Swift Testing Agent Skill for AI Coding Assistants
An agent skill that helps AI coding assistants like Claude Code, Codex, Cursor, and Gemini write better tests using Swift Testing. Covers @Test, #expect, #require, parameterized testing, traits, exit tests, confirmations, and more, targeting the mistakes LLMs actually make.
Also available:
Find more agent skills for Swift and Apple platform development at Swift Agent Skills.
Installing Swift Testing Pro
Claude Code
Add the Swift Testing Agent Skill marketplace, then install the plugin:
/plugin marketplace add twostraws/Swift-Testing-Agent-Skill
/plugin install swift-testing-pro@swift-testing-agent-skill
Codex, Gemini, Cursor, and others
npx skills add https://github.com/twostraws/swift-testing-agent-skill --skill swift-testing-pro
If you get the error npx: command not found, it means you don’t currently have Node installed. You need to run this command to install Node through Homebrew:
brew install node
And if that fails it usually means you need to install Homebrew first.
When using npx, you can select exactly which agents you want to use during the installation. You can also select whether the skill should be installed just for one project, or whether it should be made available for all your projects.
Alternatively, you can clone this whole repository and install it however you want.
If you're using Xcode, watch the YouTube video on How to Install and Use Agent Skills in Xcode for a walkthrough.
Using Swift Testing Pro
The skill is called Swift Testing Pro, and can be triggered in various ways. For example, in Claude Code you would use this:
/swift-testing-pro
And in Codex you would use this:
$swift-testing-pro
In both cases you can provide specific instructions if you want only a partial review. For example, /swift-testing-pro Make sure my tests are fully parameterized on Claude, or $swift-testing-pro Add exit tests to my test suites in Codex.
You can also trigger the skill using natural language:
Use the Swift Testing Pro skill to look for ways to improve the tests in this project.
Why Use an Agent Skill for Swift Testing?
I wrote a book on Swift Testing, and update it regularly as new features are added. I’ve also written a comprehensive set of articles introducing what’s new in Swift (see here, here, and here for examples), and so I’ve made it my business to understand the ins and outs of Swift Testing.
This skill is the result of all that work. The rules contained here directly target common Swift Testing mistakes made by LLMs, covering new features they aren’t trained on, older features they frequently make mistakes with, and patterns that help make tests stay smaller and run faster.
What this is not is just a dumping ground for all Swift Testing advice ever. Agents already have a solid grounding of the fundamentals of Swift Testing, so skills that do little more than reteach them what they already know are just burning tokens.
This skill focuses on what actually has an impact.
Contributing
I welcome all contributions, whether that's adding new checks, improving existing checks, or editing this README – everyone is welcome!
- Keep your Markdown concise. There is a token cost to using skills, particularly with SKILL.md, so please respect the token budgets of users.
- Do not repeat things that LLMs already know, because it burns tokens for no benefit. Focus on edge cases, surprises, soft deprecations, and similar.
- All work must be licensed under the MIT license so it can benefit the most people.
Please ensure you abide by the Code of Conduct.
License
