skill-creator

Automate the creation, testing, and refinement of Claude skills.

2|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/ingbyr/lzcode --skill skill-creator-ingbyr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ingbyr/lzcode/tree/main/packages/desktop/src-tauri/lz-assets/skills/skill-creator
Command: npx skills add https://github.com/ingbyr/lzcode --skill skill-creator-ingbyr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml.

What problem does it solve?

The Skill Creator addresses the slow, manual process of building, tuning, and validating Claude skills. It provides a repeatable workflow to go from a draft SKILL.md to a reliable, trigger-ready skill.

Core Features & Use Cases

  • Draft and structure SKILL.md frontmatter and body to define a new skill.
  • Run iterative evaluation loops to test triggering and performance across varied prompts.
  • Generate and compare descriptions to optimize triggering accuracy and user guidance.
  • Package validated skills into distributable bundles (.skill) for deployment.
  • Produce reports and benchmarks to guide decision-making and continuous improvement.

Quick Start

Draft your SKILL.md, run the built-in loop to test triggers, review results, and iterate until the skill reliably triggers.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate Claude skill creation and testing?

Automate Claude skill creation by drafting a SKILL.md file, running iterative evaluation loops to test triggers, and refining the skill until it reliably performs. The workflow moves through draft, test, review, and improve stages to optimize trigger accuracy.

What is the best way to validate SKILL.md frontmatter for a new skill?

Validate SKILL.md frontmatter by checking that the name and description fields meet structural requirements and trigger accurately. Automated evaluation loops test the frontmatter against varied prompts to ensure reliable activation before deployment.

How does iterative evaluation improve Claude skill triggering accuracy?

Iterative evaluation improves triggering accuracy by running the skill against varied prompts, reviewing the results, and refining the description. This loop continues until the skill reliably triggers only when intended, reducing false activations.

Can I package validated Claude skills into distributable bundles?

Package validated Claude skills into distributable .skill bundles for deployment. These bundles can include optional resources like scripts, references, and assets needed for deterministic task execution.

Do I need pyyaml to use the skill-creator workflow?

You need pyyaml installed to use the skill-creator workflow, as it is a required dependency for parsing and validating the YAML frontmatter within your SKILL.md files.

Why is my Claude skill not triggering correctly from user prompts?

A Claude skill fails to trigger correctly when the SKILL.md description lacks accuracy. Resolve this by generating and comparing descriptions, then running iterative evaluation loops to test and refine triggering across varied prompts.