skill-creator

Automate the lifecycle of creating, testing, and iterating Claude skills.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/leogomez74/studio --skill skill-creator-leogomez74
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/leogomez74/studio/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/leogomez74/studio --skill skill-creator-leogomez74

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

skill-creator helps teams rapidly craft, evaluate, and refine Claude skills—from initial drafting through iterative evaluation and optimization—so you can ship higher-performing prompts faster.

Core Features & Use Cases

  • Draft new skills and iterate on existing ones with guided evaluation and benchmarking.
  • Run evals to measure triggering accuracy, performance, and iteration progress.
  • Use the skill description improver to optimize triggering for better discovery.

Quick Start

Write a draft SKILL.md, run the evaluation loop, review results, and iterate until the results stabilize.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate creating and testing Claude skills?

You can automate Claude skill creation and testing by drafting a SKILL.md file, running an evaluation loop to measure performance, and iterating until results stabilize. This automates the end-to-end lifecycle for skill development.

What is skill description optimization and how does it improve triggering?

Skill description optimization refines frontmatter and prompt text to improve triggering accuracy. Running eval loops measures how accurately your skill activates, ensuring better discovery across multiple iterations.

Do I need pyyaml to run skill evaluation and benchmarking loops?

Yes, pyyaml is required. It parses YAML frontmatter for skill configuration, which is essential for the evaluation loops, benchmarking, and description optimization processes to function correctly.

Can I use bundled scripts and assets for deterministic skill tasks?

Yes, bundled scripts, references, and assets enable deterministic tasks, documentation access, and output templating. These components integrate directly into the skill creation and iteration workflow.

What's the best way to iterate on a prompt until benchmark results stabilize?

The best way to iterate on prompts is to run the evaluation loop, review benchmarking results for triggering accuracy and performance, adjust the SKILL.md draft, and repeat until metrics stabilize.

Why does my Claude skill description fail to trigger correctly in evaluations?

Triggering failures often occur when descriptions lack clear keywords or frontmatter context. Use the skill description improver to optimize text, then rerun evals to verify triggering accuracy improves.