skill-creator

Create, modify, test, and benchmark AI skills with SKILL.md files.

Updated Mar 7, 2026

Search Tags:#skill development #workflow automation #prompt engineering #AI agent #evaluation #performance tuning

Ready to run

npx skills add https://github.com/Geargrindadmin/gg-agentic-harness --skill skill-creator-geargrindadmin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Geargrindadmin/gg-agentic-harness/tree/main/.agent/skills/skill-creator
Command: npx skills add https://github.com/Geargrindadmin/gg-agentic-harness --skill skill-creator-geargrindadmin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the entire lifecycle of creating and improving AI skills, from initial concept to performance measurement, making it accessible to users of all technical backgrounds.

Core Features & Use Cases

Skill Creation: Guides users through defining intent, interviewing for edge cases, and writing the SKILL.md file.
Iterative Improvement: Facilitates testing, evaluation, and refinement of skills based on user feedback and performance metrics.
Performance Measurement: Includes tools for running benchmarks, analyzing results, and optimizing skill descriptions for better triggering accuracy.
Use Case: You have an idea for a new skill to help Claude summarize meeting transcripts. Use this Skill to draft the SKILL.md, create test cases, run evaluations against a baseline, analyze the results, and iterate on the skill until it performs optimally.

Quick Start

Use the skill creator to help me build 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 create and test AI skills from scratch?▼

To create and test AI skills, you define the skill intent, write the `SKILL.md` file, set up test cases, and run evaluations to measure performance against a baseline. This iterative development loop refines skill descriptions for optimal triggering accuracy.

What is the best way to measure AI agent performance and optimize prompts?▼

Measuring AI agent performance involves running benchmarks with and without the skill, analyzing the evaluation results, and optimizing the prompt engineering in the skill description to improve triggering accuracy and overall task execution.

Can I use this for iterative workflow automation improvement?▼

Yes, iterative workflow automation improvement is supported through testing loops that evaluate performance metrics, gather feedback, and refine the skill logic until the AI agent performs optimally for your specific use case.

How does skill development handle edge cases in prompt engineering?▼

Skill development handles edge cases by interviewing users during the creation phase to identify potential scenarios, which are then translated into test cases for evaluation, ensuring the prompt engineering is robust against unexpected inputs.

Do I need prior coding experience to write and evaluate SKILL.md files?▼

No prior coding experience is strictly required to write and evaluate `SKILL.md` files, as the process guides users of all technical backgrounds through defining intent, setting up test cases, and analyzing benchmark results.

Why is my AI skill not triggering correctly during workflow automation?▼

An AI skill might not trigger correctly if the skill description lacks optimization, requiring you to run performance tuning evaluations, analyze benchmark results, and iteratively refine the description for improved accuracy.