Shortcuts Generator logo

Shortcuts Generator

Community
drewocarr
shortcuts-generator

Generate macOS/iOS Shortcuts by creating plist files. Use when asked to create shortcuts, automate workflows, build .shortcut files, or generate Shortcuts plists. Covers 1,155 actions (427 WF*Actions + 728 AppIntents), variable references, and control flow.

Overview

Publisherdrewocarr
Repositorygenerate-shortcuts-skill
Skill nameshortcuts-generator
Stars
219
Forks
20
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the Shortcuts Generator 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/drewocarr/generate-shortcuts-skill/tree/main
  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/drewocarr/generate-shortcuts-skill.git \
  .claude/skills/shortcuts-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shortcuts Generator 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 Shortcuts Generator 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 Shortcuts Generator 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.

macOS Shortcuts Generator

Generate valid .shortcut files that can be signed and imported into Apple's Shortcuts app.

Quick Start

A shortcut is a binary plist with this structure:

xml
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>WFWorkflowActions</key>
    <array>
        <!-- Actions go here -->
    </array>
    <key>WFWorkflowClientVersion</key>
    <string>2700.0.4</string>
    <key>WFWorkflowHasOutputFallback</key>
    <false/>
    <key>WFWorkflowIcon</key>
    <dict>
        <key>WFWorkflowIconGlyphNumber</key>
        <integer>59511</integer>
        <key>WFWorkflowIconStartColor</key>
        <integer>4282601983</integer>
    </dict>
    <key>WFWorkflowImportQuestions</key>
    <array/>
    <key>WFWorkflowMinimumClientVersion</key>
    <integer>900</integer>
    <key>WFWorkflowMinimumClientVersionString</key>
    <string>900</string>
    <key>WFWorkflowName</key>
    <string>My Shortcut</string>
    <key>WFWorkflowOutputContentItemClasses</key>
    <array/>
    <key>WFWorkflowTypes</key>
    <array/>
</dict>
</plist>

Minimal Hello World

xml
<dict>
    <key>WFWorkflowActionIdentifier</key>
    <string>is.workflow.actions.gettext</string>
    <key>WFWorkflowActionParameters</key>
    <dict>
        <key>UUID</key>
        <string>A1B2C3D4-E5F6-7890-ABCD-EF1234567890</string>
        <key>WFTextActionText</key>
        <string>Hello World!</string>
    </dict>
</dict>
<dict>
    <key>WFWorkflowActionIdentifier</key>
    <string>is.workflow.actions.showresult</string>
    <key>WFWorkflowActionParameters</key>
    <dict>
        <key>Text</key>
        <dict>
            <key>Value</key>
            <dict>
                <key>attachmentsByRange</key>
                <dict>
                    <key>{0, 1}</key>
                    <dict>
                        <key>OutputName</key>
                        <string>Text</string>
                        <key>OutputUUID</key>
                        <string>A1B2C3D4-E5F6-7890-ABCD-EF1234567890</string>
                        <key>Type</key>
                        <string>ActionOutput</string>
                    </dict>
                </dict>
                <key>string</key>
                <string></string>
            </dict>
            <key>WFSerializationType</key>
            <string>WFTextTokenString</string>
        </dict>
    </dict>
</dict>

Core Concepts

1. Actions

Every action has:

  • Identifier: is.workflow.actions.<name> (e.g., is.workflow.actions.showresult)
  • Parameters: Action-specific configuration in WFWorkflowActionParameters
  • UUID: Unique identifier for referencing this action's output

2. Variable References

To use output from a previous action:

  1. The source action needs a UUID parameter
  2. Reference it using OutputUUID in an attachmentsByRange dictionary
  3. Use  (U+FFFC) as placeholder in the string where the variable goes
  4. Set WFSerializationType to WFTextTokenString

3. Control Flow

Control flow actions (repeat, conditional, menu) use:

  • GroupingIdentifier: UUID linking start/middle/end actions
  • WFControlFlowMode: 0=start, 1=middle (else/case), 2=end

