creating-skills

Scaffold agent skill directories with SKILL.md and resource folders.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/aufrank/agent-skills --skill creating-skills-aufrank
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: creating-skills
Source: https://github.com/aufrank/agent-skills/tree/main/skills/creating-skills
Command: npx skills add https://github.com/aufrank/agent-skills --skill creating-skills-aufrank

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of creating and refining agent skills, ensuring they are well-structured, discoverable, and follow best practices for deterministic execution and progressive disclosure.

Core Features & Use Cases

  • Skill Scaffolding: Generates a new skill directory with a basic SKILL.md and optional resource folders (scripts/, references/, assets/, templates/).
  • Best Practice Guidance: Provides instructions on naming conventions, content structure, trust policies, and observable logging.
  • Use Case: When starting a new agent skill, use this skill to quickly set up the correct directory structure and boilerplate SKILL.md file, ensuring adherence to the project's standards from the outset.

Quick Start

Use the creating-skills skill to scaffold a new skill named 'auditing-permissions' within the 'skills/security' directory, including scripts and references.

Frequently Asked Questions about creating-skills

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

FAQPage Schema
How do I scaffold a new agent skill with the correct directory structure?

Agent skill scaffolding provides a standardized directory structure with a base SKILL.md and optional resource folders like scripts/ and references/ to ensure best practices from the outset.

What is progressive disclosure in agent development?

Progressive disclosure in agent development structures skill content to reveal complexity only as needed, supported by templated files and observable artifacts for deterministic execution.

How do I ensure deterministic execution when authoring agent skills?

Ensure deterministic execution in agent skills by following best practices for naming conventions, content organization, and observable logging provided during the skill authoring process.

Can I include scripts and references when generating a new skill?

Yes, you can include scripts and references when generating a new skill, as the scaffolding process supports creating optional resource folders like scripts/, references/, assets/, and templates/.

What's the best way to structure a self-contained agent skill?

The best way to structure a self-contained agent skill is to use scaffolding that enforces naming conventions, trust policies, and content organization for maintainable skill development.