skill-creator

Create and update Codex skills with structured templates and validation rules.

2|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/metric-space-ai/ctox --skill skill-creator-metric-space-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/metric-space-ai/ctox/tree/main/skills/system/skill_meta/skill-creator
Command: npx skills add https://github.com/metric-space-ai/ctox --skill skill-creator-metric-space-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Codex skill creation and maintenance can be inconsistent without a shared structure, templates, and validation. This guide helps users create or update skills with standardized frontmatter, templates, and resource layouts.

Core Features & Use Cases

  • Standardized SKILL.md frontmatter (name + description) and a clear body structure.
  • Optional resource folders (scripts, references, assets) with guidance on when to use them.
  • Guidance for generating and validating tooling (agents/openai.yaml) and quality checks.
  • Use Case: A team creates a new skill for a domain and aligns its metadata and resources before activation.

Quick Start

Follow the initialization and validation steps to scaffold a new skill and verify its structure.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create a Codex skill with the correct YAML frontmatter structure?

To create a Codex skill, use standardized SKILL.md frontmatter containing the name and description fields, followed by a structured body. This ensures consistent quality and discoverability across skill design workflows.

What is the best way to validate a Codex skill before activation?

The best way to validate a Codex skill is by running quick_validate.py integrations and metadata checks. This verifies that your skill structure, frontmatter, and resource layouts meet the required validation rules before activation.

When do I need to include scripts or references folders in my skill directory?

You include optional scripts, references, or assets folders when your skill requires supporting tooling artifacts or documentation. These resource folders provide guidance and structure for complex skill design workflows that need external code or data.

How does the agents/openai.yaml file work with Codex skill creation?

The agents/openai.yaml file works as a generated tooling artifact that defines skill metadata for the Openai platform. The skill creation guide helps generate and validate this YAML file to ensure proper integration and consistent quality.

Can I update an existing skill's metadata without breaking validation rules?

Yes, you can update existing skill metadata by applying the provided templates and validation rules iteratively. The guide supports iterative improvement through example resources and metadata checks to ensure updates maintain consistent quality.