skills.rest
mfmezger
mfmezgerCOMMUNITY
Explore all skills by this author →
Website𝕏@mfmezgerGitHub

skill-creator

Create, refine, and evaluate AI skills with SKILL.md and automated tests.

5|Updated Feb 2, 2026
Search Tags:#automation#skill development#testing#prompt engineering#evaluation#ai agent
One-click install
npx skills add https://github.com/mfmezger/ai_agent_dotfiles --skill skill-creator-mfmezger
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/mfmezger/ai_agent_dotfiles/tree/main/shared/skills/skill-creator
Command: npx skills add https://github.com/mfmezger/ai_agent_dotfiles --skill skill-creator-mfmezger

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the entire lifecycle of creating and improving AI capabilities, from initial concept to robust performance measurement.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing SKILL.md, and structuring skill resources.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement based on user feedback and performance metrics.
  • Performance Benchmarking: Runs automated tests against baseline models to quantify skill effectiveness.
  • Description Optimization: Fine-tunes skill descriptions for optimal triggering accuracy.
  • Use Case: A developer wants to create a new skill to summarize code files. They use this Skill to draft the SKILL.md, write test cases, run evaluations, analyze the results, and optimize the description for better triggering.

Quick Start

Use the skill creator to help me build a new skill that can summarize markdown files.

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 AI skills for automation workflows?▼

To build and test AI skills, you define skill intent, draft a SKILL.md file, bundle resources, and run automated test cases against baselines to measure performance. This iterative process ensures robust skill development and quality assurance.

What is the best way to optimize AI agent descriptions for accurate triggering?▼

Optimizing AI agent descriptions for triggering accuracy involves fine-tuning the skill text. By running automated evaluations and analyzing results via a web viewer, you iteratively refine descriptions to ensure the agent activates correctly in relevant scenarios.

Can I run automated test cases against baseline models for prompt engineering?▼

Yes, you can run automated test cases against baseline models for prompt engineering. The skill facilitates performance benchmarking by executing tests, allowing you to quantify prompt effectiveness and make data-driven refinements.

How does performance benchmarking work for AI skill evaluation?▼

Performance benchmarking for AI skill evaluation works by running automated test cases against baseline models to quantify effectiveness. You analyze results via a web viewer to identify areas for iterative improvement and ensure quality assurance.

Do I need external evaluation frameworks to refine SKILL.md files?▼

You do not need external evaluation frameworks to refine SKILL.md files, as the skill integrates internal evaluation capabilities. It supports iterative development by analyzing test results and user feedback directly to improve skill structure.

Related Skills

Explore More Software Engineering Skills→
Crispy13Crispy13

skill-creator-copilot

Draft SKILL.md files with frontmatter, instructions, and test workflows.

Community
Advanced
niduran-orionniduran-orion

skill-creator

Create, evaluate, and refine Claude skills with SKILL.md and trigger evaluations.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

skill-creator

Create AI skills with structured evaluation and benchmarking workflows for GLM Code.

Community
Advanced
bdbchbdbch
2

browser-test

Execute manual browser tests in Chrome with navigation, form interactions, and state verification.

Community
Intermediate