skills.rest
ConductionNL
ConductionNLOFFICIAL
Explore all skills by this author →
WebsiteGitHub

skill-creator

Draft, test, and optimize AI skills with Python-based test suites.

1|1|Updated Apr 8, 2026
Search Tags:#automation#workflow#prompt engineering#ai development#benchmarking#evaluation
One-click install
npx skills add https://github.com/ConductionNL/shillinq --skill skill-creator-conductionnl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ConductionNL/shillinq/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/ConductionNL/shillinq --skill skill-creator-conductionnl

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill streamlines the complex process of developing, evaluating, and refining AI skills, ensuring they are robust, accurate, and performant before deployment.

Core Features & Use Cases

  • Iterative Development: Provides a structured loop for drafting, testing, and improving skill instructions based on real-world performance.
  • Quantitative Benchmarking: Automates the creation of test cases and the generation of performance reports to verify skill reliability.
  • Trigger Optimization: Includes specialized tools to refine skill descriptions, ensuring the AI triggers the skill at the right time.
  • Use Case: If you are building a custom research assistant, use this skill to draft the initial instructions, run it against a set of test prompts, analyze the failures, and automatically refine the prompt until it consistently produces high-quality research summaries.

Quick Start

Use the skill-creator to draft a new skill for summarizing financial reports and generate an initial set of 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 before deployment?▼

To build and test AI skills iteratively, you draft initial instructions, run them against test prompts, analyze failures, and automatically refine the prompt until it consistently produces high-quality outputs.

What is quantitative benchmarking for AI development workflows?▼

Quantitative benchmarking for AI development automates the creation of test cases and generates performance reports to verify skill reliability against baseline performance metrics.

Do I need a Python environment to automate AI skill evaluation and test suites?▼

Yes, you need a Python-based execution environment to manage test suites, run evaluations, and package final skill artifacts during the AI development lifecycle.

How do I optimize trigger descriptions to ensure my AI skill activates accurately?▼

You optimize trigger descriptions using specialized tools to refine skill descriptions, ensuring the AI triggers the skill at the right time and improving overall activation accuracy.

What's the best way to package final skill artifacts after prompt refinement?▼

The best way to package final skill artifacts is through the Python-based execution environment, which manages the test suites and evaluation runs required before finalizing the optimized skill.

Related Skills

Explore More Software Engineering Skills→
dlt-hubdlt-hub
53

run-eval

Evaluate AI skill trigger accuracy against test queries using Python scripts.

Official
Advanced
robertzengcnrobertzengcn

canary

Monitor live web applications for console errors, performance regressions, and page failures after deployment.

Community
Advanced
dacydacy

skill-creator-skill

Guide Claude skill creation from intent capture through evaluation and refinement.

Community
Advanced
yasuwrldhyperyasuwrldhyper

skill-creator

Create and refine AI skills with SKILL.md metadata and benchmark testing.

Community
Advanced