skill-creator

Create, edit, and optimize Claude AI skills with test cases and evaluations.

1|Updated Jul 3, 2026
One-click install
npx skills add https://github.com/noahsilve123/claude-skillset --skill skill-creator-noahsilve123
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/noahsilve123/claude-skillset/tree/main/skills/skill-creator
Command: npx skills add https://github.com/noahsilve123/claude-skillset --skill skill-creator-noahsilve123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires subagents, Claude API, and includes scripts (resource) and references (resource) components.

What problem does it solve?

The Skill-creator skill simplifies the process of creating new Claude AI skills, iterating on existing ones, and optimizing skill descriptions for better triggering accuracy.

Core Features & Use Cases

  • Skill Creation: Facilitate the creation of new Claude AI skills from scratch.
  • Skill Iteration: Assist in editing, refining, and testing existing skills.
  • Performance Optimization: Optimize skill descriptions to improve triggering accuracy and skill performance.
  • Use Case: Imagine you want to build a new skill for generating code reviews. The Skill-creator can guide you through the process of defining the skill's functionality, writing test cases, running evaluations, and refining the skill based on user feedback.

Quick Start

Use the skill-creator skill to generate a new skill for generating code reviews with the following prompt: "I want to create a skill for generating code reviews. The skill should identify issues in the code, suggest improvements, and summarize the changes made."

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create and optimize Claude AI skills for better triggering accuracy?

Yes, you can edit and refine existing Claude AI skills by iterating on their definitions, running evaluations, testing specific cases, and adjusting descriptions based on feedback to improve overall performance.

What's the best way to write test cases for evaluating AI skill performance?

The best way to write test cases for AI skill evaluation is to define specific skill functionality, run targeted evaluations, and iteratively refine the skill based on test outcomes and user feedback.

Do I need subagents and the Claude API to automate skill creation?

Yes, you need both subagents and the Claude API to automate the skill creation process, as these dependencies are required for executing the automated creation, editing, and optimization workflows.

Can I use this approach to build a code review skill from scratch?

Yes, you can build a code review skill from scratch by defining the functionality to identify code issues, suggest improvements, and summarize changes, then generating the skill through automated guidance.