skills.rest
EduardoSousaPO
EduardoSousaPOCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, test, and optimize AI skills with SKILL.md files and benchmarks.

Updated Aug 23, 2026
Search Tags:#skill development#testing#prompt engineering#optimization#AI agent#evaluation
One-click install
npx skills add https://github.com/EduardoSousaPO/Ads-Claw- --skill skill-creator-eduardosousapo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/EduardoSousaPO/Ads-Claw-/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/EduardoSousaPO/Ads-Claw- --skill skill-creator-eduardosousapo

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 skills, from initial concept to performance optimization, making AI development accessible and efficient.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, interviewing for details, and writing the SKILL.md file.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on performance metrics and user feedback.
  • Description Optimization: Enhances skill discoverability and triggering accuracy through automated testing and AI-driven description rewriting.
  • Use Case: You have an idea for a new AI capability, like summarizing meeting notes. Use this Skill to draft the initial skill, write test cases, run evaluations, analyze results, and iterate on the skill's logic and description until it performs optimally.

Quick Start

Use the skill-creator to help me build a new skill that can generate commit messages from git diffs.

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 from scratch?▼

To build and test AI skills, you define the skill intent, draft the SKILL.md content, set up evaluation test cases, and run performance benchmarks against baseline models to iteratively improve triggering accuracy.

What is the best way to optimize AI agent prompts for better triggering accuracy?▼

Optimizing AI agent prompts involves running automated testing and AI-driven description rewriting loops, using blind comparison and performance benchmarks to iteratively refine the SKILL.md content.

How does performance benchmarking work for prompt engineering?▼

Performance benchmarking for prompt engineering works by running evaluation test cases against baseline models, analyzing the results, and iteratively improving the skill descriptions to enhance overall discoverability and accuracy.

Can I set up evaluation test cases for AI skills without prior testing frameworks?▼

Yes, you can set up evaluation test cases without external testing frameworks by using built-in scripts and references to define test scenarios, run performance benchmarks, and evaluate AI agent responses directly.

How do I refine skill descriptions when AI agent triggering is inaccurate?▼

To refine skill descriptions when triggering is inaccurate, you run description optimization loops, analyze performance metrics from test cases, and iteratively rewrite the skill logic until optimal accuracy is achieved.

Related Skills

Explore More Software Engineering Skills→
fagemxfagemx
2

domain-plan

Derive domain skill maps and artifact flows with lifecycle stages and gap analysis.

Community
Advanced
LittleSongxxLittleSongxx
2

skill-creator

Create, evaluate, and optimize AI skills with SKILL.md files.

Community
Advanced
jin-bojin-bo
94

skill-creator

Automate creation, testing, and optimization of Claude Code skills.

Community
Advanced
zhongjiszhongjis

skill-creator

Create, test, and optimize AI skills with SKILL.md files.

Community
Advanced