executing-plans

Executes written implementation plans task-by-task with review checkpoints and verification steps.

1|Updated Sep 10, 2026
One-click install
npx skills add https://github.com/thienty1207/Hotel_Staff --skill executing-plans-thienty1207
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/thienty1207/Hotel_Staff/tree/main/.baron/core/skills/superpowers/executing-plans
Command: npx skills add https://github.com/thienty1207/Hotel_Staff --skill executing-plans-thienty1207

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Written implementation plans often get executed inconsistently: steps get skipped, verifications are ignored, and blockers are worked around with guesses. This Skill enforces a disciplined process for loading a plan, reviewing it critically, executing every task in order, and stopping to ask for help when something is unclear. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file, identifies questions or concerns, and raises them with the human partner before any work begins. - Structured Task Execution: Converts plan items into todos, marks each in progress, follows steps exactly, and runs the specified verifications before marking tasks complete. - Controlled Completion and Escalation: Hands off to a finishing-a-development-branch workflow after all tasks pass, and stops immediately on blockers, failed verifications, or unclear instructions instead of guessing. - Use Case: You have a multi-task refactoring plan written in a previous session. Invoke this Skill in a fresh session to execute every task in an isolated git worktree, with checkpoints and a clean branch-completion handoff. ## Quick Start Use the executing-plans skill to implement the plan in my plan file, reviewing it critically first and stopping if you hit any blockers.

Frequently Asked Questions about executing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute an implementation plan with an AI coding assistant?

Provide the written plan file and invoke the executing-plans workflow. The assistant reviews the plan critically, creates todos for each task, executes steps exactly as written, runs the specified verifications, and reports when all tasks are complete.

What should happen before executing a written development plan?

The plan should be reviewed critically first: identify questions, gaps, or concerns and raise them with your human partner before starting. An isolated workspace such as a git worktree should also be created or verified so work does not touch the main branch.

Can I execute a plan on the main or master branch?

No. Implementation should never start on main or master without explicit user consent. The recommended approach is to create an isolated git worktree first, then execute the plan's tasks inside that workspace.

What happens when a plan step fails or is unclear?

Execution stops immediately when a blocker appears, such as a missing dependency, a failing test, or an unclear instruction. The assistant asks for clarification rather than guessing, and returns to plan review if the fundamental approach needs rethinking.

When should I use subagent-driven development instead of executing plans directly?

If your platform supports subagents (such as Claude Code, Codex CLI, Copilot CLI, or Gemini CLI), subagent-driven development is recommended over direct plan execution. Direct execution is the fallback for sessions without subagent access.