claude-code-pilot 2.0.0 → 3.1.0

package/src/skills/coding-standards/SKILL.md

@@ -0,0 +1,530 @@
+---
+name: coding-standards
+description: Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
+origin: ECC
+---
+
+# Coding Standards & Best Practices
+
+Universal coding standards applicable across all projects.
+
+## When to Activate
+
+- Starting a new project or module
+- Reviewing code for quality and maintainability
+- Refactoring existing code to follow conventions
+- Enforcing naming, formatting, or structural consistency
+- Setting up linting, formatting, or type-checking rules
+- Onboarding new contributors to coding conventions
+
+## Code Quality Principles
+
+### 1. Readability First
+- Code is read more than written
+- Clear variable and function names
+- Self-documenting code preferred over comments
+- Consistent formatting
+
+### 2. KISS (Keep It Simple, Stupid)
+- Simplest solution that works
+- Avoid over-engineering
+- No premature optimization
+- Easy to understand > clever code
+
+### 3. DRY (Don't Repeat Yourself)
+- Extract common logic into functions
+- Create reusable components
+- Share utilities across modules
+- Avoid copy-paste programming
+
+### 4. YAGNI (You Aren't Gonna Need It)
+- Don't build features before they're needed
+- Avoid speculative generality
+- Add complexity only when required
+- Start simple, refactor when needed
+
+## TypeScript/JavaScript Standards
+
+### Variable Naming
+
+```typescript
+// ✅ GOOD: Descriptive names
+const marketSearchQuery = 'election'
+const isUserAuthenticated = true
+const totalRevenue = 1000
+
+// ❌ BAD: Unclear names
+const q = 'election'
+const flag = true
+const x = 1000
+```
+
+### Function Naming
+
+```typescript
+// ✅ GOOD: Verb-noun pattern
+async function fetchMarketData(marketId: string) { }
+function calculateSimilarity(a: number[], b: number[]) { }
+function isValidEmail(email: string): boolean { }
+
+// ❌ BAD: Unclear or noun-only
+async function market(id: string) { }
+function similarity(a, b) { }
+function email(e) { }
+```
+
+### Immutability Pattern (CRITICAL)
+
+```typescript
+// ✅ ALWAYS use spread operator
+const updatedUser = {
+  ...user,
+  name: 'New Name'
+}
+
+const updatedArray = [...items, newItem]
+
+// ❌ NEVER mutate directly
+user.name = 'New Name'  // BAD
+items.push(newItem)     // BAD
+```
+
+### Error Handling
+
+```typescript
+// ✅ GOOD: Comprehensive error handling
+async function fetchData(url: string) {
+  try {
+    const response = await fetch(url)
+
+    if (!response.ok) {
+      throw new Error(`HTTP ${response.status}: ${response.statusText}`)
+    }
+
+    return await response.json()
+  } catch (error) {
+    console.error('Fetch failed:', error)
+    throw new Error('Failed to fetch data')
+  }
+}
+
+// ❌ BAD: No error handling
+async function fetchData(url) {
+  const response = await fetch(url)
+  return response.json()
+}
+```
+
+### Async/Await Best Practices
+
+```typescript
+// ✅ GOOD: Parallel execution when possible
+const [users, markets, stats] = await Promise.all([
+  fetchUsers(),
+  fetchMarkets(),
+  fetchStats()
+])
+
+// ❌ BAD: Sequential when unnecessary
+const users = await fetchUsers()
+const markets = await fetchMarkets()
+const stats = await fetchStats()
+```
+
+### Type Safety
+
+```typescript
+// ✅ GOOD: Proper types
+interface Market {
+  id: string
+  name: string
+  status: 'active' | 'resolved' | 'closed'
+  created_at: Date
+}
+
+function getMarket(id: string): Promise<Market> {
+  // Implementation
+}
+
+// ❌ BAD: Using 'any'
+function getMarket(id: any): Promise<any> {
+  // Implementation
+}
+```
+
+## React Best Practices
+
+### Component Structure
+
+```typescript
+// ✅ GOOD: Functional component with types
+interface ButtonProps {
+  children: React.ReactNode
+  onClick: () => void
+  disabled?: boolean
+  variant?: 'primary' | 'secondary'
+}
+
+export function Button({
+  children,
+  onClick,
+  disabled = false,
+  variant = 'primary'
+}: ButtonProps) {
+  return (
+    <button
+      onClick={onClick}
+      disabled={disabled}
+      className={`btn btn-${variant}`}
+    >
+      {children}
+    </button>
+  )
+}
+
+// ❌ BAD: No types, unclear structure
+export function Button(props) {
+  return <button onClick={props.onClick}>{props.children}</button>
+}
+```
+
+### Custom Hooks
+
+```typescript
