skill-creator

Creates, tests, and iterates Claude skills through SKILL.md workflows and evaluation loops.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/oteroweb/OWFINANCE2026 --skill skill-creator-oteroweb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/oteroweb/OWFINANCE2026/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/oteroweb/OWFINANCE2026 --skill skill-creator-oteroweb

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill provides a structured, repeatable workflow for creating new Claude skills, testing them with formal evaluations, and iterating based on results to improve triggering accuracy and usefulness.

Core Features & Use Cases

  • Create a new skill by writing a SKILL.md with mandatory frontmatter (name and description) and a detailed body describing usage.
  • Run evaluation loops, collect metrics, compare configurations with and without the skill, and generate actionable feedback to drive improvements.
  • Manage iterative improvements by saving history, generating improved descriptions or tooling, and re-running experiments until a stable, high-quality skill is achieved.

Quick Start

Draft a skill by filling SKILL.md, then initiate the evaluation loop to begin the iterative improvement process.

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 test Claude skills with formal evaluations?

To create and test Claude skills, draft a SKILL.md file with mandatory frontmatter and a detailed usage body, then initiate an evaluation loop to collect metrics, compare configurations, and generate actionable feedback for improvements.

What is the best way to automate prompt engineering iteration for skill development?

Automating prompt engineering iteration involves running structured evaluation loops, comparing benchmarks with and without the skill, and tracking history to generate improved descriptions until a stable, high-quality skill is achieved.

Does the skill-creator workflow require specific dependencies to run?

The skill-creator workflow requires the yaml dependency to parse and manage the mandatory frontmatter configurations within the SKILL.md file during the creation and iteration process.

Why does my Claude skill fail to trigger correctly during testing?

If your Claude skill fails to trigger, the evaluation loop identifies low trigger rates by comparing baseline configurations, allowing you to optimize descriptions and re-run benchmarks to increase triggering accuracy.

Can I track history and manage iterative improvements for Claude skills?

You can manage iterative improvements by saving history logs, generating optimized descriptions, and re-running experiments to ensure maintainable skill development with automated improvements.