skills.rest
guanyang
guanyangCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create, modify, and evaluate AI skills with testing and benchmarking.

947|163|Updated Jan 13, 2026
Search Tags:#prompt engineering#ai development#skill creation#benchmarking#evaluation#iterative improvement
One-click install
npx skills add https://github.com/guanyang/antigravity-skills --skill skill-creator-guanyang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/guanyang/antigravity-skills/tree/main/skills/skill-creator
Command: npx skills add https://github.com/guanyang/antigravity-skills --skill skill-creator-guanyang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the entire process of creating, refining, and evaluating AI-powered skills, making it easier to build powerful agentic tools.

Core Features & Use Cases

  • Skill Creation: Guides users through drafting new skills from scratch.
  • Iterative Improvement: Facilitates testing, feedback, and rewriting of existing skills.
  • Performance Benchmarking: Runs evaluations to measure skill accuracy and efficiency.
  • Use Case: You have an idea for a skill that summarizes meeting transcripts. Use this Skill to draft the initial SKILL.md, write test prompts, run evaluations against baseline models, analyze the results, and iterate on the skill's description and logic until it performs optimally.

Quick Start

Use the skill-creator to help me draft a new skill for generating commit messages.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create an AI skill from scratch?▼

To create an AI skill from scratch, this tool guides you through drafting the initial SKILL.md file, defining operational logic, and setting up triggers for modular agent capabilities.

What is the best way to benchmark and evaluate AI skill performance?▼

Benchmarking AI skill performance involves running evaluations to measure accuracy and efficiency against baseline models, providing quantitative data to iterate and optimize skill logic.

How does iterative improvement work for prompt engineering and skill development?▼

Iterative improvement for prompt engineering works by facilitating testing, analyzing feedback loops, and rewriting existing skills until the description and logic perform optimally.

Do I need any specific frameworks to define skill triggers and bundled resources?▼

No specific frameworks are required to define skill triggers and bundled resources, as the Skill operates independently without dependencies to enable modular agent capabilities.

Can I use this to test AI skills for summarizing meeting transcripts?▼

Yes, you can use this to test AI skills for summarizing meeting transcripts by writing test prompts, running evaluations against baseline models, and analyzing the results.

Related Skills

Explore More Software Engineering Skills→
VjayRamVjayRam

dspy-expert

Define DSPy signatures and modules with deterministic evaluation across splits.

Community
Advanced
johnlindquistjohnlindquist
24

skill-creator

Scaffold modular Claude Code skills with SKILL.md and supporting templates.

Community
Advanced
barnabasJbarnabasJ
3

testing

Design language-agnostic test strategies using TDD, BDD, and AAA patterns.

Community
Basic
silaratursilaratur

opensquad-skill-creator

Create and benchmark custom AI agent skills with iterative testing.

Community
Advanced