+// ✅ GOOD: Reusable custom hook
+export function useDebounce<T>(value: T, delay: number): T {
+  const [debouncedValue, setDebouncedValue] = useState<T>(value)
+
+  useEffect(() => {
+    const handler = setTimeout(() => {
+      setDebouncedValue(value)
+    }, delay)
+
+    return () => clearTimeout(handler)
+  }, [value, delay])
+
+  return debouncedValue
+}
+
+// Usage
+const debouncedQuery = useDebounce(searchQuery, 500)
+```
+
+### State Management
+
+```typescript
+// ✅ GOOD: Proper state updates
+const [count, setCount] = useState(0)
+
+// Functional update for state based on previous state
+setCount(prev => prev + 1)
+
+// ❌ BAD: Direct state reference
+setCount(count + 1)  // Can be stale in async scenarios
+```
+
+### Conditional Rendering
+
+```typescript
+// ✅ GOOD: Clear conditional rendering
+{isLoading && <Spinner />}
+{error && <ErrorMessage error={error} />}
+{data && <DataDisplay data={data} />}
+
+// ❌ BAD: Ternary hell
+{isLoading ? <Spinner /> : error ? <ErrorMessage error={error} /> : data ? <DataDisplay data={data} /> : null}
+```
+
+## API Design Standards
+
+### REST API Conventions
+
+```
+GET    /api/markets              # List all markets
+GET    /api/markets/:id          # Get specific market
+POST   /api/markets              # Create new market
+PUT    /api/markets/:id          # Update market (full)
+PATCH  /api/markets/:id          # Update market (partial)
+DELETE /api/markets/:id          # Delete market
+
+# Query parameters for filtering
+GET /api/markets?status=active&limit=10&offset=0
+```
+
+### Response Format
+
+```typescript
+// ✅ GOOD: Consistent response structure
+interface ApiResponse<T> {
+  success: boolean
+  data?: T
+  error?: string
+  meta?: {
+    total: number
+    page: number
+    limit: number
+  }
+}
+
+// Success response
+return NextResponse.json({
+  success: true,
+  data: markets,
+  meta: { total: 100, page: 1, limit: 10 }
+})
+
+// Error response
+return NextResponse.json({
+  success: false,
+  error: 'Invalid request'
+}, { status: 400 })
+```
+
+### Input Validation
+
+```typescript
+import { z } from 'zod'
+
+// ✅ GOOD: Schema validation
+const CreateMarketSchema = z.object({
+  name: z.string().min(1).max(200),
+  description: z.string().min(1).max(2000),
+  endDate: z.string().datetime(),
+  categories: z.array(z.string()).min(1)
+})
+
+export async function POST(request: Request) {
+  const body = await request.json()
+
+  try {
+    const validated = CreateMarketSchema.parse(body)
+    // Proceed with validated data
+  } catch (error) {
+    if (error instanceof z.ZodError) {
+      return NextResponse.json({
+        success: false,
+        error: 'Validation failed',
+        details: error.errors
+      }, { status: 400 })
+    }
+  }
+}
+```
+
+## File Organization
+
+### Project Structure
+
+```
+src/
+├── app/                    # Next.js App Router
+│   ├── api/               # API routes
+│   ├── markets/           # Market pages
+│   └── (auth)/           # Auth pages (route groups)
+├── components/            # React components
+│   ├── ui/               # Generic UI components
+│   ├── forms/            # Form components
+│   └── layouts/          # Layout components
+├── hooks/                # Custom React hooks
+├── lib/                  # Utilities and configs
+│   ├── api/             # API clients
+│   ├── utils/           # Helper functions
+│   └── constants/       # Constants
+├── types/                # TypeScript types
+└── styles/              # Global styles
+```
+
+### File Naming
+
+```
+components/Button.tsx          # PascalCase for components
+hooks/useAuth.ts              # camelCase with 'use' prefix
+lib/formatDate.ts             # camelCase for utilities
+types/market.types.ts         # camelCase with .types suffix
+```
+
+## Comments & Documentation
+
+### When to Comment
+
+```typescript
+// ✅ GOOD: Explain WHY, not WHAT
+// Use exponential backoff to avoid overwhelming the API during outages
+const delay = Math.min(1000 * Math.pow(2, retryCount), 30000)
+
+// Deliberately using mutation here for performance with large arrays
+items.push(newItem)
+
+// ❌ BAD: Stating the obvious
+// Increment counter by 1
+count++
+
+// Set name to user's name
+name = user.name
+```
+
+### JSDoc for Public APIs
+
+```typescript
+/**
+ * Searches markets using semantic similarity.
