skills.rest
BearyDevs
BearyDevsCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create and optimize Claude Skills with SKILL.md lifecycle workflows.

Updated Aug 27, 2026
Search Tags:#automation#workflow#optimization#claude#benchmark#skill-creation#evals
One-click install
npx skills add https://github.com/BearyDevs/dotfiles --skill skill-creator-bearydevs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/BearyDevs/dotfiles/tree/main/.config/opencode/skills/skill-creator
Command: npx skills add https://github.com/BearyDevs/dotfiles --skill skill-creator-bearydevs

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This description explains how to create, validate, and iterate Claude Skills from drafting SKILL.md to running evals, benchmarking, and optimizing the trigger description.

Core Features & Use Cases

  • End-to-end Skill creation workflow: draft, validate, test, iterate, and optimize.
  • Integrated tooling: built-in scripts for evaluation, benchmarking, and description improvement; references for deeper research; assets for templates and artifacts.
  • Use cases include creating a new skill from scratch, refining an existing skill, and continuously optimizing triggering accuracy and performance through data-driven iterations.

Quick Start

Draft a new skill’s SKILL.md, then run the evaluation loop to start refining its description and testing prompts.

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 optimize Claude skills end-to-end?▼

To create and optimize Claude skills, draft a SKILL.md file with frontmatter, then use evaluation loops and benchmarking scripts to refine the trigger description and test prompts iteratively for reliable behavior.

What is the standard lifecycle for Claude skill development and evaluation?▼

The standard lifecycle for Claude skill development involves drafting the SKILL.md, validating frontmatter, running evals, benchmarking performance, and triggering optimization to ensure reliable and accurate skill behavior.

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

Yes, pyyaml is required to parse and validate the SKILL.md frontmatter, ensuring the required name and description fields are correctly formatted for Claude skill activation.

Can I bundle scripts and references with my Claude skill?▼

Yes, you can bundle optional resources like scripts, references, and assets with your Claude skill, which are loaded during activation to support evaluation, benchmarking, and deeper research.

What's the best way to improve an existing skill's trigger accuracy?▼

The best way to improve an existing skill's trigger accuracy is to run data-driven evaluation loops and benchmarking scripts, iterating on the description and testing prompts to optimize performance.

Why are my Claude skill evaluations not producing reliable behavior?▼

Evaluations may not produce reliable behavior if the SKILL.md frontmatter lacks a proper name and description, or if the optimization loop is not using benchmarking data to iterate on trigger descriptions.

Related Skills

Explore More Product & Management Skills→
wjyugutouwjyugutou

vueuse-functions

Extract structured metadata from SKILL.md files and optional resource directories.

Community
Basic
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
micaelmaltamicaelmalta
1

skill-creator

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

Community
Basic
AgLyx3AgLyx3

senior-prompt-engineer

Design prompt patterns and evaluation frameworks for LLM-driven workflows.

Community
Advanced