skill-creator

Manage SKILL.md content, metadata, and evaluation workflows for Claude skills.

6|Updated Jan 29, 2023

Search Tags:#automation #evaluation #packaging #description #skill #skill-creator

Ready to run

npx skills add https://github.com/rethinkhealth/glion --skill skill-creator-rethinkhealth

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/rethinkhealth/glion/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/rethinkhealth/glion --skill skill-creator-rethinkhealth

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps teams systematically create, test, and improve Claude skills by automating the end-to-end lifecycle—from drafting SKILL.md frontmatter to running evaluations and packaging.

Core Features & Use Cases

Draft and validate SKILL.md frontmatter (name, description, compatibility)
Run trigger-evaluation loops (train/test splits) and track results
Iterate on skill descriptions using evals and history
Package skills into distributable .skill files
Generate benchmarks and lightweight reports to compare iterations

Quick Start

Draft SKILL.md, run evals, review results, and iterate to improve triggering and descriptions.

Frequently Asked Questions about skill-creator

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

FAQPage Schema

How do I create and validate SKILL.md frontmatter for Claude skills?▼

To create and validate SKILL.md frontmatter, draft metadata fields like name, description, and compatibility, then run automated validation to enforce correct formatting. This ensures your Claude skill is properly structured before testing and packaging.

What is a trigger-evaluation loop and how does it improve skill descriptions?▼

A trigger-evaluation loop tests skill descriptions using train and test splits to measure performance. By running evaluations and tracking history, you iteratively refine descriptions to improve how accurately Claude triggers the correct skill.

How do I package Claude skills into distributable files?▼

You package Claude skills into distributable .skill files after drafting and validating the SKILL.md content. This bundles validated metadata, evaluation history, and optional resources like scripts, references, and assets into a single distributable file.

Do I need YAML to automate the Claude skill lifecycle?▼

Yes, YAML is a required dependency for automating the Claude skill lifecycle. It manages SKILL.md content and metadata throughout the drafting, evaluation, iteration, and packaging workflows.

Can I generate benchmark reports to compare different skill iterations?▼

Yes, you can generate lightweight benchmark reports to compare different skill iterations. The evaluation workflow tracks history and results, allowing you to compare performance across iterations and select the best performing skill description.

What are the limitations of automating skill creation with evaluation workflows?▼

The main limitation is that automated evaluation workflows rely on train and test splits, meaning trigger accuracy depends heavily on test data quality. Additionally, packaging requires strict frontmatter validation, which can block distribution if formatting errors exist.