skills.rest
gewoonseba
gewoonsebaCOMMUNITY
Explore all skills by this author →
Website𝕏@sebastoelenGitHub

skill-creator

Create, evaluate, and improve Claude skills with iterative benchmarks.

9|Updated Dec 21, 2025
Search Tags:#automation#workflow#tooling#claude#evaluation#iteration#skill
One-click install
npx skills add https://github.com/gewoonseba/dotfiles --skill skill-creator-gewoonseba
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/gewoonseba/dotfiles/tree/main/claude/.claude/skills/skill-creator
Command: npx skills add https://github.com/gewoonseba/dotfiles --skill skill-creator-gewoonseba

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you create new skills, modify and improve existing skills, and measure skill performance. It provides a repeatable workflow for drafting, evaluating, and iterating on skills to improve triggering accuracy and overall effectiveness.

Core Features & Use Cases

  • Create, modify, and improve Claude skills from scratch or from drafts.
  • Run guided evals and benchmarks to quantify triggering accuracy and performance.
  • Iterate quickly using feedback from qualitative reviews and quantitative metrics to refine skill descriptions and guidance.

Quick Start

Draft a skill, run iterative evaluations, and refine triggering and performance based on results.

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 refine Claude skills from scratch?▼

You create and refine Claude skills by drafting the skill, running guided evaluations, and iterating on trigger descriptions using qualitative and quantitative feedback to improve overall effectiveness.

What's the best way to evaluate Claude skill triggering accuracy?▼

The best way to evaluate Claude skill triggering accuracy is to run guided evals and benchmarks that quantify performance, then iterate quickly using the resulting metrics to refine trigger descriptions.

How does skill benchmarking and iteration work for Claude automation workflows?▼

Skill benchmarking works by running guided evaluations to measure triggering accuracy, then applying feedback from qualitative reviews and quantitative metrics to iterate and optimize skill performance.

Do I need YAML to use this skill creation and evaluation workflow?▼

Yes, you need YAML because it is a required dependency for this workflow, which enables end-to-end skill creation, evaluation, and improvement for Claude skills including drafting and benchmarking.

Can I modify and improve existing Claude skills instead of starting new ones?▼

Yes, you can modify and improve existing Claude skills by running iterative evaluations and refining their trigger descriptions and guidance based on benchmarking results and qualitative reviews.

When should I run skill evaluations to optimize trigger descriptions?▼

You should run skill evaluations after drafting a skill and whenever you refine trigger descriptions, using the benchmark results to measure accuracy and iterate quickly on performance improvements.

Related Skills

Explore More Software Engineering Skills→
tneztnez

bootstrap

Initialize the .docent directory structure and configuration for new projects.

Community
Basic
CHENyiru3CHENyiru3

skill-creator

Automate end-to-end creation, evaluation, and refinement of Claude Code skills.

Community
Advanced
luminos-accessibilityluminos-accessibility
2

skill-creator

Create, modify, and evaluate Claude Skills with SKILL.md and benchmarking workflows.

Official
Advanced
xurenluxurenlu
1

skill-creator

Creates and iteratively improves AI skills with SKILL.md and test cases.

Community
Advanced