skills.rest
guiledo
guiledoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create, evaluate, and refine AI skills with YAML frontmatter and benchmarks.

Updated Nov 26, 2025
Search Tags:#automation#ai#evaluation#iteration#creation#benchmark#skill
One-click install
npx skills add https://github.com/guiledo/dotfiles --skill skill-creator-guiledo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/guiledo/dotfiles/tree/main/opencode/.config/opencode/skills/skill-creator
Command: npx skills add https://github.com/guiledo/dotfiles --skill skill-creator-guiledo

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 streamlines the process of creating new AI skills, editing existing ones, and measuring their performance through structured evals and benchmarks, enabling teams to iterate quickly and improve triggering accuracy.

Core Features & Use Cases

  • Capture Intent: Understand user goals and translate them into a precise Skill spec (frontmatter + body).
  • Draft SKILL.md: Produce a complete frontmatter and instructional body, including optional sections for scripts, references, and assets.
  • Run Evals and Benchmark: Integrate with run_eval, run_loop, and aggregate_benchmark to test skills and compare iterations.
  • Iterate and Improve: Use eval results to refine the skill description and instructions.
  • Packaging and Sharing: Validate and package the skill into a .skill file for deployment.

Quick Start

Draft the SKILL.md, wire up evals, and run the evaluation loop to start creating and improving a skill.

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 on AI skills systematically?▼

To create and iterate on AI skills systematically, you draft a SKILL.md file with YAML frontmatter, run structured evaluations and benchmarks, and refine the triggering descriptions based on the results.

How do I benchmark and evaluate AI skills to improve triggering accuracy?▼

You benchmark and evaluate AI skills by integrating with run_eval, run_loop, and aggregate_benchmark tools to test skills, compare iterations, and optimize triggering accuracy across domains.

What's the best way to structure a new AI skill for deployment?▼

The best way to structure a new AI skill is to use a SKILL.md file containing a YAML frontmatter with name and description, an instructional body, and optional sections for scripts, references, and assets.

Do I need pyyaml to design and test AI skills?▼

Yes, you need pyyaml because the skill creation workflow requires a YAML frontmatter to define the skill name and description before running evaluations and packaging.

How do I package a validated AI skill into a deployable file?▼

You package a validated AI skill into a deployable file by using the skill creation workflow to verify the structure and bundle it into a .skill file for deployment.

Related Skills

Explore More Software Engineering Skills→
mecolejrmecolejr

file-converter

Convert files across CSV, JSON, YAML, XML, Markdown, and images.

Community
Advanced
gelowzzzgelowzzz

skill-creator

Create, validate, and package Claude Skills into .skill files.

Community
Advanced
michaelvolzmichaelvolz

skill-creator

Automate SKILL.md updates and eval metadata from workflow intent.

Community
Advanced
darknetopencv-altdarknetopencv-alt
34

skill-creator

Guide creation, testing, and optimization of AI skills with SKILL.md.

Community
Advanced