write-skill

Creates agent skill directories and entrypoint SKILL.md files.

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/lukeylias/lukeydev --skill write-skill-lukeylias
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: write-skill
Source: https://github.com/lukeylias/lukeydev/tree/main/skills/write-skill
Command: npx skills add https://github.com/lukeylias/lukeydev --skill write-skill-lukeylias

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you design and package a new agent skill without missing the structure, clarity, or workflow details needed for reliable reuse.

Core Features & Use Cases

  • Requirements Gathering: Captures the task domain, target use cases, and whether the skill needs scripts or only instructions.
  • Skill Drafting: Produces a compact SKILL.md with clear process, rules, and error handling guidance.
  • Structure Validation: Ensures the skill design is reviewed with the user before it is saved, reducing rework.
  • Use Case: Use this when you want to turn a vague automation idea into a well-scoped skill directory that another agent can activate confidently.

Quick Start

Ask the write-skill assistant to help design a new skill for your task, then answer its questions about scope, use cases, scripts, and composition with other skills.

Frequently Asked Questions about write-skill

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

FAQPage Schema
How do I create a new agent skill from a vague automation idea?

To create a new agent skill, define the task domain and target use cases to generate a compact SKILL.md file with clear process rules, error handling guidance, and concise frontmatter for reliable agent reuse.

What is the required structure for a valid SKILL.md entrypoint file?

A valid SKILL.md entrypoint requires concise frontmatter, under-100-line instructions, and optional references or scripts only when justified, ensuring the agent workflow has clear process and error handling guidance.

How do I validate instruction design and scope before saving an agent skill?

Validate instruction design by reviewing the drafted skill directory structure and scope with the user before saving, confirming use cases and composition with existing skills to reduce rework.

Do I need to include scripts in my skill directory, or are instructions enough?

Scripts are optional in a skill directory; you can use only instructions if justified, capturing requirements during the design phase to determine whether the automation workflow needs scripts.

What is the best way to package an agent workflow for reliable reuse?

The best way to package an agent workflow is by creating a well-scoped skill directory with a drafted SKILL.md, ensuring structure validation and composition with existing skills before finalizing.

Can I compose a new skill with existing skills in the same directory?

Yes, you can compose a new skill with existing skills by defining the scope and use cases during requirements gathering, ensuring the agent workflow integrates smoothly before the structure is saved.