Scripting App Development logo

Scripting App Development

Organization
ScriptingApp
scripting-app-development

Develop, modify, debug, and validate Scripting App projects: TypeScript/TSX scripts, iOS-style pages, native APIs, Widgets, Live Activities, rich notifications, Shortcuts/Share Sheet intents, App Intents, and Safari browser scripts. Uses Scripting's official llms.txt as the API reference entry point.

Overview

PublisherScriptingApp
Repositoryscripting-app-development
Skill namescripting-app-development
Stars
62
Forks
1
Bundled files
33
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.

  • 33 bundled files

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

  • Open source

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

Installation

Install the Scripting App Development 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/ScriptingApp/scripting-app-development/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/ScriptingApp/scripting-app-development.git \
  .claude/skills/scripting-app-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Scripting App Development 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 Scripting App Development 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 Scripting App Development 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.

Scripting App Development

Use this skill to help users create, change, debug, or validate Scripting App script projects. It is a technical development guide; it does not prescribe task planning, spec files, Git workflow, or a generic coding-agent process.

Scope and routing

Use this skill for a Scripting project or any of these files/capabilities:

  • script.json, index.tsx, shared .ts / .tsx modules, and SwiftUI-style TSX pages.
  • widget.tsx, app_intents.tsx, live_activity.tsx, notification.tsx, and intent.tsx.
  • browser.tsx or a separately installed Safari .user.js script.
  • Desktop-editor live sync/debugging with scripting-cli.
  • Scripting-provided iOS APIs such as Notification, Calendar, Location, Photos, Storage, Speech, and Device.
  • Advanced entry points: Home Screen default UI, control widgets, custom keyboard, Spotlight, Translation UI, Assistant Tools, and Alarm Live Activities.

Do not use it as a substitute for creating a standalone Apple Shortcut, ordinary Node/Python automation, or a generic web app.

Mandatory official-documentation workflow

Before writing or changing any Scripting-specific API usage, use the current environment's bundled Scripting reference/API declarations when available (for example, scripting_reference). For desktop agents without that tool, consult the official LLM documentation index:

text
https://scriptingapp.github.io/llms.txt
  1. Search the bundled docs first when available; otherwise search the public index for the exact API, entry point, or capability.
  2. Read the full matching documentation and exact API declarations—not only a search-result summary.
  3. Verify the symbols to be used: import/global module, parameters, result type, async behavior, iOS/version availability, permissions, host constraints, and official example patterns.
  4. Implement only APIs confirmed by the current documentation. Do not infer an API from Swift, React, old examples, or model memory.
  5. If a connected scripting-cli workspace is available, search its app-synced .d.ts declarations to confirm exact local TypeScript signatures/imports; use them with—not instead of—the official documentation's behavior, permission, and host constraints.

Read only the necessary topic reference below. If a local reference conflicts with current official documentation, the official documentation wins.

Start work

New project

  1. Identify the requested host: finite script, in-app page, resident/resumable script, Widget, Live Activity, rich notification, Intent, Safari project script, or installed userscript.
  2. Create a project directory with script.json and index.tsx; use the templates only as a starting point.
  3. Add capability entry files only when requested.
  4. Read references/project-and-lifecycle.md, then the matching capability reference.

Existing project

  1. Read script.json, index.tsx, the requested entry file, and its direct dependencies before modifying code.
  2. Preserve the existing project naming, metadata, entry points, lifecycle, and user configuration unless the requested change requires otherwise.
  3. Make the narrowest compatible change. Do not add unused capabilities or refactor unrelated files.

Project rules

  • A project requires script.json and index.tsx.
  • script.json must include name, icon, color, and version; name normally matches the directory name.
  • Keep shared business logic in regular modules; entry files should adapt that logic to their host environment.
  • Use async / await, handle expected failure paths, and give the user meaningful feedback.
  • For standalone scripting-ts run execution, make sure finite paths call Script.exit(); otherwise the process may wait indefinitely.
  • TSX modifier order affects layout and appearance. When debugging UI, inspect the order of frame, padding, background, clipShape, buttonStyle, contentMargins, and widgetBackground as well as their values.
  • Avoid unbounded vertical layouts inside Grid / ScrollView; validate image-heavy layouts on an actual render.

