ck:skill-creator

Create and update Claude skills with automated benchmarking and testing.

1|Updated Jun 16, 2026
One-click install
npx skills add https://github.com/TNHoang2708/Gym_Ver2 --skill ck-skill-creator-tnhoang2708
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:skill-creator
Source: https://github.com/TNHoang2708/Gym_Ver2/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/TNHoang2708/Gym_Ver2 --skill ck-skill-creator-tnhoang2708

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires json, argparse, pathlib, requests, subprocess, sys, math, datetime, jsonschema, urllib3, and includes scripts (resource) and references (resource) and agents (resource) and assets (resource) components.

What problem does it solve?

This Skill empowers the management, creation, and optimization of Claude skills. It addresses the challenge of maintaining and refining skill quality over time, simplifying the process of skill deployment and iteration.

Core Features & Use Cases

  • Skill Creation and Updates: Automates the process of creating and updating Claude skills.
  • Evaluation and Benchmarking: Provides infrastructure for testing skill effectiveness through automated benchmarks.
  • Iterative Improvement: Enables incremental optimization based on feedback and testing.
  • Use Case: Ideal for skill authors who wish to iterate on skill designs, improve trigger accuracy, and ensure optimal performance through comprehensive benchmarking and iterative development.

Quick Start

Create a new Claude skill with the 'ck:skill-creator' by navigating to '.claude/skills/' and using the 'init_skill.py' script to begin.

Frequently Asked Questions about ck:skill-creator

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

FAQPage Schema
How do I create and initialize a new Claude skill?

To create a Claude skill, navigate to the '.claude/skills/' directory and run the 'init_skill.py' script. This initialization process sets up the foundational structure for skill development and deployment.

What is the best way to benchmark and evaluate Claude skill performance?

Benchmarking Claude skills involves using automated testing infrastructure to measure skill effectiveness. This process provides benchmark scoring to evaluate trigger accuracy and ensure optimal performance during iterative development.

Do I need Python to manage and iterate on Claude skills?

Yes, managing Claude skills requires Python 3.7 or higher. The skill management process depends on various Python libraries including 'json', 'argparse', 'pathlib', 'requests', and 'jsonschema' for execution and validation.

How does iterative improvement work for refining existing Claude skills?

Iterative improvement enables incremental optimization of Claude skills based on testing feedback. It supports automated description optimization and trigger accuracy enhancements to ensure continuous quality refinement over time.

Can I automate the packaging and deployment of Claude skills?

Yes, skill management includes automated packaging capabilities. This streamlines the skill deployment process by handling the creation and update workflows, reducing manual overhead for skill authors.

Why does my Claude skill benchmark scoring fail during automated testing?

Benchmark scoring failures during automated testing typically indicate issues with trigger accuracy or skill effectiveness. Running iterative improvement processes helps identify and resolve these performance gaps through incremental optimization.