Common Actions Quick Reference

ActionIdentifierKey Parameters
Textis.workflow.actions.gettextWFTextActionText
Show Resultis.workflow.actions.showresultText
Ask for Inputis.workflow.actions.askWFAskActionPrompt, WFInputType
Use AI Modelis.workflow.actions.askllmWFLLMPrompt, WFLLMModel, WFGenerativeResultType
Commentis.workflow.actions.commentWFCommentActionText
URLis.workflow.actions.urlWFURLActionURL
Get Contents of URLis.workflow.actions.downloadurlWFURL, WFHTTPMethod
Get Weatheris.workflow.actions.weather.currentconditions(none required)
Open Appis.workflow.actions.openappWFAppIdentifier
Open URLis.workflow.actions.openurlWFInput
Alertis.workflow.actions.alertWFAlertActionTitle, WFAlertActionMessage
Notificationis.workflow.actions.notificationWFNotificationActionTitle, WFNotificationActionBody
Set Variableis.workflow.actions.setvariableWFVariableName, WFInput
Get Variableis.workflow.actions.getvariableWFVariable
Numberis.workflow.actions.numberWFNumberActionNumber
Listis.workflow.actions.listWFItems
Dictionaryis.workflow.actions.dictionaryWFItems
Repeat (count)is.workflow.actions.repeat.countWFRepeatCount, GroupingIdentifier, WFControlFlowMode
Repeat (each)is.workflow.actions.repeat.eachWFInput, GroupingIdentifier, WFControlFlowMode
If/Otherwiseis.workflow.actions.conditionalWFInput, WFCondition, GroupingIdentifier, WFControlFlowMode
Choose from Menuis.workflow.actions.choosefrommenuWFMenuPrompt, WFMenuItems, GroupingIdentifier, WFControlFlowMode
Find Photosis.workflow.actions.filter.photosWFContentItemFilter (see FILTERS.md)
Delete Photosis.workflow.actions.deletephotosphotos (NOT WFInput!)

Detailed Reference Files

For complete documentation, see:

Signing Shortcuts

Shortcuts MUST be signed before they can be imported. Use the macOS shortcuts CLI:

bash
# Sign for anyone to use
shortcuts sign --mode anyone --input MyShortcut.shortcut --output MyShortcut_signed.shortcut

# Sign for people who know you
shortcuts sign --mode people-who-know-me --input MyShortcut.shortcut --output MyShortcut_signed.shortcut

The signing process:

  1. Write your plist as XML to a .shortcut file
  2. Run shortcuts sign to add cryptographic signature (~19KB added)
  3. The signed file can be opened/imported into Shortcuts.app

Workflow for Creating Shortcuts

  1. Define actions - List what the shortcut should do
  2. Generate UUIDs - Each action that produces output needs a unique UUID
  3. Build action array - Create each action dictionary with identifier and parameters
  4. Wire variable references - Connect outputs to inputs using OutputUUID
  5. Wrap in plist - Add the root structure with icon, name, version
  6. Write to file - Save as .shortcut (XML plist format is fine)
  7. Sign - Run shortcuts sign to make it importable

Key Rules

  1. UUIDs must be uppercase: A1B2C3D4-E5F6-7890-ABCD-EF1234567890
  2. WFControlFlowMode is an integer: Use <integer>0</integer> not <string>0</string>
  3. Range keys use format: {position, length} - e.g., {0, 1} for first character
  4. The placeholder character:  (U+FFFC) marks where variables are inserted
  5. Control flow needs matching ends: Every repeat/if/menu start needs an end action with same GroupingIdentifier

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 Shortcuts Generator AI skill do?

Generate macOS/iOS Shortcuts by creating plist files. Use when asked to create shortcuts, automate workflows, build .shortcut files, or generate Shortcuts plists. Covers 1,155 actions (427 WF*Actions + 728 AppIntents), variable references, and control flow.

Why use Shortcuts Generator on TypingMind?

Because you install it once and use it with any model. Shortcuts Generator 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 Shortcuts Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/drewocarr/generate-shortcuts-skill/tree/main. 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 Shortcuts Generator?

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 Shortcuts Generator?

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

Is the Shortcuts Generator AI skill free?

It is published on GitHub by drewocarr. 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 👇