skills.rest
locnbk2002
locnbk2002COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, refine, and evaluate AI skills with SKILL.md authoring and test execution.

1|Updated Feb 28, 2026
Search Tags:#skill development#AI tools#prompt engineering#code generation#optimization#evaluation
One-click install
npx skills add https://github.com/locnbk2002/my-copilot --skill skill-creator-locnbk2002
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/locnbk2002/my-copilot/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/locnbk2002/my-copilot --skill skill-creator-locnbk2002

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, refining, and evaluating AI-powered skills, making it easier to build powerful and accurate AI tools.

Core Features & Use Cases

  • Skill Creation: Guide users through defining intent, writing skill logic, and structuring SKILL.md.
  • Iterative Improvement: Run evaluations, analyze results, and refactor skills based on feedback.
  • Performance Benchmarking: Compare skill performance against baselines and track improvements over time.
  • Description Optimization: Automatically tune skill descriptions for optimal triggering accuracy.
  • Use Case: You have an idea for a new AI skill to summarize meeting notes. Use this Skill to help you draft the SKILL.md, create test cases, run evaluations, and optimize the description so Claude uses it effectively.

Quick Start

Use the skill creator to help me build a new skill that summarizes 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 develop and test AI skills end-to-end?▼

To develop AI skills, define the skill intent, author the SKILL.md content, generate test cases, and analyze benchmark results to iteratively refine and evaluate performance. This process covers creation, testing, and optimization for accurate triggering.

What is the best way to optimize AI skill descriptions for triggering accuracy?▼

Optimizing AI skill descriptions involves automatically tuning the text to improve triggering accuracy and discoverability. The skill creator analyzes evaluation results to refine descriptions so the AI invokes the skill effectively when needed.

How do I evaluate and benchmark AI prompt engineering performance?▼

Evaluating prompt engineering performance requires running test cases and analyzing benchmark results against baselines. The skill creator integrates with evaluation frameworks to provide quantitative and qualitative assessment to track improvements over time.

Can I use this skill creator to refactor and improve existing AI skills?▼

Yes, you can iteratively improve existing AI skills by running evaluations, analyzing the results, and refactoring the skill logic and SKILL.md content based on the feedback and benchmark data from the evaluation frameworks.

Do I need any external dependencies to benchmark AI skill performance?▼

No external dependencies are required to benchmark AI skill performance. The skill creator includes internal scripts and references to generate test cases, execute evaluations, and analyze results against baselines without additional packages.

Related Skills

Explore More Software Engineering Skills→
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
JonathanMitchell1234JonathanMitchell1234

skill-creator

Create and refine AI skills with SKILL.md files and test cases.

Community
Advanced
kollaboraikollaborai
1

skill-creator

Create and iteratively improve AI skills with structured evaluation and benchmarking workflows.

Community
Advanced
codeboltaicodeboltai

skill-creator

Create and refine Claude skills with structured SKILL.md templates and packaging workflows.

Official
Intermediate