skill-creator

Name: skill-creator
Availability: InStock
Author: Lucas

Design, draft, and iteratively improve Claude skills with SKILL.md frontmatter.

2|20|Updated Jan 20, 2026

Search Tags:#benchmarking #skills #claude #evaluation #packaging #iteration #trigger-optimization

Ready to run

npx skills add https://github.com/LucasMatuszewski/JSystems-SilkyCoders-1 --skill skill-creator-lucasmatuszewski

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/LucasMatuszewski/JSystems-SilkyCoders-1/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/LucasMatuszewski/JSystems-SilkyCoders-1 --skill skill-creator-lucasmatuszewski

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 you design, test, and refine Claude skills so they trigger more reliably and produce better outcomes over time.

Core Features & Use Cases

Skill Drafting: Turn an idea or rough workflow into a structured SKILL.md with clear trigger guidance and operating instructions.
Evaluation & Benchmarking: Create realistic test prompts, run comparisons with and without the skill, and review pass rates, timing, and token usage.
Iterative Improvement: Use feedback, transcripts, and benchmark analysis to tighten instructions, add scripts or references, and improve triggering accuracy.
Packaging: Validate and bundle a finished skill into a distributable .skill file.
Use Case: A teammate wants a reusable skill for a repeated workflow, so you draft it, test it against real prompts, inspect failures, revise the description, and ship the improved version.

Quick Start

Use the skill-creator skill to draft or improve a skill, test it with realistic prompts, review the results, and iterate until the behavior is reliable.

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 package a Claude skill for a repeated workflow?▼

To create a Claude skill, draft a structured SKILL.md with trigger guidance, test it against realistic prompts, review benchmark results, and package the validated instructions into a distributable .skill file. This process ensures reliable triggering and consistent outcomes for repeated workflows.

What is skill benchmarking and how does it improve Claude trigger descriptions?▼

Skill benchmarking evaluates Claude trigger accuracy by running comparison tests with and without the skill using realistic prompts. Analyzing pass rates, timing, and token usage from these evaluation outputs reveals trigger failures so you can iteratively refine and tighten the trigger descriptions.

Do I need pyyaml installed to use the skill-creator?▼

Yes, pyyaml is a required dependency for the skill-creator. You need this Python package installed in your environment to properly parse SKILL.md frontmatter and execute the bundled scripts used during skill drafting, evaluation, and packaging.

Can I use bundled scripts and references to iterate on existing Claude skills?▼

Yes, you can revise existing Claude skills by using bundled scripts, references, and assets alongside evaluation outputs. This allows you to inspect failure transcripts, tighten instructions, add supporting references, and refine trigger optimization for improved behavior.

What's the best way to validate Claude skill behavior before distribution?▼

The best way to validate Claude skill behavior is to generate realistic test prompts, run comparative benchmarking with and without the skill, and inspect pass rates alongside token usage. Iterating on instructions based on these evaluation outputs ensures the skill triggers reliably before packaging.

Why does my Claude skill fail to trigger reliably during testing?▼

Claude skills fail to trigger reliably when instructions and trigger descriptions are too broad or misaligned with actual user prompts. Benchmarking test runs, reviewing failure transcripts, and iteratively tightening the SKILL.md frontmatter and operating instructions resolves these triggering inaccuracies.