prompt

Create executable task prompts with scope boundaries and verification steps.

Updated May 23, 2026

Search Tags:#prompt engineering #verification #acceptance criteria #coding agents #scope boundaries #task prompts

Ready to run

npx skills add https://github.com/matthewharwood/dean-n-dean --skill prompt-matthewharwood

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prompt
Source: https://github.com/matthewharwood/dean-n-dean/tree/main/.agents/skills/prompt
Command: npx skills add https://github.com/matthewharwood/dean-n-dean --skill prompt-matthewharwood

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you create clear, executable task prompts for coding agents so they don’t guess scope, miss acceptance criteria, or write to the wrong places.

Core Features & Use Cases

Prompt-first workflow for creating review, split, or task prompts under ./prompts/ with consistent structure.
Explicit scope & boundaries (in/out) to prevent drift into adjacent concerns.
Verification-centered prompts that require concrete checks (tests, lint, typecheck, expected outputs) before the work is considered done.

Quick Start

Use the prompt skill to create a new prompt file for a requested feature or refactor, ensuring it includes scope boundaries and a verification step, saving it under ./prompts/.

Frequently Asked Questions about prompt

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

FAQPage Schema

How do I write coding prompts with clear scope boundaries for AI agents?▼

Coding prompts with clear scope boundaries require explicit in/out sections to prevent scope drift and concrete acceptance criteria. Standardizing task prompts ensures executing agents understand exact deliverables and avoid guessing project scope.

What should task prompts for coding agents include to ensure reliable execution?▼

Task prompts for coding agents should include explicit scope boundaries, acceptance criteria, output paths, and non-negotiable verification steps like tests or lint checks. This structured approach guarantees the agent can reliably reach a defined done state.

How do I create verification-centered prompts for coding agent workflows?▼

Verification-centered prompts require concrete checks such as tests, lint, typecheck, and expected outputs before work is considered done. Defining these non-negotiable verification steps within the prompt ensures coding agents validate their own results against acceptance criteria.

How do I standardize prompt creation for coding agents under a prompts directory?▼

Standardizing prompt creation involves applying a strict template with literal-readability, scope sections, and subagent guidance, then saving files under ./prompts/ with correct numbering and naming after user approval to maintain consistent task prompt workflows.

Why do coding agents drift outside the original task scope during execution?▼

Coding agents drift outside task scope when prompts lack explicit in/out boundaries and acceptance criteria. Adding strict scope boundaries to task prompts prevents agents from wandering into adjacent concerns and missing the required done state.

Can I split large feature requests into separate task prompts for coding agents?▼

You can split large feature requests into separate task prompts using a prompt-first workflow. This process creates review, split, or task prompts under ./prompts/ with consistent structure, ensuring each subagent receives clear scope and verification steps.