clean-classes

Clean Classes (Clean Code, Ch. 10)

Run this skill on one target type at a time. Language may be Swift, Kotlin, Java, TypeScript, or anything else — the procedure does not change.

If the user did not name a type, ask which class (or file) to run on. Do not scan the whole repo unless they asked for that.

Copy and track:

Clean Class Run:
- [ ] Target type identified
- [ ] Inventory (methods, fields, concretes, switches)
- [ ] Naming test (25 words, no and/or/but)
- [ ] Reasons to change listed
- [ ] Cohesion clusters mapped
- [ ] Open/Closed (switch-on-kind) checked
- [ ] DIP (concretes in policy) checked
- [ ] Split executed if more than one responsibility
- [ ] Each new type re-audited (must pass)
- [ ] Report delivered

Rules that decide a split

A type must be split if any of these fail:

1. Naming test — cannot describe it in ~25 words without "and," "or," or "but."
2. SRP — more than one reason to change (product, network, cache, format, analytics, validation, persistence are different reasons).
3. Cohesion — methods form clusters that barely share fields.
4. Open/Closed — a switch / when / if-else on kind / type / enum grows for every new variant.
5. DIP — high-level policy names concretes (URLSession, Retrofit, UserDefaults, Room, shared prefs) or hidden singletons.

Vague names (Manager, Helper, Processor, Super…, Util) are a smell, not proof — still run the tests above.

A type must not dump leftover jobs into one "helper." Orchestrators (ViewModel, use case) delegate; they do not own networking, cache, formatting, or analytics.

Do not expose private methods just to test them. Extract a type and test that.

Procedure

1. Inventory

From the target type, list:

• Public API (methods the callers use)
• Private helpers
• Instance/static fields
• Concrete types it constructs or calls (URLSession.shared, Retrofit, disk, analytics SDK)
• switch / when / if-else on kind

2. Naming test