skill-creator

Guide creation, structuring, and packaging of modular AI agent skills.

11|4|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/wpank/ai --skill skill-creator-wpank
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/wpank/ai/tree/main/skills/tools/skill-creator
Command: npx skills add https://github.com/wpank/ai --skill skill-creator-wpank

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive guide and workflow for creating, structuring, and packaging modular AI agent skills, transforming raw knowledge into reusable components.

Core Features & Use Cases

  • Skill Anatomy: Understand the structure of a skill unit (SKILL.md, scripts/, references/, assets/).
  • Creation Workflow: Follow a step-by-step process from understanding requirements to iterating on a finished skill.
  • Resource Management: Learn best practices for using scripts, references, and assets effectively.
  • Use Case: You need to build a new skill for your AI agent to handle a specific domain, like "API documentation lookup." This Skill will guide you through defining the SKILL.md, organizing necessary reference files, and packaging it for distribution.

Quick Start

Use the skill-creator to learn how to build a new AI agent skill.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create and package an AI agent skill?

To create an AI agent skill, you structure a modular knowledge module containing a SKILL.md file, scripts, references, and assets. This skill guides you through defining YAML frontmatter, organizing bundled resources, and packaging the unit for distribution.

What is the correct anatomy of a modular AI skill?

The anatomy of a modular AI skill consists of a SKILL.md file alongside bundled scripts, references, and assets directories. This structure transforms raw domain knowledge into reusable components that AI agents can access during task execution.

Do I need YAML frontmatter to build a new AI agent skill?

Yes, YAML frontmatter is a requirement when building a new AI agent skill. It defines the metadata for the modular knowledge module, ensuring the AI agent can correctly identify and load the packaged skill.

What is the best way to structure scripts and references for AI skills?

The best way to structure scripts and references for AI skills is using bundled resource patterns within dedicated directories. This approach supports progressive disclosure, allowing the agent to access necessary code and data without overwhelming its context window.

How does progressive disclosure work in AI agent skill creation?

Progressive disclosure in AI agent skill creation limits the initial context loaded by the agent, revealing deeper scripts and references only as needed. This calibration optimizes agent performance while keeping the modular knowledge module highly reusable.

Are there quality checklists available for packaging AI skills?

Yes, quality checklists are provided to validate your packaged AI skills before distribution. They ensure the SKILL.md, bundled scripts, and references meet structural requirements and function correctly as a modular knowledge module.