executing-plans

Execute written implementation plans with per-task verification and safe completion.

Updated Apr 30, 2026
One-click install
npx skills add https://github.com/koseki2580/skills --skill executing-plans-koseki2580
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/koseki2580/skills/tree/main/skills/executing-plans
Command: npx skills add https://github.com/koseki2580/skills --skill executing-plans-koseki2580

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents sloppy implementation by turning a written plan into a controlled execution workflow with critical review, verification at each step, and safe completion handling.

Core Features & Use Cases

  • Plan loading and critical review: Reads the written plan, identifies questions or concerns, and pauses to resolve them before proceeding.
  • Step-by-step task execution: Executes each task by following bite-sized plan steps exactly, with in-progress/completed tracking and specified verifications.
  • Safe completion workflow: Finishes using branch/PR-oriented completion (via a required sub-skill) or, for spikes/explorations, runs the plan’s own verification and reports artifacts without auto-discarding.

Quick Start

Use the executing-plans skill to implement the plan you already wrote, with verification after each task and safe completion after everything passes.

Frequently Asked Questions about executing-plans

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

FAQPage Schema
How do I execute a development plan without missing verification steps?

To execute a development plan with verification, load the written plan, conduct a critical pre-execution review, and run specified verifications after each tracked task. This enforces plan granularity exactly and pauses on blockers to prevent sloppy implementation.

What is the best way to handle blockers when implementing a written task plan?

The best way to handle blockers during plan execution is stopping for clarification when instructions are unclear or verification fails. The workflow pauses execution immediately, ensuring issues are resolved before moving to the next bite-sized plan step.

Can I run spike-style explorations without auto-discarding the verification results?

Yes, spike-style explorations run the plan's own verification and report artifacts without auto-discarding. This allows safe exploratory implementation while still completing via branch or PR workflows for standard development tasks.

How do I ensure my implementation plan is ready for step-by-step execution?

Ensuring a plan is ready for step-by-step execution requires a critical pre-execution review. The workflow reads the written plan, identifies questions or concerns, and pauses to resolve them before proceeding with task tracking and implementation.

Does plan execution support branch and PR-oriented completion workflows?

Yes, plan execution supports branch and PR-oriented completion workflows through a required sub-skill. This ensures safe completion after all specified verifications pass, properly handling development work through merge or pull request workflows.