layered-reasoning

# Layered Reasoning

## Purpose

Layered reasoning structures thinking across multiple levels of abstraction—from high-level principles (30,000 ft) to tactical approaches (3,000 ft) to concrete actions (300 ft). Good layered reasoning maintains consistency: lower layers implement upper layers, upper layers constrain lower layers, and each layer is independently useful.

Use this skill when:
- **Designing systems** with architectural layers (strategy → design → implementation)
- **Explaining complex topics** at multiple depths (executive summary → technical detail → code)
- **Strategic planning** connecting vision → objectives → tactics → tasks
- **Ensuring consistency** between principles and execution
- **Bridging communication** between stakeholders at different levels (CEO → manager → engineer)
- **Problem-solving** where high-level constraints must guide low-level decisions

Layered reasoning prevents inconsistency: strategic plans that can't be executed, implementations that violate principles, or explanations that confuse by jumping abstraction levels.

---

## Common Patterns

### Pattern 1: 30K → 3K → 300 ft Decomposition (Top-Down)

**When**: Starting from vision/principles, deriving concrete actions

**Structure**:
- **30,000 ft (Strategic)**: Why? Core principles, invariants, constraints (e.g., "Customer privacy is non-negotiable")
- **3,000 ft (Tactical)**: What? Approaches, architectures, policies (e.g., "Zero-trust security model, end-to-end encryption")
- **300 ft (Operational)**: How? Specific actions, procedures, code (e.g., "Implement AES-256 encryption for data at rest")

**Example**: Product strategy
- **30K**: "Become the most trusted platform" (principle)
- **3K**: "Achieve SOC 2 compliance, publish security reports, 24/7 support" (tactics)
- **300 ft**: "Implement MFA, conduct quarterly audits, hire 5 support engineers" (actions)

**Process**: (1) Define strategic layer invariants, (2) Derive tactical options that satisfy invariants, (3) Selec