CreateSkill

Create and validate new skills with standardized SKILL.md frontmatter and workflow references.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/davdunc/Alvin --skill createskill-davdunc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: CreateSkill
Source: https://github.com/davdunc/Alvin/tree/main/Packs/pai-core-install/src/skills/CreateSkill
Command: npx skills add https://github.com/davdunc/Alvin --skill createskill-davdunc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It provides a canonical framework to create, structure, and validate new skills, ensuring consistency across SKILL.md frontmatter, naming conventions, and workflow references.

Core Features & Use Cases

  • Standardized SKILL.md frontmatter with required fields like name and description.
  • Validation workflows that ensure referenced Workflows exist and the Examples section is present.
  • Guidance for canonicalizing legacy skills to TitleCase and consistent structure.

Quick Start

Create a new skill by following the spec: add a properly named directory, place SKILL.md with the required frontmatter, and implement or reference any Workflows.

Frequently Asked Questions about CreateSkill

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

FAQPage Schema
How do I create valid SKILL.md frontmatter for a new skill?

Validating skill structure requires checking that all referenced Workflows exist and that an Examples section is present for tangible guidance. This governance process ensures your SKILL.md file resolves all dependencies and provides consistent, usable instructions.

How do I canonicalize legacy skills to a consistent structure?

Canonicalizing legacy skills involves converting their names to TitleCase and restructuring their SKILL.md frontmatter to meet standardized validation rules. This blueprint brings older skills into compliance with current naming and workflow reference requirements.

What's the best way to standardize skill creation across multiple authors?

Standardizing skill creation across authors requires enforcing a canonical framework with required SKILL.md frontmatter fields, workflow validation, and structural governance checks. This ensures every author follows identical naming conventions and reference resolution rules.

Do I need an Examples section when creating a new skill?

If workflow validation fails during skill creation, it means referenced Workflows do not resolve or the SKILL.md frontmatter is missing required fields. You must fix the naming structure and ensure all references point to existing workflows.