create-skill

Create and manage reusable AI agent skills with structured SKILL.md files.

Updated Aug 23, 2026

Search Tags:#workflow #templates #validation #packaging #skill-creation #agent-skills #AskUserQuestion

Ready to run

npx skills add https://github.com/Oxilith/CopilotSkills --skill create-skill-oxilith

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: create-skill
Source: https://github.com/Oxilith/CopilotSkills/tree/main/.agentskills/skills/create-skill
Command: npx skills add https://github.com/Oxilith/CopilotSkills --skill create-skill-oxilith

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill guides the creation and management of modular AI agent skills that extend capabilities with workflows, knowledge, and tooling, reducing duplication and enabling consistent quality.

Core Features & Use Cases

Structured frontmatter and instructional body for SKILL.md
Resource scaffolding with optional scripts/, references/, and assets/ directories
Validation and packaging workflows to prepare skills for deployment or reuse
Use cases: creating new skills, updating existing ones, shipping a catalog of skills across teams

Quick Start

Run a pre-creation interview to gather requirements using AskUserQuestion.
Initialize a new skill: scripts/init_skill.py <skill-name> (creates in .agentskills/skills/ by default).
Edit SKILL.md to fill name/description and add operational guidance; add resources as needed.
Validate the skill: scripts/quick_validate.py <path/to/skill>.
Package for distribution: scripts/package_skill.py <path/to/skill> [output-dir].

Frequently Asked Questions about create-skill

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

FAQPage Schema

How do I create reusable AI agent skills with proper validation and packaging?▼

To create reusable AI agent skills, use a structured workflow that gathers requirements, scaffolds directories, fills SKILL.md frontmatter, and validates the package before deployment. This ensures consistent quality and reduces duplication across teams.

What is included in the scaffolding when initializing a new agent skill?▼

Scaffolding a new agent skill creates a default directory structure including a SKILL.md file for instructions and frontmatter, alongside optional folders for scripts, references, and assets to bundle resources directly with the skill.

Does this skill creation workflow require specific frontmatter for the SKILL.md file?▼

Yes, the skill creation workflow requires specific frontmatter in the SKILL.md file, mandating at minimum a name and description to define the skill's identity and scope before validation and packaging can proceed.

Can I update existing AI agent skills or is this only for building new ones?▼

You can update existing AI agent skills by editing their SKILL.md operational guidance, adding new bundled resources, and re-running the validation and packaging workflows to prepare the updated version for reuse.

What's the best way to validate an AI agent skill before distribution?▼

The best way to validate an AI agent skill before distribution is to run a dedicated validation script against the skill's directory to check frontmatter requirements and structural integrity prior to packaging.

Why do I need to run a pre-creation interview before building an agent skill?▼

You need to run a pre-creation interview to accurately gather requirements and define the skill's scope, ensuring the scaffolding, resources, and SKILL.md content precisely match the intended workflow before initialization.