Wednesday, October 7, 2026ArchiveSearchAsk the paper

The Computomatix Times

All the posts fit to save — curated from @computomatix's bookmarks & likes on X

Edition of Friday, April 10, 2026

3 stories

Developer Lists Five Agent Skill Packs for Swift and Xcode Projects

Install These Skills Before Codex Touches Your Xcode Project

iOS developer Paul Solt recommends installing community skill packs before letting Codex or Claude Code work on Xcode projects, citing deprecated code and compiler errors as common agent failures. The packs come from Paul Hudson, Antoine van der Lee, Thomas Ricouard and others, covering SwiftUI, concurrency, testing and build optimization.

Original post · 6 min read
X ArticleInstall These Skills Before Codex Touches Your Xcode Project
I've been building iOS and macOS apps with Codex and Claude Code since last year. One thing I've learned: agents need simple systems that produce reliable results.
Without the right skills, agents write deprecated code, create compiler errors, and waste your time debugging their mistakes. These 5 skill packs fix that. Each one comes from a developer who's been shipping real apps with agents.
1. Paul Hudson: The Swift Foundation

If you've learned Swift online, you've probably read Paul Hudson's work (@twostraws). His agent skills come from a decade of teaching Swift through Hacking with Swift — and his SwiftUI rules help correct common mistakes with agents.
I met Paul at try! Swift in NYC and we spent some time together in the SwiftUI labs at WWDC 2019. He's a prolific writer and digs in deep so you can understand what works.

These skills will jumpstart your agents:
SwiftUI Pro: modern SwiftUI APIs, view composition, state management
Swift Concurrency Pro: async/await, actors, Sendable, Swift 6 migration
Swift Testing Pro: Test macros, parameterized tests, XCTest migration
SwiftData Pro: models, queries, migrations, CloudKit sync
He also maintains the canonical directory of every community Swift skill.
2. Antoine van der Lee: SwiftLee

Antoine van der Lee (@twannl) runs SwiftLee — one of the most widely read Swift blogs. He has 5 skill repos, each with detailed reference docs. His Xcode Build Optimization skill stands out — 6 sub-skills for build settings and compilation times to make your code build faster.
SwiftUI Expert: state management, view composition, performance, Liquid Glass
Swift Concurrency: actors, Sendable, data race safety, Swift 6 migration
Swift Testing Expert: modern testing patterns, XCTest migration, parameterized tests
Core Data Expert: stack setup, fetch requests, background contexts, migrations
Xcode Build Optimization: 6 sub-skills for build settings, compilation times, project config
The Xcode Build Optimization skill is a powerful tool that can make both you and your agents more productive. And if you want a better workflow with the iOS Simulator, check out his developer app: @rocketsim_app
3. Thomas Ricouard: Codex Expert

Thomas Ricouard (@Dimillian) built Codex Monitor — the open source macOS app for managing multiple Codex agents — and then joined OpenAI's Developer Experience team.
His skills now ship as the official Codex Build iOS App and Build Mac App plugins. These automatically update with each new release of the Codex app or Codex CLI.
Build iOS Apps plugin
SwiftUI Liquid Glass: iOS 26+ Liquid Glass APIs, modifier ordering, fallbacks
SwiftUI UI Patterns: navigation, sheets, app wiring, reusable components
SwiftUI Performance Audit: invalidation storms, identity churn, layout thrash
SwiftUI View Refactor: smaller subviews, MV-style data flow, Observation
iOS Debugger Agent: simulator build/run/debug with XcodeBuildMCP
iOS App Intents: Siri, Shortcuts, widget integration
Build macOS Apps plugin adds AppKit interop, packaging/notarization, signing/entitlements, window management, and SwiftPM workflows.
You can dig into the source for both of these plugins at the Official OpenAI Plugins repo,
4. Krzysztof Zabłocki: Advanced Swift + Tooling

