spec-driven-claude-code: Skill for Claude Code

Incremental Implementation Skill

Philosophy

"The simplest thing that could work."

Build in thin vertical slices. Each increment leaves the system working and testable.

---

When to Apply

Use this skill when:

• Multi-file changes
• New features
• Refactoring work
• Any change > 100 lines

Skip for:

• Single-file, small changes
• Simple bug fixes
• Configuration updates

---

The Increment Cycle

┌─────────────────────────────────────────┐
│  1. Pick smallest complete piece        │
│                 ↓                       │
│  2. Write failing test (RED)            │
│                 ↓                       │
│  3. Implement minimal code (GREEN)      │
│                 ↓                       │
│  4. Refactor if needed                  │
│                 ↓                       │
│  5. Run all tests                       │
│                 ↓                       │
│  6. Commit with clear message           │
│                 ↓                       │
│  7. Repeat for next piece               │
└─────────────────────────────────────────┘

---

Vertical vs Horizontal Slicing

Vertical Slices (Correct)

Each slice delivers end-to-end functionality:

Task 1: User can create a task
        └── DB model + API route + UI component

Task 2: User can view task list
        └── DB query + API endpoint + List component

Task 3: User can complete a task
        └── DB update + API handler + Toggle UI

Horizontal Slices (Anti-pattern)

Layers completed separately:

Task 1: Create all DB models
Task 2: Create all API routes
Task 3: Create all UI components

❌ Problem: Nothing works until everything is done

---

Slicing Strategies

1. Happy Path First

Slice 1: Basic flow works
Slice 2: Add validation
Slice 3: Add error handling
Slice 4: Add edge cases

2. Risk-First

Slice 1: Uncertain/complex piece (reduce risk early)
Slice 2: Dependent pieces (build on verified foundation)
Slice 3: Polish (now safe to invest time)