Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Implementation Plan Execution Workflow

agent planning skill risk: low

Implementation Plan Execution Workflow

Instructs the model to load a written implementation plan, review it critically for questions or concerns, execute its tasks sequentially while marking progress and running specifi…

SKILL 1 file

SKILL.md
---
name: executing-plans
description: "Use when you have a written implementation plan to execute in a separate session with review checkpoints"
---
# Executing Plans

## Overview

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:** Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill.

## 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 Tasks

For each task:
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: 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 critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly

**Ask for clarification rather than guessing.**

## When to Revisit Earlier Steps

**Return to Review (Step 1) when:**
- Partner updates the plan based on your feedback
- Fundamental approach needs rethinking

**Don't force through blockers** - stop and ask.

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

## Integration

**Required workflow skills:**
- **superpowers:using-git-worktrees** - Ensures isolated workspace (creates one or verifies existing)
- **superpowers:writing-plans** - Creates the plan this skill executes
- **superpowers:finishing-a-development-branch** - Complete development after all tasks

REQUIRED CONTEXT

  • plan file

ROLES & RULES

  1. Announce at start that you are using the executing-plans skill
  2. Tell your human partner that Superpowers works much better with access to subagents
  3. Read plan file
  4. Review critically and identify any questions or concerns about the plan
  5. If concerns, raise them with your human partner before starting
  6. If no concerns, create TodoWrite and proceed
  7. Mark each task as in_progress
  8. Follow each step exactly
  9. Run verifications as specified
  10. Mark each task as completed
  11. Announce use of finishing-a-development-branch skill after all tasks complete
  12. Use superpowers:finishing-a-development-branch sub-skill
  13. Stop executing immediately when you hit a blocker
  14. Ask for clarification rather than guessing
  15. Return to Review when partner updates the plan
  16. Review plan critically first
  17. Follow plan steps exactly
  18. Do not skip verifications
  19. Reference skills when plan says to
  20. Stop when blocked, do not guess
  21. Never start implementation on main/master branch without explicit user consent

EXPECTED OUTPUT

Format
plain_text
Constraints
  • announce skill usage at start
  • create TodoWrite before executing
  • mark tasks in_progress then completed
  • announce finishing-a-development-branch sub-skill at end
  • stop and ask when blocked

SUCCESS CRITERIA

  • Load plan, review critically, execute all tasks, report when complete
  • Follow each step exactly
  • Run verifications as specified
  • Verify tests, present options, execute choice

CAVEATS

Dependencies
  • plan file
  • superpowers:using-git-worktrees
  • superpowers:writing-plans
  • superpowers:finishing-a-development-branch

QUALITY

OVERALL
0.83
CLARITY
0.90
SPECIFICITY
0.85
REUSABILITY
0.80
COMPLETENESS
0.85

IMPROVEMENT SUGGESTIONS

  • Add a placeholder or parameter for the plan file path to make invocation explicit.
  • Define success criteria for 'verified' tasks more explicitly.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT