Skill

executing-plans

Executes written implementation plans step-by-step in git worktrees with critical review, verifications, blocker handling, and finishing sub-skill invocation.

Git

git-workflow

npx claudepluginhub codeape-7/ai-agent-workflowgroup

Tool Access

This skill uses the workspace's default tool permissions.

Preview

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

SKILL.md

Similar Skills

executing-plans

178.4k

Executes written implementation plans step-by-step: critical review, task execution with verifications and checkpoints, git worktrees, stopping at blockers.

superpowers

nbl.executing-plans

Executes written implementation plans step-by-step: critically reviews, marks tasks in_progress/completed, runs verifications, stops at blockers to ask for help. For isolated dev sessions with git worktrees.

nbl.superpowers

executing-plans

2.0k

Executes written development plans: reviews for flaws, implements tasks with verification/tests and per-task git commits, pauses on issues/blockers for human input, reports completion.

superpowers-zh

Stats

Stars10

Forks2

Last CommitApr 26, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

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: When subagents are available (Claude Code / Codex), prefer dispatching per docs/rules/agents.md over inline execution — fresh context per task and two-stage review yield higher-quality output. Use this skill when subagent dispatch is unavailable or batched checkpoint execution is preferred.

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 TodoWrite 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 - REQUIRED: Set up isolated workspace before starting
superpowers:writing-plans - Creates the plan this skill executes
superpowers:finishing-a-development-branch - Complete development after all tasks