From empire-dev
Decomposes overwhelming dev tasks into right-sized, independent units by diagnosing failure modes like excessive size, unclear starts, dependencies, and scope creep using INVEST, vertical slicing.
npx claudepluginhub marcoskichel/empire --plugin empire-devThis skill uses the workspace's default tool permissions.
<section id="core">
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Guides code writing, review, and refactoring with Karpathy-inspired rules to avoid overcomplication, ensure simplicity, surgical changes, and verifiable success criteria.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Share bugs, ideas, or general feedback.
The goal isn't more tasks — it's the right tasks. Small enough to understand completely. Large enough to deliver value. Independent enough to avoid blocking.
| Cognitive Limit | Threshold | Implication |
|---|---|---|
| Working memory | 7±2 items | Max concepts per task |
| Context switch recovery | 23 minutes | Minimize task switching |
| Files examined | 15-20 max | Bound task scope |
| Days before completion drops | 2-3 days | Keep tasks under this |
| Duration | Completion Rate |
|---|---|
| < 2 hours | 95% |
| 2-4 hours | 90% |
| 4-8 hours (1 day) | 80% |
| 2-3 days | 60% |
| 1 week | 35% |
| > 2 weeks | <10% |
Symptoms: Estimates range wildly. Can't hold all requirements in mind. More than 7 concepts to track.
Interventions: Apply INVEST criteria: Independent, Negotiable, Valuable, Estimable, Small, Testable. Use vertical slicing (each slice independently deployable). Apply walking skeleton (minimal end-to-end first).
Symptoms: Multiple valid starting points. Paralysis. Everything seems connected.
Interventions: Front-load risk: start with highest-uncertainty items. Tracer bullet: minimal proof of concept. Find the walking skeleton: thinnest slice through all layers.
Symptoms: "Blocked on X." Diamond dependencies. Coordination overhead.
Interventions: Interface contracts: define API, mock while implementing. Feature flags: deploy independently, enable when ready. Branch by abstraction: create layer, swap implementations.
Symptoms: "Almost done" forever. No way to verify completion.
Interventions: Define acceptance criteria (Given / When / Then). Time-box to force prioritization. Define explicit out-of-scope items.
Symptoms: Task keeps growing. "While we're here" additions.
Interventions: Freeze scope, spawn new tasks for additions. Define minimum viable version. Ship smallest version that solves the problem.
Symptoms: Estimate variance > 4x. New technology. Multiple viable approaches.
Interventions: Time-boxed spike (8 hours max). Deliverables: options, POC, trade-offs, revised estimate. Spike-then-implement pattern.
Vertical Slicing (preferred for features) — each slice is independently deployable and delivers value end-to-end.
Feature: User Profile Management
Slice 1: View basic profile (4h)
- UI: Profile display
- API: GET /profile
- DB: Read profile
Slice 2: Edit profile name (6h)
- UI: Edit dialog
- API: PATCH /profile/name
- DB: Update profile
Walking Skeleton (for new systems) — minimal end-to-end first, then flesh out incrementally.
1. Hello World page
2. One GET endpoint
3. Single table
4. Basic deploy
Tracer Bullet (validate architecture) — minimal proof that components can communicate.
Step 1: Minimal Service A (1h) - Hardcoded response
Step 2: Minimal Service B (1h) - Simple transformation
Step 3: Integrate (2h) - Prove they communicate
→ 4 hours to decision point
Fibonacci sizing:
| Points | Meaning |
|---|---|
| 1 | Trivial, < 1 hour |
| 2 | Simple, 1-2 hours |
| 3 | Standard, 2-4 hours |
| 5 | Moderate, 4-8 hours |
| 8 | Complex, 1-2 days |
| 13 | Very complex, 2-3 days |
| 21 | Too large, must decompose |
Three-point estimation:
O = Optimistic (everything perfect)
L = Likely (normal case)
P = Pessimistic (major issues)
PERT estimate: (O + 4L + P) / 6
Before starting any task, verify:
Any "no" → further decomposition needed.
Big Bang Delivery — building complete system before any delivery. Fix: vertical slices, incremental value.
Technical Tasks Without Value — "Set up database," "Create service layer." Fix: include in feature tasks: "User can view products (includes DB)."
Research Forever — unbounded investigation. Fix: time-boxed spikes with deliverables.
Perfect Decomposition — over-analyzing before starting. Fix: decompose next 2 weeks only; details for later work emerge.