Swift Coding Agent Skill

Apply when writing or editing Swift (.swift) files.

Context cost
3.5k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 14.2 kBtext throughout, nothing executable
Licence
Apache-2.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Apply when writing or editing Swift (.swift) files. Behavioral corrections for error handling, concurrency, memory management, type safety, protocol-oriented design, security defaults, and common antipatterns. Project conventions always override these defaults.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

mobileswiftwriting

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md14.2 kB · preview
--- name: swift-coding ---
6# Swift Coding
7
8Match the project's existing conventions. When uncertain, read 2-3 existing files to infer the local style. Check Package.swift or .xcodeproj/.xcworkspace for Swift version, platform targets, and dependencies. New Xcode 26+ app projects default to Approachable Concurrency (Swift 6.2+) with main-actor isolation for app module code — assume this default unless the project explicitly disables it. These defaults apply only when the project has no established convention.
9
10## Never rules
11
12These are unconditional. They prevent bugs and vulnerabilities regardless of project style.
13
14- **Never force unwrap (!) outside tests and controlled contexts** — crashes at runtime with no recovery path. Use guard let, if let, ??, or optional chaining. Force unwrap is acceptable in tests, @IBOutlet, and when failure is provably a programmer error with an explaining comment.
15- **Never try! outside tests** — crashes on any error. Use do-catch, try?, or propagate with throws. A network timeout, a missing file, a malformed response — any of these kill your process silently with no chance to recover or report.
16- **Never bare catch { } without handling** — silently swallows errors. Catch specific error types, or log and rethrow. A decode failure looks the same as a permission error, and you'll never know which one is happening in production.
17- **Never [weak self] without checking for nil** — accessing self after capture without guard let self leads to silent no-ops or partial execution. Half-completed operations are worse than failures because they corrupt state without raising errors.
18- **Never mutable global or static state** — shared mutable state causes data races. Use actors, @MainActor, or dependency injection. The Swift 6 concurrency model will flag these as compile errors, so fix them now.
19- **Never blocking calls on MainActor** — no Thread.sleep(), synchronous network calls, or heavy computation on the main thread. Use Task, async/await, or dispatch to a background context. Blocking main freezes the UI and triggers watchdog kills on iOS.
20- **Never x = x + y to build strings in loops** — use += or append(contentsOf:), which grow the buffer in place (amortized, via copy-on-write), or joined(separator:) for collections. x = x + y allocates and copies a fresh string every iteration.
21- **Never hand-roll cryptographic key material** — use CryptoKit (SymmetricKey(size:)) or SecRandomCopyBytes for keys, tokens, and session IDs. For general randomness, Int.random(in:) and SystemRandomNumberGenerator are fine — the system RNG is cryptographically secure.
22- **Never print() in production code** — use os.Logger or OSLog. print is not filterable, not structured, and persists in release builds. It cannot be searched in Console.app and adds noise to device logs.
23- **Never class when struct suffices** — default to value types. Use class only when you need reference semantics, inheritance, or identity. Value types avoid retain/release overhead and are safe to copy across threads — though closure captures, existential boxes, and CoW buffers can still put struct storage on the heap.
24- **Never retain cycles in closures** — escaping closures capturing self in classes must use [weak self] or [unowned self]. Retain cycles cause silent memory leaks that accumulate over app lifetime, eventually triggering OOM kills.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,951 words
Files1
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈80
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
3,470
on trigger
The instruction body, read only when the skill fires.
1.8%
of a 200k window
Ten skills this size would take about 18% of the window before you open a file.
050k100k150k200k context window

3.5k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 14.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md14.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Swift Coding · 3.5k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/swift-coding/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/swift-coding" ] && { [ ! -e .claude/skills/swift-coding ] || { mv .claude/skills/swift-coding "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/swift-coding" .claude/skills/ && echo "Installed .claude/skills/swift-coding"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add dynokostya/swift-coding

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/swift-coding/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/swift-coding/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/swift-coding" ] && { [ ! -e ~/.claude/skills/swift-coding ] || { mv ~/.claude/skills/swift-coding "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/swift-coding" ~/.claude/skills/ && echo "Installed ~/.claude/skills/swift-coding" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/swift-coding/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencedynokostya/swift-coding

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

DY
Dynokostya

Publishes on mcprush.

0 servers listed2 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill