-driven** — it runs the session evaluation pipeline.
+
+## What This Does
+
+Analyzes the completed coding session to evaluate quality, identify improvements, and suggest harness enhancements.
+
+## Process
+
+1. **Run the evaluation script:**
+
+```bash
+node .claude/hooks/scripts/evaluate-session.js
+```
+
+This script analyzes:
+- Files created/modified during the session
+- Test results and coverage changes
+- Build success/failure history
+- Hook trigger patterns (which rules fired, which were ignored)
+- Time spent in different phases (planning, coding, testing, debugging)
+
+2. **Generate session report:**
+
+```
+## Session Retrospective
+
+### Work Summary
+- Files changed: 12
+- Tests added: 8
+- Tests passing: 47/47
+- Build status: Success
+
+### Quality Metrics
+- Type safety: 100% (no new `any`)
+- Test coverage delta: +3.2%
+- Bundle size delta: +8KB
+
+### Patterns Observed
+- [GOOD] Consistent use of error boundaries
+- [GOOD] All new components have tests
+- [IMPROVE] 3 files missing JSDoc on public API
+- [IMPROVE] 2 effects missing cleanup
+
+### Harness Feedback
+- Rule `common/state-management.md` triggered 5 times → Well calibrated
+- Rule `expo/patterns.md` never triggered → May need broader globs
+- Hook `lint-staged.cjs` caught 2 issues → Working as intended
+- Suggestion: Add rule for consistent error message format
+
+### Recommendations
+1. Add error message formatting rule
+2. Review expo/patterns.md glob coverage
+3. Consider adding pre-commit test hook
+```
+
+3. **Act on recommendations:**
+Review each recommendation and decide whether to implement it now or add to backlog.
+
+## When to Use
+- At the end of a significant coding session
+- After completing a feature or milestone
+- When the harness feels miscalibrated (too many or too few rule triggers)
+- Periodically for continuous improvement

package/commands/setup-device.md

@@ -0,0 +1,99 @@
+---
+name: setup-device
+description: Install and configure agent-device MCP server for simulator/emulator control
+---
+
+# /setup-device — Setup Device Control
+
+You are executing the `/setup-device` command. This is **script-driven** — it sets up the agent-device MCP server.
+
+## What This Does
+
+Installs and configures the agent-device MCP server so commands like `/debug`, `/perf`, `/component`, and `/deploy` gain visual device interaction capabilities.
+
+## Process
+
+### Step 1: Check Prerequisites
+
+```bash
+# iOS: Check for Xcode and simulator
+xcodebuild -version
+xcrun simctl list devices
+
+# Android: Check for Android Studio and emulator
+adb version
+emulator -list-avds
+```
+
+### Step 2: Install agent-device MCP
+
+Check if already configured in `.claude/settings.json`:
+```json
+{
+  "mcpServers": {
+    "agent-device": {
+      "command": "npx",
+      "args": ["-y", "agent-device"]
+    }
+  }
+}
+```
+
+If not present, add the configuration.
+
+### Step 3: Verify Connection
+
+```bash
+# Boot a simulator (iOS)
+xcrun simctl boot "iPhone 16 Pro"
+
+# Or start an emulator (Android)
+emulator -avd Pixel_8_API_35 &
+```
+
+Test that agent-device can:
+- Take a screenshot
+- Detect booted device
+- Perform a tap action
+
+### Step 4: Configure Command Integration
+
+After setup, these commands gain enhanced capabilities:
+
+| Command | Enhancement |
+|---------|-------------|
+| `/debug` | Screenshot reproduction steps, tap through UI |
+| `/perf` | Measure real FPS, capture actual jank frames |
+| `/component` | Render on device, visual verification screenshot |
+| `/deploy` | Launch preview build, verify UI before submit |
+| `/build-fix` | Build, install, and launch to verify fix |
+
+### Output
+
+```
+## agent-device Setup Complete
+
+### Status
+- MCP server: Configured ✓
+- iOS Simulator: Available (iPhone 16 Pro)
+- Android Emulator: Available (Pixel 8 API 35)
+
+### Capabilities Enabled
+- Screenshot capture
+- Tap/type/swipe interaction
+- App navigation
+- Visual verification
+
+### Commands Enhanced
+/debug, /perf, /component, /deploy, /build-fix
+now have visual device control.
+```
+
+## Troubleshooting
+
+| Problem | Solution |
+|---------|----------|
+| iOS simulator not found | Install Xcode, run `xcode-select --install` |
+| Android emulator not found | Install Android Studio, create AVD in AVD Manager |
+| agent-device fails to connect | Check MCP server config in `.claude/settings.json` |
+| Screenshots are black | Wait for device to finish booting, retry |