+ *
+ * @param query - Natural language search query
+ * @param limit - Maximum number of results (default: 10)
+ * @returns Array of markets sorted by similarity score
+ * @throws {Error} If OpenAI API fails or Redis unavailable
+ *
+ * @example
+ * ```typescript
+ * const results = await searchMarkets('election', 5)
+ * console.log(results[0].name) // "Trump vs Biden"
+ * ```
+ */
+export async function searchMarkets(
+  query: string,
+  limit: number = 10
+): Promise<Market[]> {
+  // Implementation
+}
+```
+
+## Performance Best Practices
+
+### Memoization
+
+```typescript
+import { useMemo, useCallback } from 'react'
+
+// ✅ GOOD: Memoize expensive computations
+const sortedMarkets = useMemo(() => {
+  return markets.sort((a, b) => b.volume - a.volume)
+}, [markets])
+
+// ✅ GOOD: Memoize callbacks
+const handleSearch = useCallback((query: string) => {
+  setSearchQuery(query)
+}, [])
+```
+
+### Lazy Loading
+
+```typescript
+import { lazy, Suspense } from 'react'
+
+// ✅ GOOD: Lazy load heavy components
+const HeavyChart = lazy(() => import('./HeavyChart'))
+
+export function Dashboard() {
+  return (
+    <Suspense fallback={<Spinner />}>
+      <HeavyChart />
+    </Suspense>
+  )
+}
+```
+
+### Database Queries
+
+```typescript
+// ✅ GOOD: Select only needed columns
+const { data } = await supabase
+  .from('markets')
+  .select('id, name, status')
+  .limit(10)
+
+// ❌ BAD: Select everything
+const { data } = await supabase
+  .from('markets')
+  .select('*')
+```
+
+## Testing Standards
+
+### Test Structure (AAA Pattern)
+
+```typescript
+test('calculates similarity correctly', () => {
+  // Arrange
+  const vector1 = [1, 0, 0]
+  const vector2 = [0, 1, 0]
+
+  // Act
+  const similarity = calculateCosineSimilarity(vector1, vector2)
+
+  // Assert
+  expect(similarity).toBe(0)
+})
+```
+
+### Test Naming
+
+```typescript
+// ✅ GOOD: Descriptive test names
+test('returns empty array when no markets match query', () => { })
+test('throws error when OpenAI API key is missing', () => { })
+test('falls back to substring search when Redis unavailable', () => { })
+
+// ❌ BAD: Vague test names
+test('works', () => { })
+test('test search', () => { })
+```
+
+## Code Smell Detection
+
+Watch for these anti-patterns:
+
+### 1. Long Functions
+```typescript
+// ❌ BAD: Function > 50 lines
+function processMarketData() {
+  // 100 lines of code
+}
+
+// ✅ GOOD: Split into smaller functions
+function processMarketData() {
+  const validated = validateData()
+  const transformed = transformData(validated)
+  return saveData(transformed)
+}
+```
+
+### 2. Deep Nesting
+```typescript
+// ❌ BAD: 5+ levels of nesting
+if (user) {
+  if (user.isAdmin) {
+    if (market) {
+      if (market.isActive) {
+        if (hasPermission) {
+          // Do something
+        }
+      }
+    }
+  }
+}
+
+// ✅ GOOD: Early returns
+if (!user) return
+if (!user.isAdmin) return
+if (!market) return
+if (!market.isActive) return
+if (!hasPermission) return
+
+// Do something
+```
+
+### 3. Magic Numbers
+```typescript
+// ❌ BAD: Unexplained numbers
+if (retryCount > 3) { }
+setTimeout(callback, 500)
+
+// ✅ GOOD: Named constants
+const MAX_RETRIES = 3
+const DEBOUNCE_DELAY_MS = 500
+
+if (retryCount > MAX_RETRIES) { }
+setTimeout(callback, DEBOUNCE_DELAY_MS)
+```
+
+**Remember**: Code quality is not negotiable. Clear, maintainable code enables rapid development and confident refactoring.

package/src/skills/content-hash-cache-pattern/SKILL.md

@@ -0,0 +1,161 @@
+---
+name: content-hash-cache-pattern
+description: Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
+origin: ECC
+---
+
+# Content-Hash File Cache Pattern
+
+Cache expensive file processing results (PDF parsing, text extraction, image analysis) using SHA-256 content hashes as cache keys. Unlike path-based caching, this approach survives file moves/renames and auto-invalidates when content changes.
+
+## When to Activate
+
+- Building file processing pipelines (PDF, images, text extraction)
+- Processing cost is high and same files are processed repeatedly
+- Need a `--cache/--no-cache` CLI option
+- Want to add caching to existing pure functions without modifying them
+
+## Core Pattern
+
+### 1. Content-Hash Based Cache Key
+
+Use file content (not path) as the cache key:
+
+```python
+import hashlib
+from pathlib import Path
+
+_HASH_CHUNK_SIZE = 65536  # 64KB chunks for large files
+
+def compute_file_hash(path: Path) -> str:
+    """SHA-256 of file contents (chunked for large files)."""
