skill-creator

Automates creation, optimization, and benchmarking of AI skills with Git-like workflows.

Updated May 30, 2026
One-click install
npx skills add https://github.com/kaiomaced0/hackamarh --skill skill-creator-kaiomaced0
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/kaiomaced0/hackamarh/tree/main/front-gestao/.agents/skills/skill-creator
Command: npx skills add https://github.com/kaiomaced0/hackamarh --skill skill-creator-kaiomaced0

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill Unit addresses the challenges of creating, iterating, and optimizing AI skills, streamlining the process for both skill developers and end-users.

Core Features & Use Cases

  • Skill Creation: Guide users through crafting new skills from scratch, including capturing intent, designing test cases, and running evaluations.
  • Skill Modification: Enable users to modify existing skills based on evaluation feedback, with options for optimizing performance and description accuracy.
  • Skill Benchmarking: Provide quantitative analysis of skill performance, including pass rates, execution times, and token usage.
  • Description Optimization: Offer tools to refine skill descriptions for improved triggering accuracy and relevance.
  • Use Case: Imagine a user wants to create a skill for generating financial reports. The Skill Unit can assist with designing the skill's behavior, setting up test cases, and optimizing its description for better triggering.

Quick Start

To create a new skill, run the following commands:

create_skill "generate financial report" "Generate financial reports from provided data"

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 from scratch?

To create an AI skill from scratch, use the structured skill creation approach to capture intent, design test cases, and run evaluations. This process automates skill design, testing, and description refinement for precise AI behavior.

What is AI skill benchmarking and how does it evaluate performance?

AI skill benchmarking provides quantitative analysis of skill performance, measuring pass rates, execution times, and token usage. This evaluation identifies areas for modification and optimization based on concrete execution metrics.

How do I optimize AI skill descriptions for better triggering?

Optimize AI skill descriptions by refining them using evaluation feedback to improve triggering accuracy and relevance. Description refinement ensures the skill activates correctly based on user intent and context.

Can I modify existing AI skills based on evaluation feedback?

Yes, you can modify existing AI skills based on evaluation feedback to optimize performance and description accuracy. The modification process uses benchmarking results to guide iterative improvements.

Do I need prior knowledge of AI interaction patterns to use this skill creation tool?

Yes, effective skill creation requires knowledge of skill development processes and AI interaction patterns. The tool automates the workflow but relies on the user's understanding of AI behavior design to function correctly.