Lifecycle decision

NeedDesign
Finite work is doneCall Script.exit().
One-time pageawait Navigation.present(...), then Script.exit() after dismissal.
Preserve runtime state or respond to notification/widget/URL re-triggersUse Script.minimize() and Script.onResume(...); do not unconditionally exit.
Return from intent.tsxReturn an appropriate Intent result with Script.exit(value).

Read references/project-and-lifecycle.md before choosing or changing this behavior.

Capability references

User needRead
Project structure, entry files, lifecyclereferences/project-and-lifecycle.md
Standard in-app pagereferences/ios-pages.md
Static or interactive Widget / App Intentreferences/widgets-and-app-intents.md
Live Activity / Dynamic Islandreferences/live-activities.md
Rich notificationreferences/notifications-and-intents.md
Shortcuts / Share Sheetreferences/notifications-and-intents.md
Desktop editor ↔ Scripting App sync/debuggingreferences/desktop-cli.md
Native iOS APIreferences/native-apis.md plus official API page
Safari browser script / userscriptreferences/safari-browser-scripts.md
Keyboard, Home Screen UI, Spotlight, Translation UI, Assistant Tool, Alarm Live Activityreferences/additional-entry-points.md plus exact bundled docs/API declaration

Validation requirements

Read references/validation-and-security.md and use the relevant checklist, including checklists/desktop-live-debug.md when setting up scripting-cli.

  • For desktop live synchronization/debugging, read references/desktop-cli.md; initialize and run scripting-cli only after checking Node.js and confirming any first-time package download/configuration effects. After App connection, consult its synced .d.ts files whenever exact local API typings or component props are needed.
  • Run static diagnostics for changed TypeScript/TSX where available.
  • Run finite index.tsx code with scripting-ts project "<name>" or an equivalent environment command when possible.
  • Preview Widget/UI surfaces when possible; test all target Widget families if layout differs by family.
  • Be explicit about host-only verification: Widget must be added to the Home Screen; Intents require Shortcuts/Share Sheet; rich notifications require a real notification; Live Activities require the Lock Screen/Dynamic Island; Safari scripts require a matching Safari page.
  • Never describe compilation, preview, Widget.present(), or a mock Intent as full system-host verification.

Safety boundary

Before expanding privileges or causing external side effects, describe the impact and get the user's confirmation. This includes sensitive system permissions, reads/writes of user data, cross-origin requests/Cookies/downloads, sending or uploading data, and deleting or bulk-modifying data.

Never hard-code or expose API keys, passwords, tokens, Cookies, private keys, or private user data in source, script.json, logs, screenshots, or sample files. Apply minimum permissions and minimum data access.

Completion response

Summarize only what matters:

  1. files and behavior changed;
  2. lifecycle choice, if relevant;
  3. official documentation topics/API symbols checked;
  4. diagnostics, run, or preview evidence;
  5. exact remaining manual host verification steps;
  6. permissions or side effects introduced.

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 Scripting App Development AI skill do?

Develop, modify, debug, and validate Scripting App projects: TypeScript/TSX scripts, iOS-style pages, native APIs, Widgets, Live Activities, rich notifications, Shortcuts/Share Sheet intents, App Intents, and Safari browser scripts. Uses Scripting's official llms.txt as the API reference entry point.

Why use Scripting App Development on TypingMind?

Because you install it once and use it with any model. Scripting App Development 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 Scripting App Development in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ScriptingApp/scripting-app-development/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 Scripting App Development?

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 Scripting App Development?

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

Is the Scripting App Development AI skill free?

It is published on GitHub by ScriptingApp. 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 👇