skill-creator

Guide creating and structuring AI skills with SKILL.md and bundled resources.

2|3|Updated Nov 24, 2020
One-click install
npx skills add https://github.com/loganlinn/dotfiles --skill skill-creator-loganlinn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/loganlinn/dotfiles/tree/main/config/claude/skills/skill-creator
Command: npx skills add https://github.com/loganlinn/dotfiles --skill skill-creator-loganlinn

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides guidance for creating effective skills, enabling users to extend Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Core Features & Use Cases

  • Skill Anatomy: Understand the structure of a skill (SKILL.md, scripts/, references/, assets/).
  • Core Principles: Learn best practices like conciseness and setting appropriate degrees of freedom.
  • Progressive Disclosure: Master efficient context management through metadata, SKILL.md body, and bundled resources.
  • Skill Creation Process: Follow a step-by-step guide from understanding the skill to iteration.
  • Use Case: A developer needs to create a new skill to integrate a custom API. They would use this Skill to understand the required structure, best practices for writing the SKILL.md, and how to bundle necessary scripts and documentation.

Quick Start

Use the skill-creator skill to learn how to create a new 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 an AI skill to extend agent capabilities with custom workflows?

To create an AI skill, you structure a SKILL.md file alongside bundled scripts, references, and assets, following core design principles like conciseness and progressive disclosure for efficient context management.

What is progressive disclosure in skill creation and why does it matter?

Progressive disclosure in skill creation is an efficient context management strategy that structures information across metadata, the SKILL.md body, and bundled resources, ensuring the AI agent receives only the necessary context for the task.

How do I structure a new skill for an AI agent to integrate a custom API?

You structure a new skill by creating a SKILL.md file for core instructions and organizing supporting files into directories for scripts, references, and assets, enabling the agent to effectively use the custom API.

What are the best practices for writing SKILL.md content for developer guides?

Best practices for writing SKILL.md content include maintaining conciseness, setting appropriate degrees of freedom for the agent, and clearly defining workflows to ensure predictable and effective skill execution.

Do I need to bundle scripts and references when packaging AI skills?

Yes, you need to bundle scripts and references when packaging AI skills if the workflow requires external logic or detailed documentation, ensuring the agent has direct access to necessary executable code and context.

How to validate an AI skill after packaging and initialization?

You validate an AI skill after packaging by iterating through the creation process, testing the agent's execution of the SKILL.md instructions, and verifying that bundled scripts and references function as intended.