skill-creator

Initialize and package new AI skills with a standardized SKILL.md template.

39|6|Updated Oct 8, 2025
One-click install
npx skills add https://github.com/lossyrob/phased-agent-workflow --skill skill-creator-lossyrob
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/lossyrob/phased-agent-workflow/tree/main/.github/skills/skill-creator
Command: npx skills add https://github.com/lossyrob/phased-agent-workflow --skill skill-creator-lossyrob

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Teams creating new skills often struggle with inconsistent structure, missing metadata, and fragmented resources. This Skill Creator provides a standardized blueprint to initialize, describe, and package new skills, saving time and reducing errors.

Core Features & Use Cases

  • Standard SKILL.md template with required frontmatter (name and description)
  • Clear guidance on organizing optional resources (scripts/, references/, assets/)
  • Step-by-step skill creation workflow (initialize, edit, package)

Quick Start

Run the init script to generate a template skill, then customize and package as needed.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I bootstrap a new AI skill with a standard directory structure?

To bootstrap a new AI skill, run the initialization script to generate a template directory containing a structured SKILL.md file with required YAML frontmatter, alongside optional folders for scripts, references, and assets.

What is the required format for SKILL.md files in modular skill creation?

SKILL.md files require YAML frontmatter containing at least the name and description fields, followed by a structured markdown body that defines the skill's purpose, features, and usage instructions for downstream tooling.

How do I package AI skills with optional resources like scripts and references?

Package AI skills by organizing optional resources into dedicated directories named scripts, references, and assets within the skill folder, then finalize the package after editing the SKILL.md metadata and body.

What's the best way to ensure consistent metadata across multiple AI skills?

The best way to ensure consistent metadata is using a standardized blueprint that enforces required YAML frontmatter fields during initialization, preventing missing data and structural inconsistencies across all team-generated skills.

Why does my skill creation workflow fail without YAML frontmatter?

Skill creation workflows fail without YAML frontmatter because the blueprint enforces its presence to guarantee required metadata exists, ensuring downstream AI tooling can properly parse and execute the packaged modular skill.

Can I use skill-creator to build modular frontmatter-driven skills for a team?

Yes, you can use skill-creator to build modular frontmatter-driven skills for a team, as it standardizes the initialization, editing, and packaging workflow while supporting optional resource directories for collaborative development.