executing-plans

Executes written implementation plans with review checkpoints and verification steps.

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill executing-plans-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/executing-plans
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill executing-plans-cyrus-pinto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a written implementation plan into working code often goes wrong when steps are skipped, verifications are ignored, or blockers are guessed through. This Skill provides a disciplined process for executing a plan in a separate session with critical review and checkpoints. ## Core Features & Use Cases - Critical Plan Review: Loads the plan, identifies questions or concerns, and raises them with your human partner before writing any code. - Step-by-Step Task Execution: Tracks each task with todo states, follows plan steps exactly, and runs the specified verifications. - Controlled Completion: Hands off to the finishing-a-development-branch skill to verify tests and finalize the work. - Use Case: You have a detailed implementation plan from a prior planning session. Use this Skill in a fresh session to execute every task in order, stop and ask when blocked, and complete the development branch cleanly. ## Quick Start Use the executing-plans skill to implement the plan in docs/plans/feature-auth.md and stop if anything is unclear.

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 assistant?

Provide the written plan file and invoke the executing-plans skill. It reviews the plan critically, creates todos for each task, follows the steps exactly, runs the specified verifications, and reports when all tasks are complete.

What should I do before executing an implementation plan?

Ensure you have an isolated workspace, such as a git worktree, and a written plan with bite-sized steps. The skill reviews the plan first and raises any concerns with you before starting implementation.

What happens when plan execution hits a blocker?

Execution stops immediately when a blocker appears, such as a missing dependency, failing test, or unclear instruction. The skill asks for clarification rather than guessing, and never forces through blockers.

Can I execute a plan on the main branch?

No. The skill never starts implementation on the main or master branch without explicit user consent. It recommends creating an isolated workspace using a git worktree before executing any tasks.

When should I use subagent-driven development instead of plan execution?

If your platform supports subagents, such as Claude Code, Codex CLI, Copilot CLI, or Gemini CLI, the skill recommends using subagent-driven development instead, since it handles plan execution more effectively with delegation.