skill-forge

Create, evaluate, and optimize Claude Code skills with YAML frontmatter validation.

4|Updated Apr 9, 2026

Search Tags:#evaluation #iteration #skill #skill-creation #prompt-engineering #yaml-frontmatter #skill-forge

Ready to run

npx skills add https://github.com/mamd69/hf-spring-retreat-26 --skill skill-forge-mamd69

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-forge
Source: https://github.com/mamd69/hf-spring-retreat-26/tree/main/Skills/skill-forge
Command: npx skills add https://github.com/mamd69/hf-spring-retreat-26 --skill skill-forge-mamd69

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a repeatable framework to design, test, and iteratively improve Claude Code skills, reducing guesswork and speeding up the skill-creation workflow.

Core Features & Use Cases

Structured SKILL.md templates and frontmatter validation to ensure consistent skill definitions.
End-to-end evaluation loop: draft eval prompts, run trigger tests, gather results, and refine.
Description optimization workflow to improve triggering accuracy and user outcomes.
Validation and packaging tooling to ensure skills are production-ready and portable.

Quick Start

Start by creating a new skill directory with SKILL.md, validate it with quick_validate, then begin the evaluation/iteration loop to refine your skill.

Frequently Asked Questions about skill-forge

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

FAQPage Schema

How do I create and evaluate Claude Code skills with structured frontmatter?▼

You create and evaluate Claude Code skills by using a structured SKILL.md template with YAML frontmatter validation, then running an end-to-end evaluation loop to draft eval prompts, test triggers, and iteratively refine the skill definitions.

What is the best way to optimize skill descriptions for accurate triggering?▼

The best way to optimize skill descriptions for triggering accuracy is to use a dedicated description optimization workflow, which systematically tests and refines trigger conditions to improve user outcomes and reduce guesswork.

How does the skill-creation evaluation loop work for prompt engineering?▼

The evaluation loop works by letting you draft eval prompts, run trigger tests, gather results, and progressively refine the skill, providing a repeatable framework to iteratively improve prompt engineering workflows.

Can I validate YAML frontmatter and package skills for production use?▼

Yes, you can validate YAML frontmatter and package skills for production use through built-in validation tooling and a quick_validate command, ensuring skills are portable, consistent, and production-ready.

Do I need any external dependencies to start building skills with skill-forge?▼

No external dependencies are required to start building skills; the framework operates independently with structured templates and progressive-disclosure workflows to speed up the skill-creation process.

When should I use a framework for iterative skill refinement instead of manual testing?▼

You should use a framework for iterative skill refinement when you need repeatable test harnesses and structured validation to reduce guesswork, especially if your manual prompt engineering workflows are slow or inconsistent.