skill-creator

Create and refine AI skills with SKILL.md files and performance evaluations.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/Jaydpatel01/.github --skill skill-creator-jaydpatel01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Jaydpatel01/.github/tree/main/skills/skill-creator
Command: npx skills add https://github.com/Jaydpatel01/.github --skill skill-creator-jaydpatel01

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-powered skills, from initial concept to performance optimization and deployment.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, interviewing for requirements, and writing SKILL.md files.
  • 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 targeted prompt engineering.
  • Use Case: You have an idea for a new AI assistant capability, like summarizing meeting transcripts. Use this Skill to draft the SKILL.md, write test cases, run evaluations against a baseline, analyze the 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 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 build and test an AI agent skill from scratch?

To build an AI agent skill, you define the intent, write the SKILL.md file, and run iterative testing with quantitative and qualitative evaluations to benchmark performance and refine the logic.

What is the best way to improve AI skill invocation accuracy?

Improving AI skill invocation accuracy requires targeted description tuning and prompt engineering to enhance discoverability, ensuring the skill triggers reliably based on user intent during evaluations.

Can I use this workflow to evaluate prompt engineering changes against a baseline?

Yes, you can evaluate prompt engineering changes by running iterative tests against a performance baseline, analyzing quantitative and qualitative metrics to measure improvements in the AI skill.

How do I start the skill development process for a new AI capability?

Skill development starts by interviewing for requirements and drafting the initial SKILL.md file, which establishes the core logic and intent before moving into iterative testing and refinement.

Does this skill development lifecycle support quantitative performance benchmarking?

Yes, the skill development lifecycle supports quantitative performance benchmarking by facilitating structured evaluations that measure how well the AI skill performs against defined test cases and baselines.

When should I iterate on an AI skill's description and logic?

You should iterate on an AI skill's description and logic after analyzing evaluation results and user feedback, refining both the prompt engineering and processing logic until performance metrics meet optimal standards.