skill-creator

Create, test, and iteratively improve AI skills with structured evaluations.

2|1|Updated Jun 12, 2026
One-click install
npx skills add https://github.com/OKHP3/skillz --skill skill-creator-okhp3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/OKHP3/skillz/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/OKHP3/skillz --skill skill-creator-okhp3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires subagents, scripts, eval-viewer, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a comprehensive framework for creating, modifying, and evaluating AI skills, enabling users to develop and refine their own AI agents effectively.

Core Features & Use Cases

  • Skill Creation: Assist users in designing and structuring new skills, including defining objectives, capturing intent, and creating test cases.
  • Skill Improvement: Provide guidance on iterating and optimizing existing skills based on evaluation results and user feedback.
  • Performance Measurement: Facilitate benchmarking skill performance through quantitative analysis and qualitative feedback.

Quick Start

To create a new skill, run the skill-creator with the desired task description.

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 test AI skills for agent development?

To create and test AI skills, use a structured lifecycle framework that facilitates defining objectives, capturing user intent, and running performance evaluations. This process supports iterative improvement based on quantitative analysis and qualitative feedback.

What is the best way to measure AI agent performance and optimize skills?

Measuring AI agent performance involves running quantitative analysis and qualitative feedback evaluations. You can optimize skills by iteratively refining them based on these benchmarking results to ensure precision and efficiency in agent development.

Do I need subagents and scripting capabilities to build AI skills?

Yes, you need subagents and scripting capabilities to build AI skills. Access to these components is required to execute tests, run performance evaluations, and analyze the results effectively during the development lifecycle.

How does skill optimization work for existing AI agents?

Skill optimization for existing AI agents works by providing guidance on iterating and modifying skills based on evaluation results and user feedback. This continuous improvement process ensures the agent meets its defined objectives with maximum efficiency.

Can I benchmark skill performance using quantitative analysis?

Yes, you can benchmark skill performance using quantitative analysis. The framework facilitates performance measurement by capturing test cases and running evaluations to generate quantitative metrics and qualitative feedback for your AI skills.