skills.rest
manuelbrandner85
manuelbrandner85COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Create, evaluate, and refine AI skills with automated testing and benchmarking.

Updated Nov 23, 2025
Search Tags:#automation#skill development#prompt engineering#optimization#benchmarking#evaluation
One-click install
npx skills add https://github.com/manuelbrandner85/Weltenbibliothekapp --skill skill-creator-manuelbrandner85
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/manuelbrandner85/Weltenbibliothekapp/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/manuelbrandner85/Weltenbibliothekapp --skill skill-creator-manuelbrandner85

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill solves the challenge of creating high-quality, reliable AI skills by providing a structured, iterative framework for development, testing, and performance optimization.

Core Features & Use Cases

  • Iterative Development: Guides you through the full lifecycle of skill creation, from intent capture to final deployment.
  • Quantitative Benchmarking: Automates the creation of test cases, baseline comparisons, and performance metrics to ensure your skill actually works.
  • Trigger Optimization: Includes a specialized loop to refine your skill's description, ensuring it triggers accurately when needed and avoids false positives.

Quick Start

Use the skill-creator to help me draft a new skill for summarizing technical documentation and set up the initial test cases.

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 iteratively?▼

Iterative AI skill development requires a structured workspace to draft instructions, run automated benchmarking against baselines, and refine trigger descriptions to ensure accurate model invocation.

What is quantitative benchmarking for prompt engineering?▼

Quantitative benchmarking for prompt engineering automates test case generation and performance metrics tracking, providing baseline comparisons to validate that AI skills function reliably.

How do I optimize trigger descriptions to avoid false positives in AI automation?▼

You can optimize trigger descriptions using a specialized evaluation loop that refines the skill's metadata, ensuring accurate model invocation when needed while avoiding false positives.

Do I need a structured workspace to manage AI skill evaluation?▼

Yes, managing AI skill evaluation requires a structured workspace to organize iterations, track performance metrics, and store baseline comparisons throughout the creation and refinement lifecycle.

What is the best way to generate quantitative assertions for skill development?▼

Generating quantitative assertions is best achieved through automated testing workflows that create test cases and benchmark performance metrics against initial baselines during skill development.

How does automated testing work when refining AI skills?▼

Automated testing refines AI skills by generating test cases, comparing current performance against stored baselines, and providing metrics to iteratively optimize instructions and trigger descriptions.

Related Skills

Explore More Software Engineering Skills→
AzrinPutraAzrinPutra

intent-capture

Guide exploratory conversations to elicit project requirements and generate an intent brief.

Community
Intermediate
FrogAiFrogAi
1

agent-test-harness

Measure skill and subagent trigger accuracy across multiple prompt trials.

Community
Advanced
felipesantiago-coderfelipesantiago-coder

skill-creator

Create AI skills with structured evaluation and benchmarking workflows for GLM Code.

Community
Advanced
EntityProcessEntityProcess
15

agentv-prompt-optimizer

Iteratively refine AI prompt files against AgentV evaluation datasets.

Official
Advanced