skills.rest
MimicHunterZ
MimicHunterZCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

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

56|4|Updated Oct 29, 2025
Search Tags:#testing#prompt engineering#optimization#ai development#skill creation#evaluation
One-click install
npx skills add https://github.com/MimicHunterZ/PocketMind --skill skill-creator-mimichunterz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/MimicHunterZ/PocketMind/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/MimicHunterZ/PocketMind --skill skill-creator-mimichunterz

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 refining AI capabilities, from initial concept to performance optimization.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing SKILL.md, and structuring skill directories.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on performance metrics and user feedback.
  • Description Optimization: Enhances skill triggering accuracy by iteratively improving the description field in SKILL.md.
  • Use Case: A developer wants to build a new AI skill to summarize meeting transcripts. They use this Skill to draft the SKILL.md, write test cases, run evaluations, and optimize the skill's description for better triggering.

Quick Start

Use the skill-creator skill to help me create a new skill for generating commit messages from code changes.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create an AI skill from scratch using prompt engineering?▼

To create an AI skill, you define the skill intent, draft the SKILL.md content, and structure the skill directories. This process facilitates end-to-end skill creation by guiding you through writing descriptions and structuring assets for accurate triggering.

What is the best way to test and evaluate AI skill performance?▼

The best way to test AI skill performance is by generating test cases and running evaluations with baseline comparisons. This process analyzes results and facilitates iterative improvement of skill descriptions for accurate triggering.

How do I optimize AI skill descriptions for better triggering accuracy?▼

You optimize AI skill descriptions by iteratively refining the description field in SKILL.md based on performance metrics. This enhancement integrates with evaluation frameworks for performance benchmarking to ensure accurate skill triggering.

Can I benchmark AI skill performance against a baseline?▼

Yes, you can benchmark AI skill performance against a baseline. The evaluation framework integrates with testing workflows to analyze results, compare performance metrics, and iteratively improve skill behavior.

What do I need to structure an AI skill directory for development?▼

Structuring an AI skill directory requires defining the skill intent and organizing components like scripts, references, and assets. This setup provides guidance on skill structure and best practices for development and optimization.

Related Skills

Explore More Software Engineering Skills→
Fr-e-dFr-e-d
157

architecture-extract

Analyze project directory structures to generate architectural summaries.

Community
Basic
Syedyasir001Syedyasir001

evaluation

Evaluate agent performance using multi-dimensional rubrics for accuracy and tool efficiency.

Community
Advanced
yuyalun-allenyuyalun-allen

skill-creator

Create and iteratively improve LLM skill definitions with evaluation workflows.

Community
Advanced
Fantasia1999Fantasia1999

skill-creator

Create, test, and refine AI skills with structured development workflows.

Community
Advanced