skills.rest
CHENyiru3
CHENyiru3COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Automate end-to-end creation, evaluation, and refinement of Claude Code skills.

Updated Apr 19, 2026
Search Tags:#automation#workflow#evaluation#iteration#claude-code#skill-creation#prompt-engineering
One-click install
npx skills add https://github.com/CHENyiru3/AI-Skills-Collections --skill skill-creator-chenyiru3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/CHENyiru3/AI-Skills-Collections/tree/main/skills-market/core/dev/skill-creator
Command: npx skills add https://github.com/CHENyiru3/AI-Skills-Collections --skill skill-creator-chenyiru3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, pyyaml, and includes scripts (resource) components.

What problem does it solve?

This Skill guides users through creating new skills, iterating on existing ones, and systematically evaluating and improving them. It helps organize drafts, run evaluation loops, benchmark performance, and optimize skill descriptions for better triggering accuracy.

Core Features & Use Cases

  • Draft new SKILL.md content and scaffold necessary resources (scripts/references/assets).
  • Run trigger-evaluation loops, compare results across iterations, and identify improvements.
  • Iterate skill body and description based on eval feedback, then re-run evaluations to converge on a robust skill.
  • Package and share skills as distributable bundles for reuse and deployment.

Quick Start

Draft your skill, run an evaluation cycle to test triggering, and iterate improvements.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate skill creation and refinement for Claude Code?▼

You can automate skill creation by drafting SKILL.md content, scaffolding resources, and running trigger-evaluation loops to systematically iterate and maximize triggering accuracy for Claude Code skills.

What is a trigger-evaluation loop in prompt engineering workflows?▼

A trigger-evaluation loop tests skill descriptions against real-world prompts, compares results across iterations, and identifies improvements to converge on a robust skill with optimal triggering accuracy and usefulness.

How do I evaluate and benchmark Claude Code skill performance?▼

You evaluate Claude Code skills by running evaluation cycles, comparing results across iterations, and analyzing feedback to optimize skill descriptions for better triggering accuracy across real-world prompts.

Can I package and share Claude Code skills as distributable bundles?▼

Yes, you can package and share skills as distributable bundles for reuse and deployment after drafting, evaluating, and iterating on the SKILL.md content and associated scripts.

Do I need Python dependencies to run Claude Code skill evaluation workflows?▼

Yes, the skill creation and evaluation workflow requires the anthropic and pyyaml Python dependencies to automate drafting, trigger evaluation, and iterative refinement processes.

What's the best way to improve triggering accuracy for Claude Code skills?▼

The best way to improve triggering accuracy is to iterate skill body and description based on evaluation feedback, then re-run evaluations to converge on a robust, optimized skill.

Related Skills

Explore More Software Engineering Skills→
lyfe2025lyfe2025
4

skill-creator

Initialize, validate, and package Skill directories into .skill files.

Community
Intermediate
onzhangonzhang
2

skill-creator

Create and evaluate Claude Skills using SKILL.md and Python scripts.

Community
Advanced
ImL1sImL1s
6

skill-creator

Automate creation, refinement, and evaluation of Claude Code skills.

Community
Advanced
lucasfthlucasfth

skill-creator

Design, validate, and iteratively improve Claude Skills with SKILL.md and eval loops.

Community
Advanced