executing-plans

Executes written implementation plans in reviewed batches with verification checkpoints.

Updated Nov 1, 2024
One-click install
npx skills add https://github.com/mlorentedev/dotfiles --skill executing-plans-mlorentedev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/mlorentedev/dotfiles/tree/main/harness/skills/executing-plans
Command: npx skills add https://github.com/mlorentedev/dotfiles --skill executing-plans-mlorentedev

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 the executor guesses past blockers. This Skill enforces a disciplined loop: load the plan, review it critically, execute tasks in small batches, and report for feedback before continuing. ## Core Features & Use Cases - Critical plan review: Reads the full plan file first and raises questions or concerns with the user before any execution begins. - Batched execution: Works through tasks in batches of three by default, marking each task in_progress and completed, and running the verifications specified in the plan. - Stop-on-blocker discipline: Halts immediately on missing dependencies, failing tests, unclear instructions, or repeated verification failures instead of guessing. - Use Case: After generating an implementation plan with a planning skill, hand the plan file to this Skill to implement it task by task, pausing after each batch so you can review the changes and verification output. ## Quick Start Ask the assistant to execute the implementation plan in your plan file, working in batches and pausing for your feedback after each batch.

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 plan file and let the skill load and review it first, raising any concerns before starting. It then executes tasks in batches of three, runs the verifications specified in the plan, and pauses after each batch for your feedback.

How to run a coding plan step by step without skipping tests?

The skill follows the plan's steps exactly and runs each task's specified verifications before marking it completed. After all tasks finish, it runs the full test suite and reports completion with evidence.

What happens when plan execution hits a blocker or failing test?

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 also stops when verification fails repeatedly.

Can I review changes between batches during plan execution?

Yes. After each batch completes, the skill shows what was implemented along with verification output and waits for feedback. You can request changes before the next batch begins.

When should I not use batch plan execution?

Avoid it when the plan has critical gaps or when you intend to work directly on main or master without explicit consent, since the skill refuses to start there. Plans with unclear instructions should be clarified first.