---
description: Systematic pre-implementation readiness assessment
argument-hint: <feature or task to prepare for>
allowed-tools: Task, Read, Write, Edit, Glob, Grep, Bash
---

Prepare to implement: $ARGUMENTS

## Instructions

Load the `prepare` skill, then follow its protocol to produce either:

1. **High confidence (>= 80%)**: An implementation brief with clear steps
2. **Gaps remain (< 80%)**: A prioritized gap list with resolution actions

### What This Command Does

1. **Scope the target** - Parse what's being prepared for
2. **Map dependencies** - Upstream, downstream, adjacent patterns
3. **Audit prerequisites** - What must be fixed first vs. alongside
4. **Inventory design decisions** - Questions that need answers
5. **Score confidence** - Per-dimension evidence-based assessment
6. **Produce output** - Brief or gap list based on readiness

### When to Use

Use `/prepare` when:
- About to implement a feature and need confidence the path is clear
- A task has been discussed/designed but not yet validated against the codebase
- Transitioning from planning to implementation and want to catch gaps early
- Picking up work someone else planned and need to verify assumptions

### When NOT to Use

- Exploring what to build (use `/thinkthrough`)
- Debugging an issue (use `/root-cause`)
- Investigating how something works (use `/investigate` or `/trace-feature`)
- The task is trivial and needs no preparation

### Expected Output

Either an **Implementation Brief** (ready to implement) or a **Gap List** (not ready, here's what's missing).

## Critical Rules

- NEVER claim ready without reading dependency source code
- NEVER skip prerequisite audit
- NEVER produce brief with unresolved design decisions
- ALWAYS find pattern templates before assessing readiness
- ALWAYS let minimum dimension score determine overall confidence