executing-plans

Executes written implementation plans in batches with review checkpoints between batches.

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/tottenjordan/me-skittles --skill executing-plans-tottenjordan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/tottenjordan/me-skittles/tree/main/gemini/executing-plans
Command: npx skills add https://github.com/tottenjordan/me-skittles --skill executing-plans-tottenjordan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Executing a multi-task implementation plan in one shot often leads to drift, skipped verifications, and undetected errors. This Skill enforces disciplined batch execution with human review checkpoints so plans are followed exactly and issues surface early. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and raises questions or concerns with the human partner before writing any code. - Batched Task Execution: Executes tasks in batches (default first 3), marking progress with TodoWrite and running each specified verification. - Checkpoint Reporting: Reports implemented work and verification output between batches, then waits for feedback before continuing. - Use Case: You have a written implementation plan for a new feature. The agent reviews it, implements the first three tasks, shows you the test output, and pauses for your approval before proceeding to the next batch. ## Quick Start Use the executing-plans skill to implement the plan in docs/feature-plan.md, executing tasks in batches and pausing for my review between batches.

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 agent?▼

Load the plan file, review it critically for gaps or concerns, then execute tasks in batches of three with TodoWrite tracking. After each batch, report what was implemented along with verification output and wait for feedback before continuing.

How many tasks should be executed per batch when implementing a plan?▼

The default is the first three tasks per batch. Each task is marked in_progress, its steps are followed exactly, verifications are run, and it is marked completed before moving to the next task in the batch.

What should an agent do when blocked during plan execution?▼

Stop executing immediately when hitting a blocker such as a missing dependency, failing test, or unclear instruction. Ask the human partner for clarification rather than guessing or forcing through the blocker.

When should a plan be reviewed again during execution?▼

Return to the plan review step when the human partner updates the plan based on feedback or when the fundamental approach needs rethinking. Do not continue executing an outdated or flawed plan.

What happens after all plan tasks are completed?▼

After all tasks complete and verifications pass, the workflow hands off to the finishing-a-development-branch sub-skill, which verifies tests, presents completion options, and executes the chosen option.