skill-creator

Create, evaluate, and refine AI skills through guided prompts and iterative feedback.

Updated Mar 14, 2026

Search Tags:#automation #prompt engineering #skill creation #benchmarking #evaluation #fine-tuning

Ready to run

npx skills add https://github.com/MessiasLima/opencode-settings --skill skill-creator-messiaslima

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/MessiasLima/opencode-settings/tree/main/skills/skill-creator
Command: npx skills add https://github.com/MessiasLima/opencode-settings --skill skill-creator-messiaslima

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Enables users to develop, modify, and evaluate AI skills seamlessly, reducing manual effort and guesswork.

Core Features & Use Cases

Skill Development: Draft, edit, and refine skills from scratch or existing templates.
Evaluation and Benchmarking: Run prompt tests, analyze results, and benchmark performance.
Iterative Improvement: Automate cycles of feedback incorporation and skill enhancement based on user input or evaluation metrics.
Use Case: A developer wants to build an automation skill. They start with a draft, run tests, review outputs, and iteratively refine the skill to improve accuracy and robustness.

Quick Start

Use the skill-creator to draft a new skill and then test its performance by providing sample prompts and reviewing generated outputs.

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 evaluate AI skills for automation workflows?▼

To create and evaluate AI skills, use guided prompts to draft the skill, run prompt tests to benchmark performance, and apply iterative feedback to refine trigger accuracy and robustness.

What is the best way to improve prompt engineering accuracy in skill development?▼

The best way to improve prompt engineering accuracy is through automated refinement cycles that incorporate evaluation metrics and user input to iteratively enhance the skill's structural clarity.

Can I benchmark AI skill performance using sample prompts?▼

Yes, you can benchmark AI skill performance by providing sample prompts, running evaluation tests, and reviewing the generated outputs to measure accuracy and identify areas for optimization.

Do I need fine-tuning to optimize AI skills, or can I use iterative feedback?▼

You do not strictly need fine-tuning; you can optimize AI skills by automating cycles of iterative feedback incorporation and scoring to enhance deployment robustness and overall performance.

When should I use guided workflows instead of manual prompt engineering for skill creation?▼

You should use guided workflows for skill creation when you need to reduce manual effort and guesswork, requiring structured development pipelines that support scoring and automated refinement.