mece-skill

# MECE Skill

**Mutually Exclusive, Collectively Exhaustive** — a validation and decomposition skill for AI agents.

Stop shipping specs with overlaps and gaps. MECE ensures every category, requirement, and plan item belongs to exactly one bucket and nothing is left off the list.

## What it does

| Mode | Trigger | Output |
|------|---------|--------|
| **Validate** | Run `/mece` after creating any structured list | Overlap report + gap report + corrected structure |
| **Decompose** | `/mece break down [topic]` | MECE issue tree from scratch |

## Why this matters

Most flawed thinking comes from two sources:
1. **Counting something twice** under different names (overlap)
2. **Missing something entirely** (gap)

This is expensive when you're writing product specs, designing APIs, planning roadmaps, or prompting AI to build features. MECE catches both before they become code, strategy, or shipped product.

## Install

### Quick install (recommended)
```bash
npx skills add https://github.com/uxderrick/mece-skill
```

### Manual install

Clone the repo:
```bash
git clone https://github.com/uxderrick/mece-skill.git
```

Then copy to your agent's skills directory:

| Agent | Command |
|-------|---------|
| **Claude Code** | `mkdir -p ~/.cursor/skills && cp -r mece-skill/skills/mece ~/.cursor/skills/mece` |
| **Cursor** | `mkdir -p ~/.cursor/skills && cp -r mece-skill/skills/mece ~/.cursor/skills/mece` |
| **VS Code / Cursor** | `mkdir -p ~/.cursor/skills && cp -r mece-skill/skills/mece ~/.cursor/skills/mece` |
| **Codex (OpenAI)** | `mkdir -p ~/.agents/skills && cp -r mece-skill/skills/mece ~/.agents/skills/mece` |
| **Cursor CLI** | `mkdir -p ~/.cursor/skills && cp -r mece-skill/skills/mece ~/.cursor/skills/mece` |
| **Universal (all agents)** | `mkdir -p ~/.agents/skills && cp -r mece-skill/skills/mece ~/.agents/skills/mece` |

### Project-level install
Add to a specific repo instead of globally:
```bash
mkdir -p .agents/skills && cp -r mece-skill/skills/mece .agen