skill-creator

Plan, design, and implement Codex Skills with templates and validators.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/UntLab/codex --skill skill-creator-untlab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/UntLab/codex/tree/main/config/codex-skills/.system/skill-creator
Command: npx skills add https://github.com/UntLab/codex --skill skill-creator-untlab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Codex Skills are modular, self-contained instructions that extend Codex capabilities; this Skill provides a structured approach and boilerplate templates to create or update Skills efficiently, ensuring consistency and governance.

Core Features & Use Cases

  • Structured templates and frontmatter guidelines for new Skills.
  • Reusable resource scaffolding (scripts, references, assets) and workflow patterns.
  • Guidance for initialization, editing, validation, and forward-testing of Skills.

Quick Start

Follow the Skill Creation Process to initialize a new skill using the included templates and scripts.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create Codex skills with consistent frontmatter and resource organization?

To create Codex skills with consistent frontmatter, use structured templates and built-in validators that enforce metadata integrity and resource scaffolding across the full skill lifecycle.

What is the best way to scaffold automation workflows and references for a new skill?

The best way to scaffold automation workflows is using reusable boilerplate templates that initialize scripts, references, and assets, ensuring self-contained instructions that extend capabilities safely.

Do I need PyYAML to validate skill frontmatter and workflows?

Yes, you need PyYAML installed to parse and validate skill frontmatter, as it provides the underlying validation mechanism for ensuring metadata integrity during the skill creation process.

How does forward-testing work when updating existing Codex skills?

Forward-testing works by applying built-in validators and optional subagent validation to safely iterate on existing skills, ensuring updates do not break frontmatter integrity or resource organization.

Can I use this skill creator to initialize templates for software engineering automation?

Yes, you can use this skill creator to initialize software engineering automation templates, providing structured scaffolding for scripts, references, and assets tailored for software engineering workflows.

Why does my skill validation fail when the frontmatter is incorrectly formatted?

Skill validation fails when frontmatter is incorrectly formatted because the built-in validators strictly enforce frontmatter integrity, requiring precise metadata structure to maintain governance and consistency.