skills.rest
EpicBlackWolfZ
EpicBlackWolfZCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Automates the build and improvement cycle of Claude skills via evaluation and feedback.

Updated Aug 27, 2026
Search Tags:#automation#workflow#evaluation#iteration#creation#skill#prompt-engineering
One-click install
npx skills add https://github.com/EpicBlackWolfZ/Gildedrose-kata --skill skill-creator-epicblackwolfz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/EpicBlackWolfZ/Gildedrose-kata/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/EpicBlackWolfZ/Gildedrose-kata --skill skill-creator-epicblackwolfz

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator helps you design, validate, and iterate Claude skills through an automated evaluation loop, reducing guesswork and boosting trigger accuracy.

Core Features & Use Cases

  • Automates the end-to-end skill lifecycle: drafting SKILL.md, running trigger evaluations, collecting feedback, and iterating to improve performance.
  • Supports a structured evaluation workflow with train/test splits, live reporting, and optional benchmarking.
  • Enables packaging and distribution of skills for reuse and versioning.

Quick Start

Use the Skill Creator to initialize a new skill directory, add SKILL.md, and run the evaluation loop to start the iteration cycle.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate Claude skill creation and evaluation?▼

You can automate Claude skill creation by using a structured workflow that guides you through SKILL.md drafting, trigger testing, and feedback-driven iteration loops to improve accuracy.

What is the best way to test and refine Claude prompt triggers?▼

Testing and refining Claude prompt triggers involves running an automated evaluation loop with train/test splits, aggregating results, and applying feedback to improve trigger performance.

How do I iterate on a SKILL.md file to improve trigger accuracy?▼

To iterate on a SKILL.md file, you run evaluation workflows that collect feedback on trigger performance, then apply that feedback to refine and enhance the skill definitions.

Can I package and distribute Claude skills for version control?▼

Yes, you can package and distribute Claude skills for reuse and versioning after completing the automated drafting, evaluation, and iteration cycle to validate the skill.

Do I need PyYAML to run the skill evaluation workflow?▼

Yes, PyYAML is required as a dependency to parse and manage the skill configuration files during the automated evaluation and iteration processes.

How does benchmarking work during Claude skill development?▼

Benchmarking during Claude skill development provides optional performance tracking by evaluating trigger accuracy across test splits, allowing you to measure improvements through iteration loops.

Related Skills

Explore More Software Engineering Skills→
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
YanBerdinYanBerdin
2

skill-creator

Coordinate end-to-end Claude skill design, evaluation, and deployment.

Community
Advanced
akbarfarooq2006akbarfarooq2006

skill-creator

Automates creation, testing, and refinement of Claude Code skills with built-in evals and benchmarking.

Community
Intermediate
iyakiiyaki

skill-creator

Coordinate end-to-end creation and refinement of Claude skills via SKILL.md and evaluation loops.

Community
Advanced