skills.rest
rd162
rd162COMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create, evaluate, and benchmark Claude skills with SKILL.md generation.

Updated Apr 8, 2026
Search Tags:#benchmarking#claude#evaluation#iteration#skill#skill-creation#prompt-engineering
One-click install
npx skills add https://github.com/rd162/skills --skill skill-creator-rd162
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/rd162/skills/tree/main/skill-creator
Command: npx skills add https://github.com/rd162/skills --skill skill-creator-rd162

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill-creator provides a structured workflow to craft, test, and iteratively improve Claude skills, including evaluation, benchmarking, and description optimization to improve triggering accuracy and reliability.

Core Features & Use Cases

  • Create new skills from scratch, or refine existing ones using a repeatable loop: draft, evaluate, analyze, and improve.
  • Run trigger evaluations, collect performance metrics, and generate actionable improvements to both body and triggering description.
  • Benchmark across configurations, identify stability and efficiency gains, and push toward robust, discoverable skills.

Quick Start

Initiate the loop by drafting an initial SKILL.md, then run evals, review results, and iteratively improve the skill's description and behavior.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I iteratively optimize Claude skills for better trigger accuracy?▼

Claude skill benchmarking executes automated trigger evaluations across different configurations, collecting performance metrics to identify stability and efficiency gains. Benchmarking results generate actionable improvements for the skill body and triggering description to ensure robust, reliable activation.

What's the best way to evaluate Claude prompt performance?▼

To build a Claude skill from scratch, you generate structured SKILL.md content defining the skill body and triggering description. You then execute automated trigger evaluations, analyze the collected performance metrics, and iteratively improve the skill based on suggested benchmarking improvements.

Do I need yaml to create and benchmark Claude skills?▼

Improving Claude skill triggering accuracy involves analyzing performance metrics from automated trigger evaluations and benchmarking runs. The results suggest specific iterative improvements to the triggering description and skill body, pushing toward robust, discoverable, and reliable skill activation.

How do I benchmark Claude skills across different configurations?▼

Claude skill creation requires generating structured SKILL.md content, which defines the skill body and triggering description. This structured format enables automated trigger evaluations and benchmarking runs to collect metrics and drive iterative improvements to the skill.

Related Skills

Explore More Software Engineering Skills→
coreyjacoreyja
12

skill-writer

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

Community
Basic
jt302jt302
2

skill-creator

Draft SKILL.md files, run structured evals, and refine descriptions.

Community
Advanced
rickyanandarickyananda
1

dspy

Build and optimize declarative language model programs with structured signatures.

Community
Advanced
Shockwave2kShockwave2k

skill-creator

Draft SKILL.md files and run evaluation loops to measure trigger accuracy.

Community
Advanced