skill-creator

Create AI skills with SKILL.md files and automated evaluations.

Updated Aug 27, 2026

Search Tags:#skill development #AI tools #workflow automation #prompt engineering #optimization #evaluation

Ready to run

npx skills add https://github.com/swtch1/dotfiles --skill skill-creator-swtch1

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/swtch1/dotfiles/tree/main/.claude/skills/skill-creator
Command: npx skills add https://github.com/swtch1/dotfiles --skill skill-creator-swtch1

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-powered skills, making it accessible for users of all technical backgrounds.

Core Features & Use Cases

Skill Creation: Guide users through defining intent, writing SKILL.md, and structuring skill resources.
Iterative Improvement: Facilitate testing, feedback collection, and refinement of skills based on performance metrics.
Description Optimization: Automatically tune skill descriptions for optimal triggering accuracy.
Use Case: You have an idea for a new skill to help users manage their code snippets. Use this Skill to draft the SKILL.md, create test cases, run evaluations, and iterate on the description until it triggers reliably.

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 build and test AI skills from an initial concept?▼

To build and test AI skills, you define the intent, draft the SKILL.md file, create test cases, and run iterative evaluations. This end-to-end process supports skill creation, automated performance benchmarking, and refinement based on feedback metrics.

How do I optimize AI skill descriptions for better triggering accuracy?▼

You optimize AI skill descriptions by tuning them iteratively through automated evaluation. This process enhances discoverability and ensures the skill triggers accurately based on user intent and performance benchmarking results.

What is the best way to automate workflow evaluation for AI tools?▼

The best way to automate workflow evaluation is using iterative testing via automated evaluation and performance benchmarking. This approach collects feedback metrics to refine prompt engineering and optimize deterministic task scripting.

Can I use scripts for deterministic task execution in skill development?▼

Yes, skill development integrates with execution environments for deterministic task scripting. This allows you to structure skill resources, automate specific workflow tasks, and provide operational context within structured documentation.

Do I need prior prompt engineering experience to create AI skills?▼

No prior prompt engineering experience is required. The skill development lifecycle streamlines the process from initial concept to deployment, making skill creation, iterative improvement, and description optimization accessible for users of all technical backgrounds.