+    if not path.is_file():
+        raise FileNotFoundError(f"File not found: {path}")
+    sha256 = hashlib.sha256()
+    with open(path, "rb") as f:
+        while True:
+            chunk = f.read(_HASH_CHUNK_SIZE)
+            if not chunk:
+                break
+            sha256.update(chunk)
+    return sha256.hexdigest()
+```
+
+**Why content hash?** File rename/move = cache hit. Content change = automatic invalidation. No index file needed.
+
+### 2. Frozen Dataclass for Cache Entry
+
+```python
+from dataclasses import dataclass
+
+@dataclass(frozen=True, slots=True)
+class CacheEntry:
+    file_hash: str
+    source_path: str
+    document: ExtractedDocument  # The cached result
+```
+
+### 3. File-Based Cache Storage
+
+Each cache entry is stored as `{hash}.json` — O(1) lookup by hash, no index file required.
+
+```python
+import json
+from typing import Any
+
+def write_cache(cache_dir: Path, entry: CacheEntry) -> None:
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    cache_file = cache_dir / f"{entry.file_hash}.json"
+    data = serialize_entry(entry)
+    cache_file.write_text(json.dumps(data, ensure_ascii=False), encoding="utf-8")
+
+def read_cache(cache_dir: Path, file_hash: str) -> CacheEntry | None:
+    cache_file = cache_dir / f"{file_hash}.json"
+    if not cache_file.is_file():
+        return None
+    try:
+        raw = cache_file.read_text(encoding="utf-8")
+        data = json.loads(raw)
+        return deserialize_entry(data)
+    except (json.JSONDecodeError, ValueError, KeyError):
+        return None  # Treat corruption as cache miss
+```
+
+### 4. Service Layer Wrapper (SRP)
+
+Keep the processing function pure. Add caching as a separate service layer.
+
+```python
+def extract_with_cache(
+    file_path: Path,
+    *,
+    cache_enabled: bool = True,
+    cache_dir: Path = Path(".cache"),
+) -> ExtractedDocument:
+    """Service layer: cache check -> extraction -> cache write."""
+    if not cache_enabled:
+        return extract_text(file_path)  # Pure function, no cache knowledge
+
+    file_hash = compute_file_hash(file_path)
+
+    # Check cache
+    cached = read_cache(cache_dir, file_hash)
+    if cached is not None:
+        logger.info("Cache hit: %s (hash=%s)", file_path.name, file_hash[:12])
+        return cached.document
+
+    # Cache miss -> extract -> store
+    logger.info("Cache miss: %s (hash=%s)", file_path.name, file_hash[:12])
+    doc = extract_text(file_path)
+    entry = CacheEntry(file_hash=file_hash, source_path=str(file_path), document=doc)
+    write_cache(cache_dir, entry)
+    return doc
+```
+
+## Key Design Decisions
+
+| Decision | Rationale |
+|----------|-----------|
+| SHA-256 content hash | Path-independent, auto-invalidates on content change |
+| `{hash}.json` file naming | O(1) lookup, no index file needed |
+| Service layer wrapper | SRP: extraction stays pure, cache is a separate concern |
+| Manual JSON serialization | Full control over frozen dataclass serialization |
+| Corruption returns `None` | Graceful degradation, re-processes on next run |
+| `cache_dir.mkdir(parents=True)` | Lazy directory creation on first write |
+
+## Best Practices
+
+- **Hash content, not paths** — paths change, content identity doesn't
+- **Chunk large files** when hashing — avoid loading entire files into memory
+- **Keep processing functions pure** — they should know nothing about caching
+- **Log cache hit/miss** with truncated hashes for debugging
+- **Handle corruption gracefully** — treat invalid cache entries as misses, never crash
+
+## Anti-Patterns to Avoid
+
+```python
+# BAD: Path-based caching (breaks on file move/rename)
+cache = {"/path/to/file.pdf": result}
+
+# BAD: Adding cache logic inside the processing function (SRP violation)
+def extract_text(path, *, cache_enabled=False, cache_dir=None):
+    if cache_enabled:  # Now this function has two responsibilities
+        ...
+
+# BAD: Using dataclasses.asdict() with nested frozen dataclasses
+# (can cause issues with complex nested types)
+data = dataclasses.asdict(entry)  # Use manual serialization instead
+```
+
+## When to Use
+
+- File processing pipelines (PDF parsing, OCR, text extraction, image analysis)
+- CLI tools that benefit from `--cache/--no-cache` options
+- Batch processing where the same files appear across runs
+- Adding caching to existing pure functions without modifying them
+
+## When NOT to Use
+
+- Data that must always be fresh (real-time feeds)
+- Cache entries that would be extremely large (consider streaming instead)
+- Results that depend on parameters beyond file content (e.g., different extraction configs)