uw-skill-creator

Automate creation, validation, and refinement of Claude Code skills.

40|6|Updated Jan 21, 2026

Search Tags:#automation #workflow #evaluation #packaging #iteration #skill #claude-code

Ready to run

npx skills add https://github.com/devdavv/unity-ai-workflow --skill uw-skill-creator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: uw-skill-creator
Source: https://github.com/devdavv/unity-ai-workflow/tree/main/.claude/skills/uw-skill-creator
Command: npx skills add https://github.com/devdavv/unity-ai-workflow --skill uw-skill-creator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) components.

What problem does it solve?

Streamlines the creation, validation, and refinement of Claude Code skills by providing a structured workflow, automation scripts, and templates.

Core Features & Use Cases

A suite of scripts for drafting, testing, and iterating SKILL.md files, evaluating prompts, and packaging skills.
A guidance framework to capture test prompts, evaluate results, and drive iterative improvements via evals, benchmarking, and trigger optimization.
A scalable workflow that coordinates discovery, validation, and versioned improvement loops across multiple skills.

Quick Start

Use this toolkit to scaffold a new skill: edit SKILL.md, run the evaluation loop and iterate until trigger accuracy is high.

Frequently Asked Questions about uw-skill-creator

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

FAQPage Schema

How do I automate Claude Code skill creation and validation?▼

You can automate Claude Code skill creation by using scriptable workflows to draft SKILL.md files, generate test prompts, and run iterative evaluation loops. This structured approach coordinates discovery, validation, and versioned improvements.

What is the best way to iterate on Claude Code skills with evals and benchmarks?▼

The best way to iterate on Claude Code skills is through a structured evaluation loop that captures test prompts, benchmarks results, and refines frontmatter. This workflow drives versioned improvements and optimizes trigger reliability.

How does trigger optimization work when packaging Claude Code skills?▼

Trigger optimization works by refining the skill description and frontmatter during the packaging process. This improves how accurately the skill activates when users submit relevant prompts.

Do I need pyyaml to run the skill evaluation workflow?▼

Yes, pyyaml is a required dependency for running the automation scripts. It supports the parsing and drafting of frontmatter data needed to validate and scaffold SKILL.md files.

Can I use this workflow to scale validation across multiple skills?▼

Yes, the workflow is designed to scale validation across multiple skills. It coordinates discovery, testing, and versioned improvement loops to maintain quality across a suite of Claude Code skills.

What is a structured interview capture process for skill drafting?▼

Structured interview capture is a guided framework that collects requirements and test prompts to draft initial SKILL.md files. It ensures the skill's core task and frontmatter accurately reflect the intended automation logic.