executing-plans

# Executing Plans

## Overview

Load plan, review critically, execute all tasks sequentially, report results.

**Core principle:** Continuous execution with stops only for blockers or failures.

**Announce at start:** "I'm using the executing-plans skill to implement this plan."

## The Process

### Step 1: Load and Review Plan
1. Read plan file
2. Review critically - identify any questions or concerns about the plan
3. If concerns: Raise them with your human partner before starting
4. If no concerns: Create TodoWrite and proceed

### Step 2: Execute All Tasks

For each task sequentially:
1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. Mark as completed

### Step 3: Capture Out-of-Scope Ideas

During implementation, you'll often discover logical next steps that aren't in scope:
- "This would be cleaner if we also refactored X"
- "Users will probably want Y after this ships"
- "There's a performance improvement we could make here"

**Don't derail current work.** Instead:
1. Note the idea
2. Add it to the appropriate document's "Future Ideas" section:
   - Game-related ideas → `docs/GDD.md`
   - Tool/infrastructure ideas → `docs/PRD.md`
   - If only one exists, use that one
3. Continue with current task

### Step 4: Final Report

After all tasks complete:
- Show what was implemented
- Show verification output
- List any out-of-scope ideas captured (if any)
- Summarize any issues encountered along the way
- Say: "All tasks complete. Ready for feedback."

### Step 5: Complete Development

After all tasks complete and verified:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice

## When to Stop and Ask for Help

**STOP executing immediately when:**
- Hit a blocker (missing dependency, test fails, instruction unclear)
- Plan has