skill-creator

Guides creating AI skills with structure, metadata, and packaging steps.

121|16|Updated Dec 16, 2025
One-click install
npx skills add https://github.com/Illuminated2020/DeepAgents-AutoGLM --skill skill-creator-illuminated2020
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Illuminated2020/DeepAgents-AutoGLM/tree/main/examples/skills/skill-creator
Command: npx skills add https://github.com/Illuminated2020/DeepAgents-AutoGLM --skill skill-creator-illuminated2020

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides guidance for creating effective skills, enabling users to extend AI capabilities with specialized knowledge, workflows, and tool integrations.

Core Features & Use Cases

  • Skill Anatomy: Explains the structure of a skill (SKILL.md, scripts/, references/, assets/).
  • Best Practices: Offers guidance on metadata quality, progressive disclosure, and writing style.
  • Skill Creation Process: Outlines a step-by-step guide from understanding examples to packaging.
  • Use Case: A user wants to create a new skill for managing company brand assets. They would use this skill to understand how to structure the skill, what files to include in assets/ (like logos and templates), and how to write the SKILL.md to guide the AI on using these assets.

Quick Start

Use the skill-creator skill to learn how to create a new skill for managing company brand assets.

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 new AI skill for workflow automation?

To create an AI skill, structure your project with a SKILL.md file and organize supporting files into scripts, references, and assets directories to guide the AI's modular extension capabilities.

What is the correct structure for developing modular AI extensions?

Modular AI extensions require a specific anatomy: a root SKILL.md file for instructions, alongside scripts for automation, references for knowledge, and assets for static resources.

What are the best practices for writing skill metadata in prompt engineering?

Skill metadata best practices involve ensuring high metadata quality, applying progressive disclosure principles to manage context, and using clear writing styles to direct AI augmentation accurately.

Do I need any specific dependencies to package a custom AI skill?

No specific dependencies are required to package a custom AI skill; the creation process focuses on understanding structural examples, organizing resources, and writing effective metadata for deployment.

How do I integrate tool workflows and static assets into a newly created skill?

Integrate tool workflows by placing automation logic in the scripts directory and static resources like templates in the assets directory, then reference them in SKILL.md for AI execution.

When should I use progressive disclosure in AI skill creation?

Use progressive disclosure during AI skill creation to prevent context overload, structuring SKILL.md to reveal complex instructions and references only when the AI needs them for task execution.