skills.rest
creamgod45
creamgod45COMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Automate drafting, evaluating, and iterating Claude Code skills with SKILL.md.

Updated Nov 22, 2024
Search Tags:#automation#workflow#evaluation#packaging#iteration#skill
One-click install
npx skills add https://github.com/creamgod45/CGCloud --skill skill-creator-creamgod45
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/creamgod45/CGCloud/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/creamgod45/CGCloud --skill skill-creator-creamgod45

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill Creator addresses the complexity of turning ideas into reproducible Claude skills by providing a structured workflow to draft, evaluate, iterate, and package SKILL.md entry points along with supporting tooling and benchmarks.

Core Features & Use Cases

  • End-to-end skill lifecycle: draft SKILL.md, wire up evaluation prompts, run trigger evaluations, and iterate based on results.
  • Integrated tooling: leverages included scripts (run_eval, run_loop, improve_description, aggregate_benchmark, generate_report) to automate testing, improvement, and benchmarking.
  • Benchmarking and review: scaffolds viewing, scoring, and analyst feedback to guide data-driven improvements.
  • Packaging and distribution: validate, package, and share skills as portable .skill bundles for deployment.

Quick Start

Define SKILL.md at the root, place optional resources under scripts/ and references/, then run the evaluation loop to draft, test, and refine the skill description.

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 evaluation and iteration for Claude Code?▼

Automate skill evaluation by running trigger evaluations and iterating SKILL.md descriptions through an integrated feedback loop, using included scripts to test, score, and benchmark Claude Code skills automatically.

What's the best way to package and distribute Claude Code skills?▼

Package and distribute Claude Code skills by validating the SKILL.md entry point and bundling it with supporting scripts and references into a portable .skill bundle for deployment.

Can I use YAML configurations to draft SKILL.md files for Claude Code?▼

You can draft SKILL.md files using structured YAML configurations, leveraging pyyaml dependencies to define skill entry points, trigger conditions, and evaluation prompts for Claude Code.

How does benchmarking work when refining Claude Code skills?▼

Benchmarking aggregates evaluation results by running scripts that view, score, and collect analyst feedback, guiding data-driven improvements to iterate skill descriptions and trigger performance.

Do I need to manually run trigger evaluations to improve skill descriptions?▼

Manual trigger evaluation is unnecessary because the automation loop runs evaluations, aggregates benchmark results, and iterates skill descriptions automatically using included scripts like run_loop and improve_description.

Related Skills

Explore More Product & Management Skills→
jungaijungai
2

skill-creator

Create and update Codex skills with standard SKILL.md frontmatter.

Community
Intermediate
hashi-demo-labhashi-demo-lab
1

skill-creator

Standardize SKILL.md frontmatter and structure for Claude skills.

Official
Basic
gesmith0606gesmith0606

skill-creator

Create, evaluate, and iteratively improve SKILL.md descriptions with Python scripts.

Community
Advanced
quanganh208quanganh208

ck:skill-creator

Create or update Claude skills with eval-driven iteration and bundled resources.

Community
Advanced