Skip to content
mcp/skillhub

Agent Skill

Write Swift skill

write-swiftemilkowalski/skillsskills/write-swift/SKILL.md

How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know about yet. Use when writing, reviewing, or migrating Swift, or when a concurrency error, a hang, a data race, a retain cycle, or a performance problem needs fixing.

48kMIT

always on

107 tokname + description

once used

9,200 tokSKILL.md body

bundled files

0

installs

111kskills.sh

Install the Write Swift skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/emilkowalski/skills --skill write-swift

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/emilkowalski/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -R /tmp/skills/skills/write-swift ~/.claude/skills/write-swift

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description107 tok
When the agent uses itThe SKILL.md instructions9,200 tok
Only if openedNo bundled files—

Until it is used, write-swift costs about 13× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 15 skills from emilkowalski/skills would load 1,400 tokens of descriptions. Skills vs MCP study

Checks

  • The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Write Swift
  • Initial Response
  • 1. Model data with value types
  • 2. Errors and optionals — make the failure paths visible
  • 3. Concurrency: stay single-threaded until profiling says otherwise
  • The rule that changed
  • Actor reentrancy
  • 4. Sendable and sharing data
  • 5. Structured concurrency
  • 6. Concurrency in SwiftUI
  • 7. Protocols and generics
  • some vs any
  • 8. API design — clarity at the point of use
  • 9. Performance — measure, then choose
  • 10. ARC and object lifetime
  • 11. Testing — Swift Testing by default
  • 12. Macros
  • 13. Logging and debugging
  • 14. Unsafe code and interop
  • 15. Modern syntax you should be using
  • 16. Migrating an existing codebase to Swift 6
  • Quick Reference

More skills from emilkowalski/skills

All skills in this repo
  1. emil-design-engemilkowalski/skills

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

    376k35 tok idle · 6,015 in use
  2. review-animationsemilkowalski/skills

    Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

    246k34 tok idle · 1,928 in use
  3. apple-designemilkowalski/skills

    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

    233k79 tok idle · 5,067 in use
  4. animation-vocabularyemilkowalski/skills

    Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

    229k98 tok idle · 2,859 in use
  5. improve-animationsemilkowalski/skills

    Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.

    214k97 tok idle · 1,748 in use
  6. find-animation-opportunitiesemilkowalski/skills

    Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use improve-animations or review-animations instead.

    199k78 tok idle · 2,206 in use
  7. pick-ui-libraryemilkowalski/skills

    Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.

    176k61 tok idle · 1,102 in use
  8. prototypeemilkowalski/skills

    Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.

    165k48 tok idle · 1,637 in use