skills.rest
AidenSbVevo
AidenSbVevoCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, evaluate, and optimize custom AI skill units with automated testing.

1|Updated Jul 5, 2026
Search Tags:#automation#workflow#testing#optimization#benchmarking#evaluation
One-click install
npx skills add https://github.com/AidenSbVevo/claude-code-starter --skill skill-creator-aidensbvevo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/AidenSbVevo/claude-code-starter/tree/main/skills/skill-creator
Command: npx skills add https://github.com/AidenSbVevo/claude-code-starter --skill skill-creator-aidensbvevo

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of creating reliable, high-performing AI workflows by providing a structured environment for drafting, testing, and refining custom skills.

Core Features & Use Cases

  • Iterative Development: Provides a loop for drafting, running, and evaluating skills against real-world prompts.
  • Quantitative Benchmarking: Includes tools to measure pass rates, token usage, and execution time to ensure skill quality.
  • Trigger Optimization: Features a dedicated loop to refine skill descriptions, ensuring Claude triggers the skill exactly when needed.
  • Use Case: If you need to build a custom skill for complex data analysis, use this to draft the logic, run it against 20 test cases, and automatically optimize the description so Claude knows when to use it.

Quick Start

Use the skill-creator to help me draft a new skill for automating my weekly project status reports.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I build and test custom AI workflows?▼

To build and test custom AI workflows, use an iterative development environment that drafts logic, runs automated subagent workflows against real-world prompts, and evaluates performance to ensure reliability.

What is quantitative benchmarking for AI skills?▼

Quantitative benchmarking for AI skills is the process of measuring pass rates, token usage, and execution time to evaluate workflow quality and ensure custom skills perform efficiently under testing conditions.

How do I optimize AI skill descriptions for accurate triggering?▼

You optimize AI skill descriptions for accurate triggering by using a dedicated refinement loop that adjusts the text so the AI model triggers the custom skill exactly when needed based on user prompts.

Can I automate evaluation tests for custom AI skills?▼

Yes, you can automate evaluation tests for custom AI skills by integrating local scripts to manage test cases, grade performance, and visualize benchmark results within an iterative testing loop.

Do I need local scripts to benchmark AI performance metrics?▼

Local scripts are required to benchmark AI performance metrics because they manage the test cases, grading logic, and benchmark visualization needed to measure pass rates and execution time accurately.

Related Skills

Explore More Software Engineering Skills→
NicolasPadovamNicolasPadovam

opensquad-skill-creator

Develop, evaluate, and optimize custom agent skills within the Opensquad framework.

Community
Advanced
I194I194
9

canary

Monitor deployed apps for console errors, performance regressions, and page failures.

Community
Advanced
guanyangguanyang
947

skill-creator

Create, modify, and evaluate AI skills with testing and benchmarking.

Community
Advanced
apassuelloapassuello

llm-evaluation

Evaluate LLM outputs with automated metrics, human judgments, and benchmarking.

Community
Advanced