skill-creator

Create, refine, and evaluate AI skills with SKILL.md and baseline comparisons.

1|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/baotoq/agent-skills --skill skill-creator-baotoq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/baotoq/agent-skills/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/baotoq/agent-skills --skill skill-creator-baotoq

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill empowers you to create new AI capabilities from scratch, enhance existing ones, and rigorously test their performance, ensuring they meet your exact needs.

Core Features & Use Cases

  • Skill Creation: Guide users through defining intent, writing SKILL.md, and structuring resources.
  • Iterative Improvement: Run evaluations, analyze results, and refine skills based on feedback.
  • Performance Benchmarking: Compare skill versions and measure improvements quantitatively.
  • Description Optimization: Fine-tune skill descriptions for accurate triggering by the AI.
  • Use Case: You have an idea for a new AI skill to summarize meeting notes. Use this Skill to draft the SKILL.md, create test prompts, run evaluations against a baseline, and iterate on the skill's logic and description until it performs perfectly.

Quick Start

Use the skill creator to help me build a new skill that can draft commit messages from git diffs.

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 from scratch?

To build and test AI skills, define the intent in a SKILL.md file, structure resources, create test prompts, and run automated evaluations against a baseline to measure performance and refine logic iteratively.

What is iterative refinement for prompt engineering?

Iterative refinement for prompt engineering is the process of running evaluations, analyzing qualitative feedback, and adjusting skill definitions and descriptions to improve AI triggering accuracy and overall performance.

Can I benchmark AI skill versions to measure improvements quantitatively?

Yes, you can benchmark AI skill versions to measure improvements quantitatively by integrating evaluation tools that compare performance differences between current iterations and historical baselines.

How do I optimize skill descriptions for accurate AI triggering?

You optimize skill descriptions for accurate AI triggering by fine-tuning the text, running tests to see how the AI responds, and applying iterative refinement based on those evaluation results.

Do I need dependencies to facilitate the AI skill development lifecycle?

No dependencies are required to facilitate the AI skill development lifecycle, as the skill operates independently using internal scripts, references, and assets for creation, testing, and benchmarking.

Why are my AI skills not triggering correctly during testing?

AI skills not triggering correctly during testing often indicate that the skill description needs optimization, requiring you to run evaluations and apply iterative refinement to the definition for accurate AI matching.