skill-creator

Create and refine AI skills with SKILL.md and YAML frontmatter.

Updated Mar 4, 2026
One-click install
npx skills add https://github.com/samura-dev/antigravity-kit --skill skill-creator-samura-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/samura-dev/antigravity-kit/tree/main/.agent/skills/skill-creator
Command: npx skills add https://github.com/samura-dev/antigravity-kit --skill skill-creator-samura-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the entire process of creating, improving, and evaluating AI skills, making it accessible even for those new to AI development.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing the SKILL.md, and structuring skill directories.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on performance metrics and user feedback.
  • Description Optimization: Automatically tunes skill descriptions for better triggering accuracy.
  • Use Case: You have an idea for a new AI capability. Use this Skill to turn that idea into a functional, well-tested AI skill, complete with documentation and performance benchmarks.

Quick Start

Use the skill creator to start building a new skill for summarizing meeting notes.

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 structure a new AI skill from scratch?

To create an AI skill, you define its intent, write a SKILL.md file with YAML frontmatter and markdown instructions, and bundle resources like scripts and references into a structured directory.

What is the best way to optimize AI skill descriptions for accurate triggering?

Optimizing AI skill descriptions involves using iterative testing workflows and description optimization loops to automatically tune metadata, improving how accurately the skill triggers during evaluation.

How do I evaluate and refine AI skills using benchmark analysis?

You evaluate AI skills by implementing iterative testing workflows that analyze performance metrics and benchmark data, allowing you to refine the skill based on measurable results and feedback.

Can I bundle scripts and references when building workflow automation skills?

Yes, when building workflow automation skills, you can bundle essential resources like scripts and references within the skill directory to support its internal design and processing logic.

Do I need prior prompt engineering experience to modify and improve existing AI skills?

No, prior prompt engineering experience is not required, as the skill facilitates modification and iterative improvement workflows, making AI development accessible even for new users.