skills.rest
kimprobably
kimprobablyCOMMUNITY
Explore all skills by this author →
GitHub

executing-plans

Execute written implementation plans with review checkpoints and verification.

Updated May 13, 2026
Search Tags:#debugging#development workflow#plan execution#checkpointing#handoff#task verification#stop-and-ask
One-click install
npx skills add https://github.com/kimprobably/maestro-os --skill executing-plans-kimprobably
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/kimprobably/maestro-os/tree/main/hermes/distribution/maestro-operator/skills/executing-plans
Command: npx skills add https://github.com/kimprobably/maestro-os --skill executing-plans-kimprobably

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns a written implementation plan into a controlled execution process with explicit review, step-by-step task completion, and clear rules for when to stop and ask for help.

Core Features & Use Cases

  • Plan loading and critical review: Reads the plan first, identifies questions or concerns, and escalates them before starting execution.
  • Checkpointed task execution: Runs each task in order, marking progress (in_progress → completed) while following the plan’s bite-sized steps and verification requirements.
  • Safe completion via a required finishing step: Hands off to a dedicated finishing skill that verifies work and presents options instead of continuing ad hoc.

Quick Start

Use the executing-plans skill to implement the provided written plan in a separate session with review checkpoints and verification before finishing.

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 with checkpoints and verification?▼

Plan execution with checkpoints works by loading a written implementation plan, critically reviewing it for concerns, running tasks sequentially, and stopping immediately on blockers or failed verifications before final handoff.

What is the best way to stop an AI agent from drifting off a written implementation plan?▼

Checkpointed plan execution prevents drift by tracking task state from in_progress to completed, enforcing verification requirements, and stopping immediately on blockers or failed verifications instead of continuing ad hoc.

How does task state tracking work during step-by-step plan execution?▼

Task state tracking works by marking each task sequentially from in_progress to completed while following bite-sized steps and verification requirements, halting execution immediately if verification fails or a blocker is encountered.

Do I need a written plan before starting checkpointed task execution?▼

Yes, checkpointed task execution requires a written implementation plan loaded beforehand. The process reads the plan first, identifies questions or concerns, and escalates them before starting any execution to ensure controlled implementation.

What happens when a verification checkpoint fails during development workflow execution?▼

When a verification checkpoint fails during development workflow execution, the process stops immediately and asks for help. It does not continue ad hoc but instead enforces a handoff to a dedicated finishing skill for final verification and choice.

Related Skills

Explore More Software Engineering Skills→
Jorge-IvanJorge-Ivan
1

executing-plans

Execute implementation plans with verification checkpoints and error handling.

Community
Advanced
alexsandrocruzalexsandrocruz
6

executing-plans

Execute implementation plans in batches with verification checkpoints.

Community
Basic
MihaiOnSoftwareMihaiOnSoftware
1

when-stuck

Apply the STOP → THINK → INVESTIGATE → ASK framework to resolve blockers.

Community
Basic
FerroxLabsFerroxLabs
21

ferrox-quick

Execute small ad hoc tasks with atomic commits and state tracking.

Community
Intermediate