← Back to list
⚡

executing-plans Checked

Use when you have a written implementation plan to execute in a separate session with review chec…
⚡ Productivity skills By obra Version v1.0.5bf4e78 Added 2026-09-07 Updated 2026-09-22 Source ↗
8.0Overall rating
2Views
4Downloads
282.5kStars

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "executing-plans" skill by following the instructions at https://skill123.me/install/executing-plans.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/executing-plans.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.5bf4e78 · 9 KB
📊 Static rating
8.0/10
Trigger
5.0
Structure
8.7
Workflow
7.6
Content
9.0
Engineering
9.0
Security
10.0

Six-dimension rubric with reviewer rationale.

View scorecard ↓
🛡 Dynamic test
—

Not live-tested yet — this skill is rated on static analysis only.

About this skill

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Executing Plans

Documentation

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 (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

1. Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one

2. Read plan file

3. Review critically - identify any questions or concerns about the plan

4. If concerns: Raise them with your human partner before starting

5. If no concerns: Create todos for the plan items 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

Score breakdown

Trigger
5.0
When condition is clear with session boundary, but no When-Not, few synonyms, and the subagent variant boundary lives in body text.
Structure
8.7
Single 64-line file, right-sized, no redundant files, no offload needed.
Workflow
7.6
Three-step process with critical plan review, explicit stop/ask guards, revisit rules, and delegated verification via sub-skills.
Content
9.0
Crisp imperative instructions; few concrete commands since work is plan-driven.
Engineering
9.0
Valid frontmatter; references ../using-superpowers/references/ which is absent from this package.
Security
10.0
No scripts, no network, no injection, no secrets; stop-and-ask rules are safety-positive.
Compact plan-execution skill with clear stop conditions and sub-skill delegation; steps stay high-level and one cross-skill reference path is unresolvable in this package.

Assessment methodology

🧪
AI-assessed
Evaluated by automated analysis across quality, usability, and security dimensions. This is not a substitute for your own review — always inspect a skill before installing it.

Version history

v1.0.5bf4e78 2026-09-22
9 KB

— Refreshed from GitHub obra/superpowers@5bf4e78

v1.0.0 2026-09-07
1 KB

Imported from obra/superpowers@main