skills.rest
shalevamin
shalevaminCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create and refine AI skills with SKILL.md and quantitative evaluations.

Updated Mar 7, 2026
Search Tags:#skill development#workflow automation#prompt engineering#benchmarking#evaluation#ai agent
One-click install
npx skills add https://github.com/shalevamin/The-_Ultimate_agents --skill skill-creator-shalevamin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/shalevamin/The-_Ultimate_agents/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/shalevamin/The-_Ultimate_agents --skill skill-creator-shalevamin

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 and improving AI capabilities, from initial concept to performance measurement.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, interviewing, and writing SKILL.md.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of existing skills.
  • Performance Benchmarking: Runs evals to measure skill accuracy, speed, and resource usage.
  • Use Case: You have an idea for a new AI function, like summarizing meeting notes. This Skill helps you draft the instructions, test it with sample prompts, analyze the results, and iterate until it performs perfectly.

Quick Start

Use the skill creator to help me draft 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 an AI agent skill from scratch?▼

To build and test an AI agent skill, you define the skill intent, draft the `SKILL.md` content, and run quantitative evaluations. This skill facilitates the end-to-end lifecycle of AI skill development, including iterative refinement and performance benchmarking.

What is the best way to evaluate prompt engineering workflows?▼

The best way to evaluate prompt engineering workflows is by running quantitative evaluations to measure skill accuracy, speed, and resource usage. This skill provides tools for analyzing benchmark results and setting up structured feedback loops for optimization.

Can I optimize skill descriptions for better AI triggering accuracy?▼

Yes, you can optimize skill descriptions for better triggering accuracy. The skill creator analyzes benchmark results and facilitates iterative refinement of your `SKILL.md` content to ensure your AI agent triggers reliably in automated workflows.

How does benchmarking work for AI skill development?▼

Benchmarking for AI skill development works by running evals that measure accuracy, speed, and resource usage. This skill integrates with testing frameworks to provide structured analysis of benchmark results, enabling data-driven iterative improvement.

Do I need testing frameworks to refine existing AI skills?▼

Yes, testing frameworks are required to refine existing AI skills effectively. This skill integrates with testing frameworks to run quantitative evaluations, analyze performance benchmark results, and provide structured feedback for optimization.

Related Skills

Explore More Software Engineering Skills→
matt-fell-aimatt-fell-ai
1

Evolve

Generate modular skills with directories, SKILL.md metadata, and Python tooling.

Community
Basic
huynguyenhhuynguyenh
3

hnh-create-skill

Create and modify AI skills with SKILL.md files and iterative testing.

Community
Advanced
z1439527767z1439527767

agent-evaluation

Evaluate and benchmark LLM agents for reliability and behavioral quality.

Community
Advanced
amanhsnamanhsn

senior-prompt-engineer

Optimize LLM prompts and evaluate AI outputs with Python scripts.

Community
Advanced