skill-creator

Create, modify, and evaluate AI skills with SKILL.md files and automated tests.

Updated Feb 18, 2026
One-click install
npx skills add https://github.com/nakaj1214/trader --skill skill-creator-nakaj1214
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/nakaj1214/trader/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/nakaj1214/trader --skill skill-creator-nakaj1214

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 developing and refining AI capabilities, from initial concept to performance measurement, making it easier to build powerful and accurate AI tools.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, writing SKILL.md, and structuring skill resources.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement based on user feedback and performance metrics.
  • Performance Benchmarking: Runs automated tests and provides detailed analysis of skill execution.
  • Description Optimization: Improves skill triggering accuracy through targeted prompt engineering and evaluation.
  • Use Case: A developer wants to create a new AI skill to summarize meeting transcripts. They use this Skill to draft the SKILL.md, write test cases, run evaluations, analyze the results, and iterate on the skill's instructions and description until it performs reliably.

Quick Start

Use the skill creator to help me build a new skill that can generate 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 build and test AI skills from scratch?

To build AI skills, you need to define the skill intent, write the `SKILL.md` file, and structure bundled resources. You can then run automated test cases against skill performance to evaluate and refine the execution logic iteratively.

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

Improving AI skill triggering accuracy requires targeted prompt engineering and description optimization. By running automated evaluations and analyzing benchmark reports, you can iteratively refine the skill descriptions to ensure reliable and precise execution.

How do I evaluate AI prompt performance using automated test cases?

You can evaluate AI prompt performance by running automated test cases against the defined skill instructions. The process generates detailed benchmark reports that analyze execution results, allowing you to measure and optimize the prompt's effectiveness.

Can I use this to modify an existing SKILL.md file?

Yes, you can modify an existing `SKILL.md` file. The tool handles both new skill development and iterative refinement, allowing you to update instructions, optimize descriptions, and re-run evaluations based on new performance metrics or user feedback.

What is included when structuring bundled resources for skill development?

Structuring bundled resources for skill development involves organizing scripts, references, and assets. These components support the core processing logic defined in the `SKILL.md` file, ensuring the AI skill has access to the necessary data and tools for execution.