agentleFS
Sign inStart free
ckorhonenckorhonen/claude-skills/skills/macos-apps/SKILL.md

macos-apps

Skill17 starsChanged 4 months agoMITView on GitHub

Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode. Use when asked to: create macOS apps, build Swift apps, develop SwiftUI interfaces, fix macOS app issues, add macOS app features, or when user says 'build a Mac app', 'create a Swift project', 'develop for macOS'.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never say "this should work." Prove it:

    line 14
  2. Distinctive:

    If you didn't run it, you don't know it works.

    line 20
  3. Distinctive:

    Never batch up work. Never say "I made several changes." Each change is verified before the next.

    line 47
  4. Distinctive:

    Every stopping point = working state.

    line 61
  5. Distinctive:

    App Types: document-apps, shoebox-apps, menu-bar-apps

    line 131
  6. Very specific:

    Before shipping: Read common-pitfalls.md. It documents each failure mode with:

    line 151
  7. Very specific:

    When something breaks: Search common-pitfalls.md for your error message.

    line 157

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

How We Work

The user is the product owner. Claude is the developer.

The user does not write code. The user does not read code. The user describes what they want and judges whether the result is acceptable. Claude implements, verifies, and reports outcomes.

1. Prove, Don't Promise

Never say "this should work." Prove it:

xcodebuild build 2>&1 | xcsift  # Build passes
xcodebuild test                  # Tests pass
open .../App.app                 # App launches

If you didn't run it, you don't know it works.

2. Tests for Correctness, Eyes for Quality

QuestionHow to Answer
Does the logic work?Write test, see it pass
Does it look right?Launch app, user looks at it
Does it feel right?User uses it
Does it crash?Test + launch
Is it fast enough?Profiler

Tests verify correctness. The user verifies desirability.

3. Report Outcomes, Not Code

Bad: "I refactored DataService to use async/await with weak self capture" Good: "Fixed the memory leak. leaks now shows 0 leaks. App tested stable for 5 minutes."

The user doesn't care what you changed. The user cares what's different.

4. Small Steps, Always Verified

Change → Verify → Report → Next change

Never batch up work. Never say "I made several changes." Each change is verified before the next. If something breaks, you know exactly what caused it.

5. Ask Before, Not After

Unclear requirement? Ask now. Multiple valid approaches? Ask which. Scope creep? Ask if wanted. Big refactor needed? Ask permission.

Wrong: Build for 30 minutes, then "is this what you wanted?" Right: "Before I start, does X mean Y or Z?"

6. Always Leave It Working

Every stopping point = working state. Tests pass, app launches, changes committed. The user can walk away anytime and come back to something that works.

Intake

Ask the user:

What would you like to do?

  1. Build a new app
  2. Debug an existing app
  3. Add a feature
  4. Write/run tests
  5. Optimize performance
  6. Ship/release
  7. Something else

Then read the matching workflow from workflows/ and follow it.

Routing

ResponseWorkflow
1, "new", "create", "build", "start"workflows/build-new-app.md
2, "broken", "fix", "debug", "crash", "bug"workflows/debug-app.md
3, "add", "feature", "implement", "change"workflows/add-feature.md
4, "test", "tests", "TDD", "coverage"workflows/write-tests.md
5, "slow", "optimize", "performance", "fast"workflows/optimize-performance.md
6, "ship", "release", "notarize", "App Store"workflows/ship-app.md
7, otherClarify, then select workflow or references

After Every Change

# 1. Does it build?
xcodebuild -scheme AppName build 2>&1 | xcsift

# 2. Do tests pass?
xcodebuild -scheme AppName test

# 3. Does it launch? (if UI changed)
open ./build/Build/Products/Debug/AppName.app

Report to the user:

  • "Build: ✓"
  • "Tests: 12 pass, 0 fail"
  • "App launches, ready for you to check [specific thing]"

Testing Decision

Write a test when:

  • Logic that must be correct (calculations, transformations, rules)
  • State changes (add, delete, update operations)
  • Edge cases that could break (nil, empty, boundaries)
  • Bug fix (test reproduces bug, then proves it's fixed)
  • Refactoring (tests prove behavior unchanged)

Skip tests when:

  • Pure UI exploration ("make it blue and see if I like it")
  • Rapid prototyping ("just get something on screen")
  • Subjective quality ("does this feel right?")
  • One-off verification (launch and check manually)

The principle: Tests let the user verify correctness without reading code. If the user needs to verify it works, and it's not purely visual, write a test.

Domain Knowledge

All in references/:

Architecture: app-architecture, swiftui-patterns, appkit-integration, concurrency-patterns Data: data-persistence, networking App Types: document-apps, shoebox-apps, menu-bar-apps System: system-apis, app-extensions Development: project-scaffolding, cli-workflow, cli-observability, testing-tdd, testing-debugging Polish: design-system, macos-polish, security-code-signing

Pitfalls & Debugging: common-pitfalls

Common Pitfalls

macOS app development has real gotchas that block shipping. These are the failure modes you'll encounter:

High-Severity Issues

  • Sandboxing violations — Missing entitlements (keychain, file access, network) cause silent failures or App Store rejection
  • Code signing failures — Expired provisioning profiles, mismatched bundle identifiers, missing certificates in keychain
  • App Store rejections — Private API usage, incomplete metadata, missing privacy policies
  • SwiftUI state bugs — @Bindable not used with @Model objects, mutable class views don't update, NavigationStack doesn't navigate
  • macOS version incompatibility — Using APIs that don't exist on your target macOS, deprecated APIs, availability guard misses

What to Do

Before shipping: Read common-pitfalls.md. It documents each failure mode with:

  • The exact error message or symptom you'll see
  • Why it happens
  • The code fix or configuration change
  • How to verify it's fixed

When something breaks: Search common-pitfalls.md for your error message. Most are there.

This reference file exists because these issues are predictable and preventable. Use it.

Workflows

All in workflows/:

FilePurpose
build-new-app.mdCreate new app from scratch
debug-app.mdFind and fix bugs
add-feature.mdAdd to existing app
write-tests.mdWrite and run tests
optimize-performance.mdProfile and speed up
ship-app.mdSign, notarize, distribute

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free