skills.rest
abogoyavlensky
abogoyavlenskyCOMMUNITY
Explore all skills by this author →
Website𝕏@abogoyavlenskyGitHub

skill-creator

Design, test, and iterate Claude skills with automated evaluations.

Updated Mar 18, 2026
Search Tags:#automation#workflow#tooling#evaluation#iteration#skill-creation#prompt-engineering
One-click install
npx skills add https://github.com/abogoyavlensky/agents --skill skill-creator-abogoyavlensky
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/abogoyavlensky/agents/tree/main/skills/skill-creator
Command: npx skills add https://github.com/abogoyavlensky/agents --skill skill-creator-abogoyavlensky

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 guides you through designing, evaluating, and iterating Claude skills—from concept to production—so you can reliably create new skills, refine existing ones, run automated evaluations, and optimize triggering descriptions for better activation.

Core Features & Use Cases

  • End-to-end skill creation: capture intent, draft, and structure a cohesive skill.
  • Automated evaluation loops: run calibrations, benchmarks, and comparatives to validate performance.
  • Iterative improvement: apply quantitative and qualitative feedback to both skill body and triggering metadata.
  • Bundled resources: scripts, references, and assets to support deterministic tasks, documentation, and output templates.
  • Use cases include building new capabilities, refining triggering phrasing, and benchmarking skill performance across prompts.

Quick Start

Draft a skill concept and begin the evaluation loop to refine its triggering and performance.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I automate evaluations and iterate on Claude skills?▼

To design and test Claude skills, you capture the initial intent, draft the structure, and run automated evaluation loops to validate performance before production deployment.

What's the best way to optimize prompt engineering for skill triggering?▼

Optimizing prompt engineering for skill triggering involves iterating on the triggering frontmatter metadata and applying quantitative feedback to improve activation reliability.

Do I need pyyaml to run automated skill evaluation loops?▼

Yes, you need pyyaml installed in your environment to support the scripts that execute deterministic tasks and parse configuration files during the skill evaluation workflow.

Can I use bundled scripts and assets for workflow automation in skill creation?▼

You can use the bundled scripts, references, and assets to support deterministic tasks, generate documentation, and apply output templates during end-to-end skill creation and workflow automation.

Why does my Claude skill fail to trigger correctly during prompt testing?▼

A Claude skill fails to trigger correctly when the triggering frontmatter lacks precise phrasing, requiring you to run comparative benchmarks and refine the metadata for better activation.

Related Skills

Explore More Software Engineering Skills→
samjhechtsamjhecht
4

initialize-governance

Generate Constitution, Roadmap, and process documentation templates for project governance.

Community
Advanced
majesticlabs-devmajesticlabs-dev
47

AI-writing-tells

Edit copy for grammar, style, and clarity with structured feedback reports.

Official
Intermediate
micaelmaltamicaelmalta
1

skill-creator

Create and refine Claude skills with SKILL.md templates and bundled resources.

Community
Basic
codeboltaicodeboltai

skill-creator

Create and refine Claude skills with structured SKILL.md templates and packaging workflows.

Official
Intermediate