skills.rest
ScotterMonk
ScotterMonkCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Create, test, and evaluate AI skills with SKILL.md files.

37|1|Updated Oct 20, 2025
Search Tags:#skill development#testing#AI tools#workflow automation#prompt engineering#evaluation
One-click install
npx skills add https://github.com/ScotterMonk/AgentAutoFlow --skill skill-creator-scottermonk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ScotterMonk/AgentAutoFlow/tree/main/.roo/skills/skill-creator
Command: npx skills add https://github.com/ScotterMonk/AgentAutoFlow --skill skill-creator-scottermonk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill 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 easier to build powerful, custom AI functionalities.

Core Features & Use Cases

  • Skill Creation: Guides users through defining intent, interviewing for edge cases, and writing SKILL.md.
  • Iterative Improvement: Facilitates testing, feedback collection, and skill refinement through a structured loop.
  • Performance Benchmarking: Runs evaluations against baseline models to measure skill effectiveness.
  • Description Optimization: Automatically tunes the SKILL.md description for optimal triggering accuracy.
  • Use Case: You have an idea for a new AI skill to summarize meeting notes. Use this Skill to draft the SKILL.md, write test cases, run evaluations, and optimize the description so Claude uses it effectively.

Quick Start

Use the skill-creator to start building a new skill for summarizing meeting notes.

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?▼

Build and test AI skills by defining intent, writing the SKILL.md file, and executing deterministic tests via bundled scripts. This approach facilitates the end-to-end lifecycle of AI skill development, including iterative refinement and performance evaluation.

What is the process for refining prompt engineering and evaluating AI skills?▼

Refining prompt engineering and evaluating AI skills involves running evaluations against baseline models to measure effectiveness, collecting feedback, and tuning the SKILL.md description for optimal triggering accuracy through a structured iterative improvement loop.

How do I write a SKILL.md file that ensures Claude uses my custom AI functionality effectively?▼

Write a SKILL.md file by defining the skill intent and capturing requirements for edge cases. You can optimize the description automatically using provided evaluation tools to ensure Claude triggers the custom AI functionality accurately and effectively.

Do I need any dependencies to run deterministic tests for skill development?▼

No dependencies are required to run deterministic tests for skill development. The skill operates independently using bundled scripts and provided evaluation tools to execute tests and analyze performance results without external packages.

What's the best way to benchmark AI skill performance against baseline models?▼

The best way to benchmark AI skill performance is by running dedicated evaluations against baseline models. This measures skill effectiveness directly, allowing you to analyze results using provided evaluation tools and refine the workflow automation logic.

When should I not use automated skill description optimization?▼

Avoid automated skill description optimization when your SKILL.md intent is not fully defined or edge cases remain uncaptured. Optimization is designed for fine-tuning triggering accuracy after the core skill creation and iterative testing phases are complete.

Related Skills

Explore More Software Engineering Skills→
PatricioOsorioPatricioOsorio

skill-creator

Document skill objectives, triggers, and success criteria for Claude skills.

Community
Advanced
vnmoorthyvnmoorthy
2

canary

Monitor live apps for console errors and performance regressions post-deploy.

Community
Advanced
guchengzhongguchengzhong
3

skill-creator

Create, modify and optimize reusable terminal skills with benchmarking support.

Community
Advanced
OKHP3OKHP3
2

skill-creator

Create, test, and iteratively improve AI skills with structured evaluations.

Community
Advanced