AI Skill

Pass

Audit score 90

executing-plans

obra/superpowers

Execute a written implementation plan with review checkpoints and task verification.

What is executing-plans?

This skill guides you through executing a pre-written implementation plan in a dedicated session. Load the plan, review it critically, execute each task with verification steps, then hand off to the finishing-a-development-branch skill. Use it when you have a detailed plan ready to implement.

Load and critically review a written plan before starting execution
Track task progress with in_progress and completed status markers
Execute each task step-by-step with embedded verification checks
Stop immediately when hitting blockers instead of guessing
Integrate with git-worktrees for isolated workspace management
Hand off to finishing-a-development-branch skill for final verification and merge

How to install executing-plans

npx skills add https://github.com/obra/superpowers --skill executing-plans

Prerequisites

A written implementation plan file (created by superpowers:writing-plans)
Access to superpowers:using-git-worktrees skill for workspace isolation
Access to superpowers:finishing-a-development-branch skill for completion
Git repository with ability to create worktrees or branches

Claude Code

Cursor

Windsurf

Cline

How to use executing-plans

1.Announce you are using the executing-plans skill
2.Read and load the implementation plan file
3.Review the plan critically and identify any questions or concerns
4.Raise concerns with your human partner before proceeding if needed
5.Create todos from the plan items
6.For each task: mark as in_progress, follow steps exactly, run verifications, mark completed
7.Stop immediately if you hit a blocker and ask for clarification
8.After all tasks complete, announce you are using finishing-a-development-branch skill

Use cases

Good for

Implementing a multi-step feature plan created in a previous session
Executing a refactoring plan with defined verification steps at each stage
Following a detailed bug-fix plan with test checkpoints
Resuming work on a plan that was paused and needs completion
Coordinating implementation across multiple related tasks with dependencies

Who it's for

Developers executing pre-planned features or fixes
Teams using plan-then-execute workflows
Anyone needing structured task tracking during implementation
Projects requiring verification checkpoints between steps

executing-plans FAQ

What should I do if I encounter a blocker while executing a task?

Stop immediately and ask your human partner for clarification. Do not guess or try to work around the blocker. Common blockers include missing dependencies, failing tests, unclear instructions, or critical gaps in the plan.

Can I skip verification steps to move faster?

No. Verification steps are required and must be run as specified in the plan. They catch issues early and prevent compounding problems.

What if the plan needs updating during execution?

Raise the issue with your human partner. If the plan is updated, return to Step 1 (Load and Review Plan) to review the changes before continuing.

Do I need subagent support to use this skill?

This skill works without subagents, but quality is significantly higher with subagent support. If subagents are available, use superpowers:subagent-driven-development instead.

What happens after I complete all tasks?

Announce that you are using the finishing-a-development-branch skill and follow that skill to verify tests, present options, and execute the final choice for completing the work.

Full instructions (SKILL.md)

Source of truth, from obra/superpowers.

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 (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in ../using-superpowers/references/). If subagents are available, use superpowers:subagent-driven-development instead of this skill.

The Process

Step 1: Load and Review Plan

Read plan file
Review critically - identify any questions or concerns about the plan
If concerns: Raise them with your human partner before starting
If no concerns: Create todos for the plan items and proceed

Step 2: Execute Tasks

For each task:

Mark as in_progress
Follow each step exactly (plan has bite-sized steps)
Run verifications as specified
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