skill-creator

Create, refine, and benchmark AI skills through iterative AI-guided workflows.

5|1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/cognitedata/builder-skills --skill skill-creator-cognitedata
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/cognitedata/builder-skills/tree/main/skills/skill-creator
Command: npx skills add https://github.com/cognitedata/builder-skills --skill skill-creator-cognitedata

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies creating, editing, and evaluating AI skills, reducing manual effort and accelerating development cycles.

Core Features & Use Cases

  • Skill Crafting: Generate and tailor new skills from scratch using AI suggestions.
  • Iterative Improvement: Refine existing skills with feedback-driven revisions.
  • Benchmarking: Measure skill performance quantitatively and optimize trigger accuracy.
  • Use Case: Develop a new data analysis skill, then iteratively enhance its prompts and trigger conditions based on test results to maximize relevance.

Quick Start

Create a basic skill file, then run the pull command to incorporate it into your system.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I streamline AI skill creation and reduce manual development effort?

AI skill creation is streamlined through AI-guided processes that generate and tailor new skills from scratch, significantly reducing manual effort. The system provides code suggestions and prompt optimization to accelerate your development cycles.

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

Iterative improvement of AI skills is achieved through feedback-driven revisions that refine existing prompts and trigger conditions. This process allows developers to continuously enhance skill quality based on targeted test results.

How can I benchmark AI skill performance and optimize trigger accuracy?

Benchmarking measures AI skill performance quantitatively to evaluate quality assurance and optimize trigger accuracy. By analyzing test results, developers can adjust prompts and conditions to maximize relevance.

Do I need any external dependencies to start developing and evaluating AI skills?

No external dependencies are required to develop and evaluate AI skills, as the system operates independently. You only need to create a basic skill file and run the pull command to incorporate it into your environment.

Can I use this for rapid prototyping of data analysis skills?

Yes, rapid prototyping is fully supported for developing data analysis skills and other use cases. You can create a basic skill, then iteratively enhance its prompts and trigger conditions based on test results.

Why does my AI skill lack relevance and how can prompt optimization help?

AI skills lack relevance when trigger conditions and prompts are misaligned with target tasks. Prompt optimization workflows refine these elements using quantitative performance measurements to maximize accuracy and quality.