skill-creator-v2

Automate creation, validation, and packaging of Claude-like skills into .skill artifacts.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/ashcastelinocs124/CasStack --skill skill-creator-v2
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator-v2
Source: https://github.com/ashcastelinocs124/CasStack/tree/main/skills/skill-creator-v2
Command: npx skills add https://github.com/ashcastelinocs124/CasStack --skill skill-creator-v2

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml.

What problem does it solve?

This Skill automates the end-to-end creation, validation, and packaging of Claude-like skills via a benchmark-driven pipeline, enabling rapid, repeatable skill development with quality gates.

Core Features & Use Cases

  • Phase-driven pipelines support both simple scaffolding and advanced benchmarking, including focused interviews, web research, test-case generation, and optional A/B subagent evaluation.
  • Automation & validation automatically collects requirements, generates SKILL.md and resource skeletons, runs quick validation, and packages the result for deployment.
  • Use Case: When building a new skill, teams can go from interview to a packaged .skill artifact in minutes, with clear benchmarks and reproducible results.

Quick Start

Provide a concise intent and expected outputs, then run the prehook to choose a pipeline and begin generating SKILL.md, assets, and references.

Frequently Asked Questions about skill-creator-v2

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

FAQPage Schema
How do I automate the creation and validation of AI copilot skills?

You can automate AI copilot skill creation by using a benchmark-driven pipeline that collects requirements, generates SKILL.md files, runs validation checks, and outputs a ready-to-package .skill artifact.

What is benchmark-driven skill creation and how does it work?

Benchmark-driven skill creation is an automated process that uses A/B subagent evaluation and test cases to evaluate and package Claude-like skills, ensuring reproducible results and quality gates before deployment.

Can I use pyyaml to scaffold advanced AI workflow pipelines with testing?

Yes, pyyaml is required as a dependency to support the automated pipeline that scaffolds advanced AI workflows, handling configuration parsing needed to generate scripts and reference assets.

How do I package a Claude-like skill into a deployable .skill artifact?

To package a deployable .skill artifact, the automation pipeline collects your intent via prehook questions, generates the necessary SKILL.md and resource skeletons, and runs quick validation before packaging.

What is the best way to generate test cases for new AI agent skills?

The best way to generate test cases for new AI agent skills is through an automated benchmarking pipeline that conducts focused interviews and web research to create targeted, reproducible test scenarios.

Does automated skill scaffolding support both simple tasks and advanced subagent evaluation?

Yes, the automated skill scaffolding supports phase-driven pipelines for both simple task generation and advanced workflows, including optional A/B subagent benchmarking and HTML comparison.