---
name: executing-plans
description: Use when you have a written implementation plan to execute in a separate session with review checkpoints
---

# Executing Plans

Audience: AI coding agents.

Load plan, review critically, execute all tasks, report when complete.

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

**Note:** For parallel task execution with subagents, use /ship instead. For multi-wave plans (>1 wave/phase OR any wave has parallel tasks), use /run-plan instead. This skill = single-wave inline sequential execution only.

## Process

### Step 1: Load and Review Plan
1. Read plan file
2. Review critically — identify questions or concerns
3. Concerns → raise with human partner before starting
4. No concerns → create TodoWrite, proceed

### Step 2: Execute Tasks

Per task:
1. Mark in_progress
2. Follow each step exactly
3. Run verifications as specified
4. Mark completed

### Step 3: 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 finishing-a-development-branch
- Follow that skill to verify tests, then auto-merge to main (no user prompt needed)

## When to Stop

**STOP immediately when:**
- Blocker (missing dependency, test fails, unclear instruction)
- Plan has critical gaps preventing start
- Don't understand an instruction
- Verification fails repeatedly

**Ask for clarification. NEVER guess.**

## When to Revisit Step 1

- Partner updates plan based on feedback
- Fundamental approach needs rethinking

**NEVER force through blockers.**

## Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Stop when blocked, never guess
- NEVER start implementation on main/master without explicit user consent

## Integration

- **using-git-worktrees** — REQUIRED: set up isolated workspace before starting
- **/plan** — creates the plan this skill executes
- **finishing-a-development-branch** — complete development after all tasks