For Claude Code devs from a dev with 9 apps on the App Store ↴

Ship your iPhone app. Idea to App Store.

Claude Code writes great Swift, then loses the plot around phase four. Eight opinionated skills + a 347-line playbook keep it honest: scoped PRDs, session-sized phases, fingers-on-simulator verification, App Review survival. No vibes. Rails.

launch week price, $29 after ✍️ P.S. Claude's new Fable 5 built this entire product + site in ~3 hours, as a "$1k in 24h" experiment. The clock is real ⏰
2 skills free
skills/build-phases/SKILL.md
## Phase 3: Persistence,
   entries survive relaunch

Verify (in simulator):
1. Cold-launch. Add three entries.
2. Force-quit. Relaunch:
   all three present, newest first.
3. Swipe-delete one. Relaunch:
   exactly two remain.
4. Dynamic Type to XXL:
   nothing truncates.

Done when: data survives force-quit,
zero fixture data left in the target.
8skills inside

What's in the box

one skill for every stage you actually hit — they fire in order ↓
Free · MIT 1

app-prd

Raw idea in, developer-ready PRD out. One-sentence-job scope test, screens map, Swift data model, and a handoff block the agent can't drift from.

Free · MIT 2

build-phases

PRD in, build plan out. Every phase fits ONE Claude Code session, sized against a real context budget, verified with fingers, not "it compiles."

3

swiftui-scaffold

Architecture before features: @Observable state, route enums, a persistence decision table, mandatory empty + error states. The decisions that cost a rewrite when you make them in phase seven.

4

mockup-to-swiftui

JSX, HTML, or a screenshot into idiomatic SwiftUI, plus the list of web patterns you should never port to iOS.

5

code-audit

Hunts what AI-generated Swift actually breaks: strict-concurrency violations, phantom features, state duplication, crash-on-empty paths.

6

appstore-listing

Every App Store Connect field, ready to paste. How to pack the 100-character keyword field, and an above-the-fold description that earns the tap.

7

screenshot-story

The 5-8 shot narrative with six-word overlay headlines. The first three screenshots decide the install; plan them like it.

8

release-runbook

Signing, TestFlight, privacy labels mapped from what your code touches, and the App Review rejection traps with pre-submission fixes.

skills 1 & 2 up there are the free ones — kick the tires first ↓ 2 skills free on GitHub Get all 8 skills — $19

Judge it by the worked example, not the pitch

FridgeFriend is a real mini-app taken from a three-sentence idea through PRD, build plan, and full SwiftUI source to an App Store listing. The whole thing ships in the free repo, so the quality bar is public.

11Swift files 0dependencies typechecks, iOS 17 SDK
Read it on GitHub — go try to break it →
example/FridgeFriend/PRD.md
## Claude Code Handoff
iOS target:    17.0
Persistence:   SwiftData, one container
Dependencies:  none (hard constraint)
Constraints:   no force-unwraps,
               every screen handles empty
               data, Swift 6 concurrency
               clean

Consumed by build-phases.
Sized: 4 phases.

Two rules do
most of the work

everything else in the system just enforces these two
Rule 01

A phase fits one session, or it's two phases.

Phases are sized against a real context budget: file counts, framework introductions, project-level changes. Mid-phase compaction is treated as a sizing bug, not weather.

Rule 02

Compiling is not verification.

Every phase ends with a numbered script of finger actions in the simulator and the exact observations you must see. "Tests pass" is banned as a milestone.

9 shipped Who's behind this

Nine apps. One pipeline.

I'm Perry. I've shipped nine apps to the App Store, and these days Claude Code is my primary development tool. ShipKit is the system that survived those launches: every phase budget, audit check, and App Review fix in here got earned the annoying way, on real submissions. No team, no course funnel, no Discord to upsell you into: the free repo is the résumé.

9apps on the App Store @TheGuyForAi MITfree tier, judge me first

One pack.
Everything in it.

  • All 8 skills, plain markdown you own. No license keys, nothing phones home.
  • The playbook: 347 lines on session doctrine, verification doctrine, App Review survival.
  • The complete FridgeFriend example repo, MIT-licensed for your own apps.
  • Free 1.x updates for every buyer — yes, even at the launch price. No "Pro" upsell coming.
  • Instant delivery: Ko-fi hands you the zip the second you pay. Drop the folders into ~/.claude/skills/ and they fire on your next session. Two minutes flat.
  • Unlimited personal and commercial apps.
$29
$19
launch week only, under an hour of your rate
Get all 8 skills — $19

Doesn't earn its keep? One message inside 14 days, full refund.

Not sure? Two skills + the example are free on GitHub.

Fair questions

asked by every reasonable developer, answered straight
Isn't this just prompts?

It's a system with opinions that cost real debugging time to earn: context budgets per phase, a persistence decision table, an audit list built from how AI-generated Swift actually fails. The free repo exists so you can check whether those opinions hold up before paying.

What exactly do I get after paying?

An instant Ko-fi download: a zip of plain markdown. Unzip it, drop the skill folders into ~/.claude/skills/, and they trigger automatically in your next Claude Code session. No license key, no account, no course portal — you own the files. Updates come through the same download link.

Does it work with Cursor or other agents?

It's written for Claude Code's skill format, and the triggers are Claude Code specific. The PRD template, phase budgets, and audit checklists port to any agent as plain markdown, but automatic invocation is Claude Code only.

Why isn't all of it free?

Two of the eight skills and the entire worked example are free and MIT-licensed. The paid pack funds maintenance and updates, and it's priced under one hour of a developer's time.

What happens when Claude Code or the models change?

The skills are plain markdown with a small YAML header — the least breakable thing in this stack. When something meaningful shifts, 1.x updates ship through the same download link, free. And since you own the files, you can edit them the day anything changes, without waiting on me. There's no runtime here to rot.

What iOS versions does it target?

iOS 17 and up as the baseline, Swift 6, SwiftUI, SwiftData. Notes are included where newer APIs change the recommendation.

What if it's not for me?

Message me on Ko-fi within 14 days and you get a refund. The files are markdown, so this policy runs on honesty in both directions.