skill-creator

Draft SKILL.md files, create evals, and run trigger tests for Claude Skills.

Updated May 14, 2026
One-click install
npx skills add https://github.com/LeroyAdonis/vector --skill skill-creator-leroyadonis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/LeroyAdonis/vector/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/LeroyAdonis/vector --skill skill-creator-leroyadonis

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Helps teams translate ideas for new Claude Skills into a formal, iteratable process: drafting SKILL.md, building eval sets, running trigger tests, and iterating descriptions to improve triggering accuracy and usefulness.

Core Features & Use Cases

  • Create, modify, and evaluate skills with an integrated loop: draft, test, review, and refine.
  • Generate structured evals, run parallel trigger tests, and compare configurations (with_skill vs without_skill) to quantify value.
  • Bundle templates, scripts, and references for rapid production-grade skill development in AI-assisted workflows.

Quick Start

Use the skill creator workflow to outline a new skill, generate its SKILL.md, and begin an iterative eval-improvement cycle.

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 evaluate reusable Claude skills through an automated workflow?

To create reusable skills, draft a SKILL.md file, generate structured eval sets, run parallel trigger tests comparing with_skill and without_skill configurations, and iterate descriptions to refine triggering accuracy and usefulness.

What is the process for turning an idea into a production-grade skill with bundled scripts and references?

Turning ideas into skills involves outlining capabilities, drafting SKILL.md, creating evals, executing trigger tests, and bundling scripts, references, and assets with validation, versioning, and description optimization until maturity.

How do I test and iterate skill descriptions to improve triggering accuracy?

Improve triggering accuracy by running parallel trigger tests that compare with_skill and without_skill configurations, then reviewing eval results to quantify value and iteratively refining the skill descriptions.

Can I use PyYAML to manage skill configuration and versioning for multiple domains?

Yes, PyYAML supports managing skill configurations by enabling structured validation, versioning, and description optimization across multiple domains during the iterative draft, test, and refine cycle.

What's the best way to identify capability gaps and translate them into formal skills?

Identify capability gaps by analyzing workflow needs, then translate them into formal skills by drafting SKILL.md, building eval sets, running trigger tests, and iterating until the skill reaches maturity.

Does this skill creation workflow support versioning and validation for bundled assets?

Yes, the skill creation workflow supports bundling scripts, references, and assets with built-in validation and versioning to ensure production-grade skill development and reliable iteration.