Swiftui Preview logo

Swiftui Preview

Community
xenodium
swiftui-preview

This skill should be used when the user invokes "/swiftui-preview" to render SwiftUI code from the current context to a PNG and output the resulting image path.

Overview

Publisherxenodium
Repositoryemacs-skills
Skill nameswiftui-preview
Stars
148
Forks
18
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by xenodium on GitHub. Read the source before you install it.

Installation

Install the Swiftui Preview AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/xenodium/emacs-skills/tree/main/skills/swiftui-preview
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/xenodium/emacs-skills.git /tmp/emacs-skills
mkdir -p .claude/skills
cp -r /tmp/emacs-skills/skills/swiftui-preview .claude/skills/swiftui-preview
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Swiftui Preview in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Swiftui Preview on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Swiftui Preview is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Render a SwiftUI preview

Generate SwiftUI code from the most recent interaction context, render it to a PNG using ImageRenderer, and output it as a markdown image so it renders inline.

The "context" can take any form: a prose description ("show a profile card with a photo on the left and name above bio on the right"), an attached screenshot or mockup image, an ASCII layout diagram, or actual Swift code. Translate whichever the user provided into a single ContentView.

For example, this ASCII diagram:

+------------------+--------------------------------------+
|                  |           Name                       |
|                  +--------------------------------------+
|    Photo         |                                      |
|                  |           Biography                  |
|                  |                                      |
+------------------+--------------------------------------+

should become an HStack with the photo on the left and a VStack { Name; Biography } on the right, sized so the photo spans the full height. Match proportions and stacking direction faithfully; choose reasonable placeholder content (e.g. Image(systemName: "person.crop.square.fill"), sample text) when the input doesn't specify.

How to render

  1. Derive SwiftUI view code from the current context — prose, image, ASCII diagram, or existing Swift. The root view must be named ContentView. Helper views may be defined alongside.
  2. Locate agent-skill-swiftui.el which lives alongside this skill file at skills/swiftui-preview/agent-skill-swiftui.el in the emacs-skills plugin directory.
  3. Invoke the elisp function in a single Bash call. To avoid shell+elisp quoting issues with arbitrary Swift code, pipe the source through base64 and decode it on the elisp side:
    sh
    emacsclient --eval "(progn (load \"/path/to/skills/swiftui-preview/agent-skill-swiftui.el\" nil t) (agent-skill-swiftui-render :swift-source (base64-decode-string \"$(base64 <<'SWIFT' | tr -d '\n'
    struct ContentView: View {
      var body: some View {
        Text("Hello, SwiftUI!")
          .font(.largeTitle)
          .padding(40)
      }
    }
    SWIFT
    )\")))"
    The 'SWIFT' heredoc delimiter is single-quoted so the source passes through verbatim — no shell escaping needed inside.
  4. The function returns the PNG path as a quoted elisp string (e.g. "/var/folders/.../agent-swiftui-XXXX.png") on success, or nil on failure.
  5. On success, output the result as a markdown image on its own line:
    ![description](/var/folders/.../agent-swiftui-XXXX.png)

SwiftUI source template

Do NOT include import SwiftUI — the wrapper imports it. Provide only the view structs:

swift
struct ContentView: View {
  var body: some View {
    VStack(spacing: 20) {
      Text("Hello, SwiftUI!")
        .font(.largeTitle)
      RoundedRectangle(cornerRadius: 12)
        .fill(Color.orange)
        .frame(width: 200, height: 100)
    }
    .padding(40)
  }
}

If the source contains no struct or class definitions, it is wrapped automatically as the body of a generated ContentView. Otherwise it must define ContentView itself.

Rules

  • The root view must be named ContentView when the source contains struct/class definitions.
  • Do not include import SwiftUI in the source — the wrapper adds it.
  • Use one Bash call. Pass the source via the base64 | tr -d '\n' pipe inside the single-quoted 'SWIFT' heredoc — do not write a temp .swift file as an intermediate step.
  • Locate agent-skill-swiftui.el relative to this skill file's directory.
  • Run the emacsclient --eval command via the Bash tool.
  • emacsclient prints the return value as an elisp literal — strip the surrounding " quotes from the path before emitting the markdown image link.
  • On success, output a markdown image (![description](path)) on its own line.
  • On nil return, inform the user that the SwiftUI render failed and show the source so they can debug.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Swiftui Preview AI skill do?

This skill should be used when the user invokes "/swiftui-preview" to render SwiftUI code from the current context to a PNG and output the resulting image path.

Why use Swiftui Preview on TypingMind?

Because you install it once and use it with any model. Swiftui Preview is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Swiftui Preview in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xenodium/emacs-skills/tree/main/skills/swiftui-preview. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Swiftui Preview?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Swiftui Preview?

As many as you like. As long as a model supports skills, you can use Swiftui Preview with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Swiftui Preview AI skill free?

It is published on GitHub by xenodium. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