skill-creator

Generate and edit SKILL.md files and run evals to measure performance.

Updated Mar 21, 2026
One-click install
npx skills add https://github.com/debridge-finance/debridge-skills --skill skill-creator-debridge-finance
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/debridge-finance/debridge-skills/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/debridge-finance/debridge-skills --skill skill-creator-debridge-finance

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you create new skills, modify and improve existing skills, and measure skill performance with evals to accelerate development.

Core Features & Use Cases

  • Create new skills: generate starter SKILL.md and basic structure for rapid experimentation.
  • Modify and optimize: edit existing skills and improve prompts, configs, and evaluation metrics.
  • Performance evaluation: run evals to benchmark skill behavior and iterate improvements across datasets.

Quick Start

Provide a goal for a new skill and let this skill generate the SKILL.md scaffolding and run a baseline eval.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I generate a new AI skill template from scratch?

You can generate a new skill template by providing a goal, which produces a starter SKILL.md scaffolding with frontmatter-driven definitions and an actionable Markdown body for rapid bootstrapping.

How can I benchmark AI skill performance using evals?

Benchmark AI skill performance by running evals across datasets to measure effectiveness, identify behavioral gaps, and iterate improvements to prompts and evaluation metrics.

What is the best way to modify and optimize an existing AI skill?

Modify and optimize an existing AI skill by editing the SKILL.md file to refine prompts, update frontmatter configurations, and adjust evaluation metrics for improved behavior.

Does skill scaffolding require specific dependencies to set up?

No specific dependencies are required to set up skill scaffolding. The process relies on a frontmatter-driven skill definition to produce an actionable Markdown body with operational instructions.

Can I run a baseline eval immediately after generating a skill?

Yes, you can run a baseline eval immediately after generating a skill template. The quick start process generates the SKILL.md scaffolding and runs a baseline eval to measure initial behavior.

When should I not use automated skill generation and evaluation?

Avoid automated skill generation when your task requires complex, non-Markdown configurations outside the frontmatter-driven definition, or when evaluating unstructured datasets lacking clear metrics.