skills.rest
ralphjohn29
ralphjohn29COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, test, and benchmark custom AI skills with SKILL.md files.

1|Updated Mar 8, 2026
Search Tags:#skill development#testing#AI tools#prompt engineering#code generation#evaluation
One-click install
npx skills add https://github.com/ralphjohn29/my-claude-skills --skill skill-creator-ralphjohn29
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ralphjohn29/my-claude-skills/tree/main/skill-creator
Command: npx skills add https://github.com/ralphjohn29/my-claude-skills --skill skill-creator-ralphjohn29

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, improving, and evaluating custom AI skills, making it easier to build powerful, specialized tools for AI assistants.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing SKILL.md, and structuring skill directories.
  • Iterative Improvement: Facilitates testing, feedback collection, and refinement of skills based on performance metrics and user input.
  • Performance Evaluation: Runs automated tests, benchmarks skill performance against baselines, and provides detailed analysis reports.
  • Use Case: You have an idea for a new skill to help developers debug CSS alignment issues. Use this Skill to draft the SKILL.md, write test cases, run them, analyze the results, and iterate on the skill until it reliably solves the problem.

Quick Start

Use the skill-creator to start building a new skill for generating commit messages.

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 custom AI skills?▼

To build and test custom AI skills, you define the intent, write the SKILL.md file, and structure directories. This skill facilitates the end-to-end lifecycle through automated testing and iterative refinement based on performance metrics.

What is the best way to structure an AI skill directory?▼

The best way to structure an AI skill directory is by defining the intent and writing a SKILL.md file. This skill guides users through creating the necessary architecture for specialized assistant tools.

How does performance benchmarking work for prompt engineering?▼

Performance benchmarking for prompt engineering works by running automated tests and comparing skill performance against baseline configurations. This skill provides detailed analysis reports to support iterative development.

Can I use this to evaluate code generation skills?▼

Yes, you can evaluate code generation skills by running automated tests and collecting feedback. This skill supports iterative improvement through detailed analysis of performance metrics against baseline configurations.

Why do I need automated testing for AI skill development?▼

You need automated testing for AI skill development to facilitate feedback loops and ensure reliable performance. This skill allows you to benchmark results against baselines and refine the architecture iteratively.

Related Skills

Explore More Software Engineering Skills→
PlagueHOPlagueHO
1

convert-prompt-to-skill

Convert GitHub Copilot .prompt.md files into SKILL.md Agent Skill directories.

Community
Intermediate
Ronin15Ronin15
14

hammer-benchmark-regression

Compare SDL3 HammerEngine metrics against baselines to flag performance regressions.

Community
Intermediate
stericisherestericishere
1

(workflow) phase-2-design

Generate frontend design prompts and architecture proposals from PRDs.

Community
Advanced
JimmyChen-NXPJimmyChen-NXP

lfg

Orchestrate planning, coding, review, and testing for software development tasks.

Community
Advanced