skill-creator

Scaffold, audit, and improve AI agent skills with structured patterns.

4|1|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/wyattowalsh/agents --skill skill-creator-wyattowalsh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/wyattowalsh/agents/tree/main/skills/skill-creator
Command: npx skills add https://github.com/wyattowalsh/agents --skill skill-creator-wyattowalsh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydantic, rich, PyYAML, and includes scripts (resource) and references (resource) and evals (resource) and templates (resource) components.

What problem does it solve?

This Skill streamlines the creation, improvement, and auditing of AI agent skills, ensuring they adhere to best practices and are easily discoverable.

Core Features & Use Cases

  • Skill Creation: Scaffold new skills from templates or exemplars.
  • Skill Improvement: Refactor and enhance existing skills based on audits.
  • Skill Auditing: Score skills deterministically and identify areas for improvement.
  • Use Case: A developer needs to create a new skill to analyze code quality. They use this Skill to scaffold the basic structure, write the SKILL.md, and then audit it to ensure it meets quality standards.

Quick Start

Use the skill creator to create a new skill named 'my-data-processor'.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create an AI agent skill from a template?

To create an AI agent skill, use the creator mode to scaffold a new project from predefined templates or exemplars. This generates a standard directory structure and a starter SKILL.md file, establishing a maintainable foundation for subsequent development.

What is the best way to audit an AI agent skill for best practices?

The best way to audit an AI agent skill is using the deterministic scoring mechanism. This process evaluates the skill's structure and documentation against established best practices, generating a quantifiable score and identifying specific areas for code improvement.

Can I improve existing AI agent skills or do I need to start from scratch?

You can improve existing AI agent skills without starting from scratch. The improvement mode analyzes current files and refactors them based on audit results, enhancing maintainability and ensuring adherence to documented best practices.

Does the skill creator require Python dependencies like pydantic and PyYAML?

Yes, the skill creator requires Python dependencies including pydantic, rich, and PyYAML. These libraries facilitate structured data validation, terminal formatting for outputs, and YAML configuration parsing during skill generation and auditing.

What components are included when scaffolding a new AI agent skill?

Scaffolding a new AI agent skill includes components such as scripts, references, evals, and templates. These elements ensure the generated skill has comprehensive documentation, executable logic, and built-in evaluation frameworks.