skills.rest
ArneBroedel
ArneBroedelCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Draft SKILL.md files, run evaluations, and optimize descriptions for Claude Skills.

Updated Feb 26, 2026
Search Tags:#automation#evaluation#iteration#workflows#skill-creation#prompt-engineering
One-click install
npx skills add https://github.com/ArneBroedel/Book-Layouting-Typst --skill skill-creator-arnebroedel
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ArneBroedel/Book-Layouting-Typst/tree/main/.github/skills/skill-creator
Command: npx skills add https://github.com/ArneBroedel/Book-Layouting-Typst --skill skill-creator-arnebroedel

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator helps teams build, iterate, and improve Claude Skills by guiding users through drafting SKILL.md, running evals, and optimizing both performance and triggering accuracy.

Core Features & Use Cases

  • Draft new skills from scratch and refine existing ones.
  • Run evaluations, compare configurations, and iterate using built-in feedback loops.
  • Optimize descriptions to improve skill triggering and overall effectiveness.
  • Use for benchmarks, variance analysis, and governance of skill quality across domains.

Quick Start

Draft your first SKILL.md, run the eval loop, and review results to begin iterating.

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 structure a Claude Skill for progressive disclosure?▼

To create a Claude Skill, draft a new SKILL.md file and structure it for progressive disclosure. This orchestrates an end-to-end workflow that supports iteration from initial draft to validated performance.

What's the best way to run evaluations and benchmark skill performance?▼

Running evaluations and benchmarking skill performance is best achieved through built-in feedback loops. You can compare configurations, conduct variance analysis, and iterate to ensure scalable deployment.

How do I optimize skill descriptions to improve triggering accuracy?▼

Optimizing skill descriptions improves triggering accuracy and overall effectiveness. Guide the evaluation process to refine descriptions, ensuring your skill activates reliably when users have matching intents.

Can I use this to refine existing skills instead of only drafting new ones?▼

Yes, you can refine existing skills as well as draft new ones from scratch. The iteration workflow supports continuous improvement through evaluation, benchmarking, and description optimization across domains.

Do I need anthropic and pyyaml dependencies to build and test skills?▼

Yes, the anthropic and pyyaml dependencies are required. They enable the underlying automation and evaluation workflows needed to orchestrate the end-to-end skill creation and testing pipeline.

Why does my skill trigger incorrectly when users search for related tasks?▼

Incorrect skill triggering happens when descriptions lack optimization. Use the evaluation loop to benchmark triggering accuracy, analyze variance, and refine descriptions to better identify user intent.

Related Skills

Explore More Software Engineering Skills→
breath57breath57
99

skill-creator

Create, test, and refine AI skills using the Anthropic skills specification.

Community
Advanced
Citrus-bitCitrus-bit
135

skill-creator

Orchestrates skill creation, evaluation, benchmarking, and description optimization workflows for Claude Skills.

Community
Advanced
zzr2718281828zzr2718281828

skill-creator

Create and refine AI skills through structured design and evaluation workflows.

Community
Advanced
tazagametazagame

skill-creator

Draft SKILL.md files and run evaluations to improve triggering and quality metrics.

Official
Advanced