skill-creator

Name: skill-creator
Availability: InStock
Author: StevenWXY

Create, test, and iterate Claude skills with evaluation workflows.

Updated Mar 1, 2026

Search Tags:#automation #workflow #testing #documentation #evaluation #benchmark #skill-creation

Ready to run

npx skills add https://github.com/StevenWXY/Project-Sibylla --skill skill-creator-stevenwxy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/StevenWXY/Project-Sibylla/tree/main/.kilocode/skills/common/skill-creator
Command: npx skills add https://github.com/StevenWXY/Project-Sibylla --skill skill-creator-stevenwxy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yaml.

What problem does it solve?

Streamlines building, testing, and iterating Claude skills from idea to production, reducing guesswork and rework.

Core Features & Use Cases

End-to-end skill creation workflow: capture intent, draft SKILL.md, run evals, and iterate based on results.
Evaluation scaffolding: build prompts, run tests, benchmark performance, and collect feedback.
Description optimization: refine triggering descriptions for better discovery and reliability.
Bundled resources: scripts, references, and assets to accelerate recurring skill-building tasks.

Quick Start

Create a new skill by drafting SKILL.md, defining evals, executing the loop, and iterating until triggering is reliable.

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 test Claude skills from scratch?▼

You can create and test Claude skills by drafting a SKILL.md file, defining evaluation prompts, running benchmark tests, and iterating based on feedback until triggering becomes reliable.

What is the best way to automate skill evaluation and benchmarking?▼

The best way to automate skill evaluation and benchmarking is using bundled scripts to execute test prompts, collect performance metrics, and establish a feedback loop to optimize triggering accuracy.

Does skill-creation work with YAML for configuring automation workflows?▼

Yes, skill creation relies on YAML as its core dependency to configure automation workflows, structure evaluation scaffolding, and define metadata templates across various domains.

How do I optimize Claude skill descriptions for better triggering accuracy?▼

Optimize Claude skill descriptions for triggering accuracy by iterating on the SKILL.md file using evaluation results and benchmark feedback to refine discovery and reliability.

Can I scale skill creation across multiple domains using templates?▼

Yes, you can scale skill creation across multiple domains by leveraging bundled templates, reference scripts, and standardized workflows to accelerate recurring skill-building tasks.