skill-creator

Draft, validate, and iterate SKILL.md frontmatter and body definitions.

4|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/smartmarbles/helm --skill skill-creator-smartmarbles
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/smartmarbles/helm/tree/main/.github/skills/skill-creator
Command: npx skills add https://github.com/smartmarbles/helm --skill skill-creator-smartmarbles

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill creation and maintenance process is often chaotic and error-prone. Skill creators need a structured loop to draft, test, evaluate, and iterate on SKILL.md definitions and their bodies.

Core Features & Use Cases

  • Guided workflow to author SKILL.md frontmatter (name, description) and the supporting Markdown body.
  • Integrated evaluation loop: spawn tests, collect results, and generate feedback for improvement.
  • Built-in tooling to manage test prompts, run loop iterations, compare configurations, and prepare benchmarks.
  • Easy packaging and deployment support (validation, packaging into .skill, and distribution).
  • Use cases include creating new skills from scratch, optimizing existing ones, and benchmarking triggering accuracy.

Quick Start

Create a new skill draft, run the evaluation loop, review results, and iterate until you reach stable performance.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate drafting and validating SKILL.md frontmatter?

Automate SKILL.md authoring using a guided workflow to draft, validate, and iterate on frontmatter and Markdown bodies. This structured loop supports generating definitions, spawning tests, and collecting evaluation results for reliable deployment.

What is the best way to benchmark skill trigger accuracy?

Benchmark trigger accuracy by running an integrated evaluation loop that spawns tests and collects results. You manage test prompts, run iterations, compare configurations, and generate feedback for reproducible skill improvements.

How do I package and deploy a validated skill definition?

Package and deploy validated skill definitions using built-in tooling that checks frontmatter and prepares the skill for distribution. This ensures reliable deployment by validating configurations before packaging into a final format.

Can I manage reusable resources like scripts and assets for skill deployment?

Yes, you can manage reusable resources such as scripts, references, and assets to support reliable skill deployment. The system coordinates these resources alongside evaluation to surface structured metadata for discovery and improvements.

Does PyYAML work with skill iteration and evaluation workflows?

PyYAML is required to support skill iteration and evaluation workflows. It enables automated parsing, validation, and generation of YAML frontmatter within SKILL.md files during the drafting and testing phases.