skills.rest
OpenElementsLabs
OpenElementsLabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-creator

Automate the end-to-end lifecycle of Claude Code skills.

Updated Mar 7, 2026
Search Tags:#iteration#creation#benchmark#skill#claude-code#grading#eval
One-click install
npx skills add https://github.com/OpenElementsLabs/claude-base --skill skill-creator-openelementslabs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/OpenElementsLabs/claude-base/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/OpenElementsLabs/claude-base --skill skill-creator-openelementslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill makes it easy to design, validate, and iterate Claude Code skills. It streamlines the process of drafting a skill, running evaluation loops to test trigger behavior, and refining the skill based on feedback.

Core Features & Use Cases

  • Create new skills from scratch with a guided workflow (draft → test → iterate → finalize)
  • Iterate existing skills by running evals, collecting results, and applying improvements
  • Run automated trigger evaluations to measure how well the skill triggers in real-world prompts
  • Maintain a revision history and benchmarking reports to compare iterations

Quick Start

Draft a new skill, run a quick trigger evaluation, and iterate based on results.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create and iterate Claude Code skills?▼

You can create and iterate Claude Code skills by using a guided workflow that drafts new skills, runs automated trigger evaluations, analyzes grading outputs, and applies benchmarked improvements to finalize deployment.

What is a trigger evaluation for Claude Code skills?▼

A trigger evaluation for Claude Code skills is an automated test process that measures how accurately a skill activates in response to real-world prompts, generating results to inform subsequent iteration and refinement.

How do I benchmark Claude Code skills during development?▼

You benchmark Claude Code skills by running trigger evaluations, collecting grading outputs, and maintaining revision history reports to compare performance differences across multiple iterations.

Can I update existing Claude Code skills with new evaluation results?▼

Yes, you can update existing Claude Code skills by running trigger evaluations on them, analyzing the eval outputs, and applying targeted improvements based on the benchmarking feedback to refine their behavior.

Do I need YAML to package Claude Code skills for deployment?▼

Yes, YAML is a required dependency to structure, configure, and package Claude Code skills for deployment, ensuring the skill definitions and trigger configurations are correctly formatted for the environment.

Related Skills

Explore More Software Engineering Skills→
diet103diet103
10.0k

skill-developer

Develop and manage Claude Code skills with trigger patterns and hook configurations.

Community
Basic
victorjoshi9victorjoshi9
1

skill-creator

Draft Claude skill instructions, generate evals, and run comparisons.

Community
Advanced
mashharukimashharuki

skill-creator

Automates creation, evaluation, and iterative improvement of Claude skills.

Community
Advanced
phoenicisfphoenicisf

skill-creator

Generate, validate, and refine SKILL.md definitions for Claude skills.

Community
Advanced