skill-creator

Automate SKILL.md authoring, resource bundling, and evaluation loops.

1|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/cr330326/AgentSkill --skill skill-creator-cr330326
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/cr330326/AgentSkill/tree/main/skill-creator
Command: npx skills add https://github.com/cr330326/AgentSkill --skill skill-creator-cr330326

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates the end-to-end workflow of creating, validating, and iterating Claude Skills, linking frontmatter design to runtime evaluation to improve reliability and discoverability.

Core Features & Use Cases

  • Structured SKILL.md development with YAML frontmatter for discoverability and routing.
  • Integrated evaluation and improvement loops (run_eval, improve_description) to test, compare, and optimize skills.
  • Bundled resources management (scripts/, references/, assets/) for on-demand tasks and richer context.

Quick Start

Draft a new SKILL.md, organize optional resources under scripts/, references/, and assets/, then run the evaluation loop to test and refine the skill.

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 evaluation end-to-end?

You can automate Claude Skill creation and evaluation by orchestrating a workflow that links SKILL.md authoring with automated evaluation loops, enabling rapid iteration to improve triggering reliability and description discoverability.

What is the best way to structure a SKILL.md file for reliable routing and discoverability?

The best way to structure a SKILL.md file is using YAML frontmatter for metadata routing, then organizing optional resources into bundled directories like scripts/, references/, and assets/ for on-demand context loading.

How does the improve_description evaluation loop optimize skill triggering?

The improve_description evaluation loop optimizes skill triggering by running automated tests, comparing runtime data, and iterating on the description to produce clear, action-oriented text that ensures reliable activation.

Do I need to install dependencies to manage bundled resources in skill workflows?

Yes, you need to install dependencies like pyyaml to manage bundled resources in skill workflows, as it is required to parse the YAML frontmatter that drives discoverability and resource routing.

Can I use this workflow to test and compare different versions of a skill description?

Yes, you can use the integrated evaluation loops to test and compare different versions of a skill description, allowing your team to iterate based on runtime data from automated runs and maintain a robust structure.

Why does my skill fail to trigger reliably during runtime evaluation?

Skills fail to trigger reliably during runtime evaluation when frontmatter metadata is misaligned with the action-oriented description, requiring automated comparison loops to refine routing and ensure consistent activation.