skill-creator

Create, refine, and optimize AI skills with SKILL.md files and evaluations.

1|Updated Mar 7, 2026

Search Tags:#skill development #prompt engineering #optimization #llm #evaluation #ai tools

Ready to run

npx skills add https://github.com/gitcomit8/agent-skills --skill skill-creator-gitcomit8

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/gitcomit8/agent-skills/tree/main/skill-creator
Command: npx skills add https://github.com/gitcomit8/agent-skills --skill skill-creator-gitcomit8

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill empowers users to create new AI skills from scratch, modify and improve existing ones, and rigorously test their performance, streamlining the AI development lifecycle.

Core Features & Use Cases

Skill Creation: Guides users through defining intent, interviewing for requirements, and writing SKILL.md files.
Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on user feedback and performance metrics.
Description Optimization: Automatically tunes skill descriptions for optimal triggering accuracy.
Use Case: You have an idea for a new AI assistant skill to summarize meeting notes. Use this Skill to draft the SKILL.md, create test prompts, run evaluations, and optimize the description so Claude Code reliably invokes it.

Quick Start

Use the skill creator to help me build a new skill that can convert markdown files to HTML.

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 write a new AI skill from scratch?▼

To create an AI skill, this tool guides you through defining intent, interviewing for requirements, and drafting the SKILL.md documentation, resulting in a structured skill ready for testing.

What is the best way to evaluate and refine LLM prompt performance?▼

Evaluating LLM prompt performance is achieved by generating test cases, running benchmark evaluations, analyzing results, and applying iterative refinement loops to optimize skill behavior.

How do I optimize AI skill descriptions for accurate triggering?▼

Optimizing AI skill descriptions involves automatically tuning the skill metadata so the LLM reliably invokes the correct skill based on user intent and input prompts.

Can I test AI skills iteratively using LLM-based evaluation loops?▼

Yes, you can test AI skills iteratively by integrating LLM-based testing and improvement loops to run evaluation test cases, analyze benchmark results, and refine performance.

Does the skill development lifecycle support end-to-end workflows from intent capture to optimization?▼

The skill development lifecycle supports end-to-end workflows including intent capture, requirement interviews, documentation drafting, evaluation testing, and description optimization.

Why are PDF parsing dependencies like pypdf and pdfplumber needed for skill development?▼

PDF parsing dependencies like pypdf and pdfplumber are included to support processing PDF assets and references during skill creation, testing, and evaluation workflows.