skills.rest
herveDarritchon
herveDarritchonCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, test, and refine AI skills through guided prompt evaluation loops.

1|Updated Mar 15, 2025
Search Tags:#prompt engineering#optimization#AI development#evaluation#iteration#skill
One-click install
npx skills add https://github.com/herveDarritchon/foundryvtt-swerpg --skill skill-creator-hervedarritchon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/herveDarritchon/foundryvtt-swerpg/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/herveDarritchon/foundryvtt-swerpg --skill skill-creator-hervedarritchon

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of designing and optimizing AI capabilities by aiding users in creating, editing, and testing skills efficiently.

Core Features & Use Cases

  • Skill Development: Guides users through drafting and refining new skills based on their objectives.
  • Evaluation Automation: Facilitates running test prompts and analyzing performance metrics.
  • Iterative Improvement: Supports repeating testing-and-improvement cycles to enhance skill quality.
  • Use Case: An AI developer wants to build a skill that summarizes legal documents; this Skill helps craft prompts, run tests, and refine instructions iteratively.

Quick Start

Use this Skill to generate an initial skill draft from a high-level goal, then execute test prompts for performance evaluation.

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 refine an AI skill from a high-level prompt?▼

To create an AI skill, you formulate an initial draft from a high-level goal, run test prompts to evaluate performance metrics, and iteratively refine instructions to enhance skill quality.

What is iterative prompt engineering for skill development?▼

Iterative prompt engineering is the process of running test prompts, analyzing performance benchmarks, and repeating testing-and-improvement cycles to optimize AI capabilities and instructions.

How do I evaluate AI skill performance with automated testing?▼

You evaluate AI skill performance by executing test prompts against the skill draft, analyzing the resulting performance metrics, and using those benchmarks to guide iterative refinements.

Can I automate the evaluation loops for my custom AI capabilities?▼

Yes, you can automate evaluation loops by running test prompts to analyze performance metrics, supporting repeated testing-and-improvement cycles to streamline AI capability development.

Does this skill work for optimizing prompts for specific use cases like document summarization?▼

Yes, it guides drafting and refining skills for specific objectives like legal document summarization, helping you craft prompts, run tests, and refine instructions iteratively.

What are the limitations of using guided evaluation loops for AI development?▼

The evaluation process relies on the quality of the initial high-level goal and test prompts; poorly defined objectives or inadequate performance benchmarks may limit the effectiveness of iterative skill improvements.

Related Skills

Explore More Software Engineering Skills→
meta-pytorchmeta-pytorch
2.5k

work-on-issue

Parse GitHub issues into goals, acceptance criteria, and constraints.

Official
Intermediate
getsentrygetsentry
905

prompt-optimizer

Optimize agent prompts across OpenAI, Claude, and Gemini with eval-driven refinements.

Official
Advanced
danielshmayaidanielshmayai

self-improvement

Automate feedback collection, evaluation, and refinement loops for Claude-powered apps.

Community
Advanced
swkim0128swkim0128

skill-creator

Create, modify, test, and optimize AI skill descriptions and performance.

Community
Advanced