skills.rest
hi-yuki-922
hi-yuki-922COMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create, refine, and benchmark AI skills through interactive prompts and automated tests.

1|Updated Jan 15, 2026
Search Tags:#skill development#AI tools#workflow automation#prompt engineering#benchmarking#evaluation
One-click install
npx skills add https://github.com/hi-yuki-922/accounting-assistant --skill skill-creator-hi-yuki-922
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/hi-yuki-922/accounting-assistant/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/hi-yuki-922/accounting-assistant --skill skill-creator-hi-yuki-922

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the entire process of creating, improving, and evaluating AI skills, making it accessible even for those new to the concepts.

Core Features & Use Cases

  • Skill Creation: Guides users through defining a new skill's purpose, triggers, and output.
  • Iterative Improvement: Facilitates testing, evaluation, and refinement of existing skills based on performance metrics.
  • Performance Benchmarking: Runs automated tests to compare skill versions and identify areas for optimization.
  • Use Case: You have an idea for a new skill to help draft commit messages. Use this Skill to define its purpose, write a draft, test it with example prompts, analyze the results, and iterate until it performs reliably.

Quick Start

Use the skill-creator to help me draft a new skill that can summarize meeting transcripts.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I build and test AI skills for workflow automation?▼

Iterative skill refinement uses automated testing frameworks to compare versions and identify optimization areas. It runs quantitative and qualitative analysis against your defined criteria to ensure the AI skill performs reliably.

How does performance benchmarking work for AI prompt engineering?▼

Skill benchmarking evaluates performance by running automated tests on example prompts, analyzing results against defined criteria, and identifying areas for optimization. This quantitative and qualitative analysis ensures reliable AI tool outputs.

Do I need Python to develop and evaluate AI skills?▼

Yes, Python is required. The Skill relies on Python dependencies to execute scripts, run automated evaluation workflows, and support the testing frameworks needed for quantitative and qualitative skill analysis.

Can I define custom triggers and operational logic for new AI tools?▼

Yes, interactive prompts guide you through defining a new skill's purpose, triggers, and output. This facilitates the end-to-end lifecycle from initial conception to drafting custom operational logic.

What is the best way to compare AI skill versions during development?▼

The best way is using automated evaluation workflows that run tests against defined criteria. This provides quantitative and qualitative analysis to compare versions, identify optimization areas, and refine your AI skills.

Related Skills

Explore More Software Engineering Skills→
KnoWhizKnoWhiz
6

skill-creator

Create and refine AI skills with SKILL.md and performance evaluations.

Official
Advanced
thanh-abaiithanh-abaii
34

gs:benchmark-models

Compare AI model performance across gstack skills using identical prompts.

Community
Advanced
wx-chevalierwx-chevalier
10

skill-creator

Create, test, and optimize AI skills with SKILL.md and evaluation workflows.

Community
Advanced
codeboltaicodeboltai

skill-creator

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

Official
Intermediate