skill-creator

Creates, modifies, and optimizes AI skills with testing and feedback.

Updated Jun 18, 2026
One-click install
npx skills add https://github.com/liujiayi3703/scientific-research-skills --skill skill-creator-liujiayi3703
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/liujiayi3703/scientific-research-skills/tree/main/library/skills/skill-creator
Command: npx skills add https://github.com/liujiayi3703/scientific-research-skills --skill skill-creator-liujiayi3703

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scripts.aggregate_benchmark, scripts.run_loop, scripts.package_skill, scripts.generate_report, agents.comparator, agents.analyzer, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill unit provides a comprehensive toolkit for creating, modifying, and optimizing AI skills, addressing the challenges of skill development and performance enhancement.

Core Features & Use Cases

  • Skill Creation: Guided process for drafting, testing, and refining new skills.
  • Skill Modification: Iterative improvement of existing skills based on feedback and testing.
  • Skill Performance Measurement: Benchmarking and optimization of skill performance through quantitative and qualitative metrics.
  • Use Case: Develop a skill for generating code from natural language descriptions, refine it through multiple iterations, and measure its performance against a set of predefined benchmarks.

Quick Start

Use the skill-creator skill to initiate the process of creating a new skill, providing the desired functionality and context.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I start AI skill development from a natural language description?

AI skill development starts by providing the desired functionality and context to initiate a guided process for drafting, testing, and refining new skills. This workflow handles everything from initial creation to iterative improvement.

What is the best way to iteratively improve existing AI skills?

Iterative improvement of AI skills is achieved through a modification workflow that incorporates testing and collected feedback. This process refines existing skills continuously to enhance their overall performance.

How does performance benchmarking work for AI crafting workflows?

Performance benchmarking measures AI crafting workflows by evaluating skills against predefined benchmarks using quantitative and qualitative metrics. This generates reports that guide targeted optimization.

Do I need specific dependencies to run skill optimization and benchmarking?

Skill optimization and benchmarking require specific dependencies like aggregate benchmark scripts, run loop scripts, and analyzer agents. These components execute the testing, analysis, and reporting functions.

Can I use this workflow to package and generate reports for newly created skills?

You can package skills and generate reports using dedicated scripts within the workflow. This outputs finalized skill units and performance documentation after the testing and analysis phases.