skills.rest
cwittorf
cwittorfCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, modify, and evaluate AI skills with SKILL.md authoring and test cases.

Updated Mar 12, 2026
Search Tags:#skill development#prompt engineering#optimization#llm#evaluation#ai skills
One-click install
npx skills add https://github.com/cwittorf/claudefluent --skill skill-creator-cwittorf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/cwittorf/claudefluent/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/cwittorf/claudefluent --skill skill-creator-cwittorf

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 process of creating, improving, and testing AI skills, from initial concept to performance optimization.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing SKILL.md, and setting up test cases.
  • Iterative Improvement: Facilitates rewriting and refining skills based on evaluation feedback.
  • Performance Measurement: Runs evaluations and benchmarks to quantify skill effectiveness and identify areas for optimization.
  • Use Case: You have an idea for a new AI capability, like summarizing meeting notes. Use this Skill to draft the initial SKILL.md, create test prompts, run evaluations, analyze the results, and iterate on the description and instructions until it performs reliably.

Quick Start

Use the skill creator to help me draft a new skill that can summarize meeting transcripts.

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 test AI skills for prompt engineering?▼

Iterative improvement uses quantitative and qualitative evaluation feedback to refine your `SKILL.md` file. You rewrite the skill instructions, run benchmarks again, and analyze the results to optimize LLM performance until the skill meets your target metrics.

What is the best way to structure a SKILL.md file for LLM optimization?▼

The best way to structure a `SKILL.md` file is by using guided intent capture to define the core task clearly. You then pair this description with generated test cases to evaluate LLM performance, ensuring the instructions are optimized for your specific AI capability.

Can I evaluate AI skills quantitatively before deploying them?▼

Yes, you can evaluate AI skills quantitatively by running performance benchmarks and generating test cases. The skill development process measures effectiveness by analyzing test results, allowing you to identify areas for optimization and iterate on the description before deployment.

Do I need prior prompt engineering experience to build AI skills?▼

No prior prompt engineering experience is required to build AI skills because the system provides guided intent capture. It facilitates the end-to-end lifecycle by helping you author the `SKILL.md` file and automatically generating test cases for evaluation.

Why does my AI skill performance fluctuate during LLM evaluation?▼

AI skill performance fluctuates during LLM evaluation when the `SKILL.md` instructions lack optimization or the test cases do not cover edge cases. You resolve this by analyzing the evaluation feedback and iteratively refining the skill description to stabilize outputs.

Related Skills

Explore More Software Engineering Skills→
mlopscommunitymlopscommunity
37

voice-first-planning

Convert spoken transcripts into structured feature specifications and requirements.

Official
Basic
spideynolovespideynolove
2

llm-evaluation

Evaluate LLM outputs with automated metrics and human evaluation checklists.

Community
Advanced
AidenSbVevoAidenSbVevo
1

skill-creator

Create, evaluate, and optimize custom AI skill units with automated testing.

Community
Advanced
open-nekoopen-neko
11

skill-creator

Create and iteratively improve AI agent skills through structured evaluation and benchmarking.

Official
Advanced