skill-creator

Create and refine AI skills with SKILL.md, tests, and evaluations.

9|Updated Aug 12, 2025
One-click install
npx skills add https://github.com/shekohex/dotai --skill skill-creator-shekohex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/shekohex/dotai/tree/main/skills/skill-creator
Command: npx skills add https://github.com/shekohex/dotai --skill skill-creator-shekohex

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 lifecycle of creating and improving AI skills, from initial concept to performance optimization and deployment.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, interviewing for edge cases, and writing SKILL.md with best practices.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on user feedback and performance metrics.
  • Description Optimization: Automatically tunes skill descriptions for optimal triggering accuracy using a robust evaluation loop.
  • Use Case: You have an idea for a new AI skill to help manage cloud deployments. Use this Skill to draft the SKILL.md, create test cases, run evaluations against baseline performance, analyze the results, and iterate on the skill's logic and description until it's highly effective.

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 build and test AI skills from scratch?

AI skill development involves structured workflows for capturing user intent, defining behavior, generating test cases, and running evaluations against baselines. This process guides you through drafting SKILL.md files and iterating on logic.

What is the process for optimizing LLM skill descriptions for triggering accuracy?

Description optimization for LLM skills requires running an evaluation loop that analyzes benchmark results and iteratively refines the text. This ensures optimal triggering accuracy when the AI skill is invoked.

How do I evaluate AI skill performance against a baseline?

Evaluating AI skill performance against a baseline involves generating specific test cases, running evaluations, and analyzing the benchmark results. This allows you to measure improvements and refine skill behavior iteratively.

Can I use prompt engineering to refine existing AI skills?

Yes, prompt engineering facilitates iterative improvement of existing AI skills through testing, evaluation, and refinement based on user feedback and performance metrics.

Do I need any specific frameworks to start AI skill development?

No specific frameworks are required to start AI skill development. The process focuses on defining intent, interviewing for edge cases, and writing SKILL.md files using best practices without external dependencies.