Krzysztof Zabłocki (@merowing_) created Sourcery — the Swift metaprogramming tool used by 40,000+ apps including Airbnb and The New York Times. His open source tools power over 80,000 apps total.
His approach to agent skills is completely different. Instead of individual skill files, he built a rules-based system over 3 years of daily LLM use — 12 domain-specific rule files with a smart loader that uses LLM self-reflection to decide which rules to apply based on context. The system is tool-agnostic: same rules work in Cursor, Claude Code, and Codex.
What I like about his approach: he has a progressive documentation reading CLI tool to offload search and make it agent-friendly. He also created Inject for hot Swift reloading — useful for fast prototyping when you want to see UI changes without rebuilding.
Read his guide: Stop Getting Average Code from Your LLM
You can grab two agent friendly files that follow his coding philosophy:
general.md: primary directive and coding standards
rule-loading.md: smart loader that selects rules by context
The full 12-file set covering dependency injection, SwiftUI architecture, ViewModel coordination, and Swift Testing is part of his Swifty Stack course.
5. AppCreator: Agent-Friendly Build Tools
None of the skills above matter if your agent can't build and test your code.
Xcode build output is verbose. Test output is worse. We're juggling XCTest and Swift Testing with two different build systems. Agents choke on this.
I built AppCreator to solve that problem. It scaffolds Xcode projects with agent-friendly defaults. I created it to quickly prototype new app ideas that used the same workflow as my existing projects.
Adopt the skill for your existing apps and it will help your agent make a build … continue on X ↗
♥ 2.6K · ⟲ 187 · 👁 1.7MView on X ↗

Aakash Gupta Proposes Shared Claude Code Repo as Product Manager Operating System

Aakash Gupta Proposes Shared Claude Code Repo as Product Manager Operating System▶

Product writer Aakash Gupta argues PMs should build a shared 'Team OS' repository with a .claude folder, function-specific folders and a CLAUDE.md doc index so every team role can query context. He frames it as a way for PMs to stop being the coordination bottleneck, and links to a video on the approach.

Original post · 2 min read
The PM job used to be about holding context across your team. Now your team is 3x bigger, every role makes product decisions, and engineers are shipping without you.

The PMs who figured this out stopped being the context node. They built one.

A PM used to support 3-4 engineers. Now it's 10+ engineers, plus sales, marketing, support, and design. You cannot manually hold context at that ratio. The math breaks. So the best PMs are building what amounts to a Team Operating System: a single repo where every role on the team queries shared context directly.

The architecture is simpler than you'd expect. A .claude folder with shared agents, commands, and skills. A product development folder with subfolders for each function. A team folder for onboarding and retros. And a CLAUDE.md at the root with a doc index that tells Claude how to navigate the entire repo.

The doc index is the part worth paying attention to. It means anyone on the team can ask a natural language question and get answers from across every function's context. The new designer asks about pricing strategy and gets the answer from the product development folder. The engineer asks about a customer pain point and gets it from support docs. No PM meeting required.

This is the PM version of what happened to middle management in the 2010s. Collaboration tools made it possible for ICs to coordinate without managers as intermediaries. Team OS does the same thing to the PM's coordination function.

The PM who only coordinates is the PM this ratio will crush.
Build the system that replaces you as the bottleneck.
Aakash Gupta @aakashgupta
Every team at your company should be creating their own 'Team OS' in Claude Code on Github. Here's how:

1:45 - What is a Team OS
13:37 - Shared skills and commands
25:24 - Shared team automations
59:50 - The learning flywheel
♥ 119 · ⟲ 7 · 👁 27.5KView on X ↗

Chamath Palihapitiya Argues Companies Should Document Expertise for AI Control

Investor Chamath Palihapitiya shares a long article on AI risks and says documenting tribal knowledge within the right agent harness lets companies control their AI rather than be controlled by it. He promotes his company Software Factory and an accompanying article by Alexander Good.

Original post · 1 min read
This is a long but important article that brings up a lot of points worth considering.

One antidote to the bear case painted below is that by documenting your expert and tribal knowledge in the right agent harness, you control the agents vs the other way around.

The big risk for most companies is leaking all of their edge into a model under the guise of “an AI strategy” only to be confounded when umpteen competitors are enabled to nibble away at your business.

But the right control over your “secrets” can allow you to ge the most of AI without giving up control.

This concept inspired many of the core flows and features of Software Factory and is why it’s becoming the trusted control plane in companies making the AI leap.

Record usage last few weeks btw!

Go check it out @8090_Factory
goodalexander @goodalexander
The Big Rug

Gooning is well covered in the Doom thesis. Elon's "Imagine" is digital crack cocaine being given out for free. So that's in progress. But, GPT5 shows us that enterprise / tool calls is where companies are converging

This mirrors the rest of the economy. Consumer apps have to use ads or extractive loops (gambling/ porn/ DLC video games) to monetize at scale. Or you do Enterprise. Anthropic's CEO has indicated that companies pay up to 10x as much for better reasoning. And that training a model is positive unit economics t+12 months

Which is the first time anyone is talking about …
♥ 257 · ⟲ 23 · 👁 155.1KView on X ↗