Build with AI.
Check with evidence.

Swift reviews

Review AI-generated Swift before you trust it

A focused review, a small patch and a real test beat a confident completion message.

Testing & Simulator

Five checks for an AI-built SwiftUI app

Use persistence, search and accessible states to make “it works” a testable claim.

AI clients

Choose an AI client for your iOS workflow

Understand the difference between a skill, a local MCP connection and ChatGPT web setup.

AI clients

Claude Code: turn a Swift finding into a tested patch

A small review-to-test loop for an existing iOS project.

AI clients

ChatGPT and Codex: plan the app, then verify it locally

Separate a browser planning session from a connected development environment.

AI clients

Gemini CLI: connect once and review one iOS feature

Avoid duplicate connections and keep setup evidence separate from app evidence.

AI clients

Muse Code: what our integration actually verifies

Discovery and hooks are useful milestones, but they are not a finished app.

SwiftUI

SwiftUI: review state transitions before polishing the screen

Make loading, empty, success and error states part of the implementation brief.

Design & assets

Generate light and dark asset catalogs without a paid design tool

Turn explicit color tokens into Assets.xcassets, then inspect the result in your app.

AI clients

Which Muse Code MCP settings actually work with a local Swift review server?

A reproducible Muse 1.3.0 connection check, with the exact configuration and clear limits on what discovery proves.

Agent workflow

How can Claude Code hooks protect generated files and verify a project before stopping?

A tested generated-file guard and Stop check, with configuration, reproducible exit codes, and enforcement limits.

Swift reviews

How can I catch Swift concurrency review findings before accepting an agent’s changes?

A real before-and-after MCP review with file and line evidence, plus the limits of text-based concurrency checks.

Swift reviews

How should I review availability guards when moving a Swift app toward iOS 27?

A measured guard-review example that separates SDK availability, runtime readiness, and static-analysis limits.

Design & assets

How can design tokens generate light, dark and high-contrast color assets?

Generate a real xcassets catalog from explicit color tokens, inspect its four variants, and compile it with actool.