skills.rest
artusjs
artusjsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-creator

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

11|3|Updated Jan 3, 2024
Search Tags:#automation#workflow#markdown#evaluation#creation#skill
One-click install
npx skills add https://github.com/artusjs/artusx --skill skill-creator-artusjs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/artusjs/artusx/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/artusjs/artusx --skill skill-creator-artusjs

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a complete workflow for creating, validating, evaluating, and iterating Claude skills. It guides users from drafting SKILL.md to running automated trigger evaluations, reviewing results, and applying improvements to both the skill content and its triggering behavior.

Core Features & Use Cases

  • End-to-end skill lifecycle: draft SKILL.md, validate frontmatter, run trigger-eval loops, view results, and iterate.
  • Evaluation-driven improvement: automatically adjust descriptions based on eval results and historical iterations.
  • Benchmarking and review tooling: leverage eval-viewer, aggregator, and analyzers to compare configurations and surface actionable insights.
  • Packaging and deployment: validate, bundle, and distribute skills as portable .skill packages for reuse.

Quick Start

Draft your SKILL.md, then run the evaluation loop to iterate on the skill's triggering and 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 Claude skill creation and evaluation in Claude Code?▼

You can automate Claude skill creation by drafting SKILL.md, validating frontmatter, and running trigger-eval loops to iteratively evaluate and optimize descriptions based on results.

What is the best way to evaluate and iterate on Claude skill triggering behavior?▼

The best way to evaluate skill triggering is running automated trigger-eval loops, reviewing results with eval-viewer and analyzers, then applying description adjustments based on historical iteration data.

How do I package Claude skills as portable .skill bundles for deployment?▼

You package Claude skills by validating SKILL.md frontmatter and bundling optional scripts, references, and assets into a portable .skill package for distribution and reuse.

Can I use markdown and YAML frontmatter to define Claude skill metadata?▼

Yes, you define Claude skill metadata using markdown and YAML frontmatter in the SKILL.md file, which the workflow validates to ensure safe packaging and deployment within Claude Code.

Do I need pyyaml installed to validate SKILL.md frontmatter?▼

Yes, pyyaml is required as a dependency to parse and validate YAML frontmatter in SKILL.md files during the skill creation and packaging workflow.

What tools help benchmark and compare Claude skill evaluation configurations?▼

You benchmark and compare skill configurations using the eval-viewer, aggregator, and analyzers to surface actionable insights from trigger-eval results across iterations.

Related Skills

Explore More Software Engineering Skills→
MiniMax-AIMiniMax-AI
2.9k

skill-creator

Generate Skill Units with YAML frontmatter, Markdown body, and bundled resources.

Official
Intermediate
krzemienskikrzemienski
2

skill-creator

Orchestrate Claude Code skill development from SKILL.md drafting to trigger evaluation.

Community
Advanced
baekenoughbaekenough
13

omcustom-improve-report

Generate read-only improvement reports from eval-core analysis data.

Community
Intermediate
tuliosouza99tuliosouza99

skill-creator

Create and iteratively improve SKILL.md-based agent skills with Python eval scripts.

Community
Advanced