skill-creator

Orchestrates drafting, testing, and refining of Claude Skills.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/Mrlyk/SKILLS --skill skill-creator-mrlyk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Mrlyk/SKILLS/tree/main/skills/skill-creator
Command: npx skills add https://github.com/Mrlyk/SKILLS --skill skill-creator-mrlyk

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill guides users through creating, updating, and evaluating Claude Skills, enabling continuous improvement of agent behavior and triggering accuracy.

Core Features & Use Cases

  • Orchestrates drafting, testing, and refining skills to meet user needs.
  • Automates evaluation workflows (evals, benchmarks, and reviewer scripts) to quantify performance.
  • Helps users expand, customize, and document skills with references, scripts, and assets for on-demand tooling.

Quick Start

Type a high-level goal for a new skill, then iterate using evaluations and the benchmark system to improve triggering accuracy and output quality.

Frequently Asked Questions about skill-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Claude skill creation and evaluation workflows?

You can automate Claude skill creation by orchestrating drafting, testing, and refining workflows with automated evaluation benchmarks to quantify performance and improve triggering accuracy.

What is the best way to iterate on agent skills to improve triggering accuracy?

Iterating on agent skills involves using evaluation workflows and benchmark systems to test, refine, and quantify performance, ensuring continuous improvement of agent behavior and output quality.

Can I use pyyaml to customize skill references and scripts for Claude agents?

Yes, pyyaml is required as a dependency to support the creation and customization of skills, allowing you to expand and document skills with references, scripts, and assets.

Does this skill creation tool support end-to-end lifecycle management from drafting to deployment?

Yes, this tool streamlines the end-to-end lifecycle of Claude skills, guiding users from the initial drafting phase through testing, evaluation, and final deployment.

How do I evaluate agent behavior and performance benchmarks for custom skills?

You evaluate agent behavior by running automated evaluation workflows, benchmarks, and reviewer scripts designed to quantify performance and highlight areas for skill refinement.

When do I need to use an iterative skill creation process for Claude agents?

You need an iterative skill creation process when you want to continuously improve agent behavior, customize on-demand tooling, and achieve high triggering accuracy for specific user needs.