skill-creator

Create, modify, and measure AI skills with SKILL.md and test cases.

1|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/Jeffreyyvdb/.dotfiles --skill skill-creator-jeffreyyvdb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Jeffreyyvdb/.dotfiles/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/Jeffreyyvdb/.dotfiles --skill skill-creator-jeffreyyvdb

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive toolkit for creating new AI skills, enhancing existing ones, and measuring their performance. It is designed for users who want to build, iterate, and optimize their AI skills effectively.

Core Features & Use Cases

  • Skill Creation: Offers a structured process for creating new skills from scratch.
  • Skill Improvement: Assists in modifying and improving existing skills based on feedback and performance data.
  • Performance Measurement: Allows benchmarking and variance analysis to optimize skill descriptions and improve triggering accuracy.
  • Use Case: If you have a specific task or workflow you want Claude to perform, this skill can help you draft the skill, create test cases, evaluate the results, and iterate until the skill meets your requirements.

Quick Start

Use the skill-creator skill to create a new skill for generating summary reports from research articles.

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 specific workflows?

To create AI skills, you need a structured approach: capture intent, write SKILL.md, run test cases, and iterate based on feedback. This facilitates building agents for specific tasks or workflows.

What is the best way to measure AI skill performance and triggering accuracy?

Measuring AI skill performance involves benchmarking and variance analysis to optimize skill descriptions and improve triggering accuracy. This allows you to evaluate results and iterate until requirements are met.

Can I modify and improve existing AI skills based on performance data?

Modifying and improving existing AI skills is supported by using feedback and performance data. You can iterate on your skill descriptions and test cases to enhance the overall agent behavior.

Does AI skill creation require a specific development environment?

AI skill creation assumes the use of Claude Code and relevant libraries or tools for development. It requires a structured approach to design, including capturing intent and writing SKILL.md files.

How do benchmarking and variance analysis optimize AI agents?

Benchmarking and variance analysis optimize AI agents by measuring performance variations across test cases. This process identifies triggering inaccuracies and guides iterative improvements to skill descriptions.

When should I iterate on test cases during AI skill development?

You should iterate on test cases during AI skill development after evaluating initial results. This feedback loop helps refine the SKILL.md file and ensures the agent meets your specific task requirements.