skill-creator

Create, modify, test, and optimize AI skills with SKILL.md files.

493|101|Updated Nov 8, 2024
One-click install
npx skills add https://github.com/coinbase/cds --skill skill-creator-coinbase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/coinbase/cds/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/coinbase/cds --skill skill-creator-coinbase

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill empowers you to create new AI skills from scratch, modify and enhance existing ones, and rigorously test their performance to ensure they meet your needs.

Core Features & Use Cases

  • Skill Creation: Guide users through defining intent, writing SKILL.md, and structuring skill resources.
  • Iterative Improvement: Facilitate testing, evaluation, and refinement of skills based on performance metrics and user feedback.
  • Performance Benchmarking: Run evaluations against baseline models to quantify skill effectiveness and identify areas for optimization.
  • Description Optimization: Automatically refine skill descriptions to improve triggering accuracy.
  • Use Case: You have an idea for a new skill to help draft marketing copy. Use this Skill to define its purpose, write the initial SKILL.md, create test prompts, run evaluations, and iterate on the skill's logic and description until it performs reliably.

Quick Start

Use the skill-creator to start building a new skill for summarizing meeting notes.

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 structure a new AI skill from scratch?

To create an AI skill, define its intent and write a structured SKILL.md file to configure the skill's resources and processing logic. This establishes the foundational definition required for the skill to function reliably.

What is the best way to evaluate and benchmark AI skill performance?

Evaluating AI skill performance involves running automated tests against baseline models to generate quantitative benchmarks. This process identifies areas for optimization and measures overall skill effectiveness.

How can I improve AI skill triggering accuracy through prompt engineering?

Improve AI skill triggering accuracy by using description optimization to automatically refine your skill definitions. This adjusts the prompt engineering parameters to ensure the correct skill activates.

Can I iteratively refine code generation logic based on testing metrics?

Yes, you can iteratively refine code generation logic by analyzing quantitative performance benchmarks and user feedback. This enables continuous modification and enhancement of the skill's internal processing.

Do I need any external dependencies to build and test AI skills?

No external dependencies are required to build and test AI skills. The environment operates independently using internal scripts, references, and assets to facilitate the entire development lifecycle.