skill-creator

Create and refine AI skills with SKILL.md files and evaluation frameworks.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/ZJUxjy/opencode_lite --skill skill-creator-zjuxjy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ZJUxjy/opencode_lite/tree/main/skills/skill-creator
Command: npx skills add https://github.com/ZJUxjy/opencode_lite --skill skill-creator-zjuxjy

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 evaluating AI capabilities, making it accessible to users of all technical backgrounds.

Core Features & Use Cases

  • Skill Creation: Guide users from intent capture to writing SKILL.md files.
  • Iterative Improvement: Facilitate testing, evaluation, and refinement loops based on user feedback and performance metrics.
  • Description Optimization: Automatically tune skill descriptions for optimal triggering accuracy.
  • Use Case: You have an idea for a new AI assistant feature. Use this Skill to draft the SKILL.md, create test cases, run evaluations, and iterate on the description until it performs perfectly.

Quick Start

Use the skill-creator to help me build a new skill that can summarize long documents.

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 refine an AI agent skill from scratch?

To build an AI agent skill, you capture user intent and draft a SKILL.md file, then iteratively refine it by running benchmarks and optimizing descriptions for enhanced triggering accuracy.

What is the process for evaluating LLM tools and prompt engineering outputs?

Evaluating LLM tools involves setting up an evaluation framework using testing scripts, running benchmarks on prompt engineering outputs, and refining the skill based on performance metrics.

How can I optimize AI skill descriptions for better triggering accuracy?

You optimize AI skill descriptions by automatically tuning the text within the SKILL.md file during the iterative improvement phase to ensure optimal and accurate skill triggering.

Do I need programming experience to create and test AI skills?

No programming experience is strictly required to create and test AI skills, as the process streamlines intent capture, SKILL.md generation, and evaluation framework setup for all technical backgrounds.

What is the best way to structure an iterative improvement loop for AI development?

The best way to structure iterative improvement for AI development is to loop through testing, evaluation, and refinement based on user feedback and performance metrics until the skill performs perfectly.