package/commands/tdd.md

@@ -0,0 +1,51 @@
+---
+name: tdd
+description: Test-driven development workflow with Jest and React Native Testing Library
+---
+
+# /tdd — Test-Driven Development
+
+You are executing the `/tdd` command. Use the **tdd-guide** agent to implement features test-first.
+
+## Red-Green-Refactor Cycle
+
+### 1. RED — Write Failing Test First
+```tsx
+// Write the test BEFORE any implementation
+test('LoginButton shows loading state during auth', () => {
+  render(<LoginButton onPress={mockAuth} />);
+  fireEvent.press(screen.getByRole('button', { name: 'Log In' }));
+  expect(screen.getByTestId('loading-spinner')).toBeVisible();
+});
+```
+Run the test — confirm it FAILS (red).
+
+### 2. GREEN — Write Minimum Code to Pass
+Implement only enough code to make the test pass. Do not over-engineer.
+
+### 3. REFACTOR — Clean Up
+Improve code quality while keeping tests green:
+- Extract shared logic into hooks
+- Improve naming and readability
+- Remove duplication
+
+## Testing Stack
+- **Unit/Component**: Jest + React Native Testing Library
+- **E2E**: Detox (when needed for user flows)
+
+## Workflow
+1. User describes the feature to implement
+2. Write test(s) for the first behavior
+3. Run test — verify it fails
+4. Implement minimum code
+5. Run test — verify it passes
+6. Refactor if needed
+7. Repeat for next behavior
+8. When feature is complete, run full test suite
+
+## Rules
+- Never write implementation code without a failing test first
+- Test behavior, not implementation details
+- Query elements by role, text, or label (not testID unless necessary)
+- Mock at boundaries (API, native modules), not internals
+- Reference `rules/common/testing.md` for conventions

package/commands/upgrade.md

@@ -0,0 +1,78 @@
+---
+name: upgrade
+description: Version migration for Expo SDK and React Native using the upgrade-assistant agent
+---
+
+# /upgrade — Version Migration
+
+You are executing the `/upgrade` command. Use the **upgrade-assistant** agent for guided version migration.
+
+## 5-Step Upgrade Process
+
+### Step 1: Pre-Assessment
+- Identify current versions (Expo SDK, React Native, key dependencies)
+- Identify target versions
+- Check release notes and breaking changes
+- Backup current state (`git stash` or commit)
+
+### Step 2: Dependency Compatibility Matrix
+Generate a compatibility table:
+
+```
+| Package | Current | Target | Compatible? | Notes |
+|---------|---------|--------|-------------|-------|
+| expo | 51.0.0 | 52.0.0 | ✅ | Major upgrade |
+| react-native | 0.74 | 0.76 | ✅ | Via Expo SDK |
+| @react-navigation | 6.x | 7.x | ⚠️ | Breaking changes |
+```
+
+### Step 3: Breaking Change Detection
+- Scan codebase for deprecated APIs being used
+- Identify removed features
+- Check for changed behavior in dependencies
+- Flag native module compatibility issues
+
+### Step 4: Migration Steps
+Execute the upgrade:
+
+**Expo projects:**
+```bash
+npx expo install expo@latest
+npx expo install --fix  # Fix peer dependency issues
+npx expo prebuild --clean  # Regenerate native projects
+```
+
+**Bare RN projects:**
+```bash
+npx react-native upgrade
+# Or use upgrade-helper: https://react-native-community.github.io/upgrade-helper/
+```
+
+- Apply codemods when available
+- Update deprecated API calls
+- Fix TypeScript type changes
+- Update config files
+
+### Step 5: Post-Upgrade Verification
+- [ ] TypeScript compiles without errors
+- [ ] ESLint passes
+- [ ] All tests pass
+- [ ] iOS build succeeds
+- [ ] Android build succeeds
+- [ ] Manual smoke test on both platforms
+
+## Output Format
+```
+## Upgrade Summary
+From: [current versions]
+To: [target versions]
+
+## Breaking Changes Found
+[List with file locations]
+
+## Changes Applied
+[Files modified with descriptions]
+
+## Verification Checklist
+[Status of each verification step]
+```