Create Apple Notes Mockup logo

Create Apple Notes Mockup

OrganizationPopular
gooseworks-ai
create-apple-notes-mockup

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

Overview

Publishergooseworks-ai
Repositorygoose-skills
Skill namecreate-apple-notes-mockup
Stars
1.2K
Forks
216
Bundled files
20
LicenseMIT
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.

  • 20 bundled files

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

  • Open source

    Published by gooseworks-ai on GitHub. Read the source before you install it.

Installation

Install the Create Apple Notes Mockup 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/gooseworks-ai/goose-skills/tree/main/skills/ads/packs/video-ad-formats/create-apple-notes-mockup
  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/gooseworks-ai/goose-skills.git /tmp/goose-skills
mkdir -p .claude/skills
cp -r /tmp/goose-skills/skills/ads/packs/video-ad-formats/create-apple-notes-mockup .claude/skills/create-apple-notes-mockup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Apple Notes Mockup 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 Create Apple Notes Mockup 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 Create Apple Notes Mockup 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.

Superseded: the video kit now does this with the phone-chat part, version 1.2.0, in the parts folder of this repository. Every phone-chat style is a style file that draws the same screen frame by frame from the plan's scenes, with the original sounds, in the kit's browser. This atom stays, unchanged in behaviour, for skills outside the kit until they move; its scripts still run.

create-apple-notes-mockup

Generate Apple Notes screens that look like real iPhone screenshots — correct status bar, floating toolbar pill, bold title, body text with paragraph spacing, yellow text cursor, autocorrect underline, optional embedded images and checklists, and an optional iOS keyboard.

Purpose

Turn a JSON note spec into a pixel-accurate Apple Notes (iPhone, light mode) screenshot — HTML + PNG at the native 1180×2556 (DPR 2). It is the deterministic, no-LLM renderer that the create-apple-notes-video-ad molecule drives frame-by-frame to fake a typing animation, and a standalone tool for one-off "noted to self" beats in ads, social posts, and storyboards. The orchestrating agent owns the copy; this atom owns the fidelity (status bar, smart punctuation, cursor, autocorrect underline, toolbar, keyboard chrome).

When to use

  • Need a fake Apple Notes screenshot for an ad, social post, video scene, or product mockup.
  • Need a sequence of Apple Notes frames (title-only → adding paragraphs → cursor moves) to drive a typing-animation video — used by create-apple-notes-video-ad.
  • Need a static "noted to self" beat in a storyboard.

If you're rendering an iMessage thread, use skills/atoms/messaging/create-imessage-mockup instead.

Inputs

The skill is deterministic — it does not embed an LLM. The orchestrating agent composes a note JSON matching the schema below, then invokes the renderer.

Note JSON schema

json
{
  "title": "Hello",
  "body": [
    { "type": "paragraph", "text": "This is a screen recording of me typing on apple notes app." },
    { "type": "paragraph", "text": "Let's see how this feels." }
  ],
  "cursor": "end",
  "autocorrect_underline": ["this", "how"],
  "status_bar": {
    "time": "9:41",
    "battery_pct": 87,
    "battery_low": false,
    "show_focus_glyph": false
  },
  "show_keyboard": false,
  "keyboard_state": {
    "suggestions": ["see", "go", "do"],
    "shift": "lower",
    "letters_row1": "qwertyuiop",
    "letters_row2": "asdfghjkl",
    "letters_row3": "zxcvbnm"
  },
  "with_iphone_frame": false
}
  • title — string. Bold display headline, single line.
  • body[] — block list. Supported block types:
    • paragraph — { "text": "..." }. Smart punctuation is auto-applied (' → ', " → ", ... → …, -- → –, --- → —).
    • image — { "src": "<path|url>", "caption": "optional" }. Relative paths are resolved against the spec file's directory and inlined as data URIs. examples/with-image.json uses a placeholder src; point it at an image of your own before rendering.
    • checklist — { "items": [{ "text": "...", "checked": true|false }] }. Checked items get yellow filled circles with strikethrough; unchecked get gray-outlined circles.
    • divider — horizontal rule.
  • cursor — "title" | "end" | null. "title" places the yellow caret at the end of the title; "end" places it at the end of the last paragraph; null hides it.
  • autocorrect_underline[] — exact-case word list. Each occurrence gets the Apple Notes mid-typing yellow underline (<span class="spell">).
  • status_bar — time, battery_pct (0–100), battery_low (color battery red), show_focus_glyph (DND/car icon next to time). The Dynamic Island is not rendered.
  • show_keyboard — true overlays the iOS QWERTY + formatting toolbar.
  • keyboard_state — only consulted when show_keyboard is true. shift = "lower" | "upper".
  • with_iphone_frame — adds a thin dark bezel inset (for hero compositions).

CLI

bash
node render.js --note examples/mid.json
node render.js --note examples/long.json --output ./my-exports/ --name todays-note
node render.js --note my-note.json --with-keyboard
node render.js --note my-note.json --viewport 1080x1920   # 9:16 ad delivery size

Flags

FlagEffect
--note <path>(required) JSON file matching the schema above
--with-keyboardforce-enables show_keyboard (overrides spec)
--with-iphone-frameforce-enables hardware bezel
--no-frameforce-disables hardware bezel
--output <dir>parent dir for the dated output folder; default ./apple-notes-mockup-exports/
--name <slug>override the output folder slug
--out-html <path> / --out-png <path>write directly to explicit paths (skip dated folder)
--viewport WxHoverride the render viewport (default 1180x2556)
--dpr Ndevice-pixel ratio (default 2)

Output

<output>/<YYYY-MM-DD>-<slug>/
  index.html       # full standalone HTML (images inlined as data URIs)
  screenshot.png   # rendered PNG at the chosen viewport × DPR
  spec.json        # copy of the input for reproducibility

Default <output> is ./apple-notes-mockup-exports/ in the cwd.

Workflow

  1. Receive a prompt or existing note JSON.
  2. If only a prompt was given: compose a note.json matching the schema, save it.
  3. Run node render.js --note <path> [--with-keyboard].
  4. Open the resulting PNG to verify the layout. If something looks wrong (wrong wrap, wrong cursor position, wrong battery color), edit the JSON and re-render.

Setup (one-time)

bash
cd create-apple-notes-mockup
npm install
npx playwright install chromium

A symlink to create-imessage-mockup/node_modules ships with the repo, so on a fresh clone npm install is only needed if you want this skill to be self-contained.

Files

FilePurpose
render.jsCLI entry — parses flags, resolves image paths, generates HTML, takes screenshot
generate.jsNote JSON → standalone HTML page (smart-punctuation + autocorrect underline applied here)
screenshot.jsHTML → PNG via Playwright (chromium headless) at 1180×2556, DPR 2
templates/note.cssAll visual styling (status bar, toolbar, body, checklist, image, keyboard)
templates/icons.jsInline SVG icons (back chevron, undo, share, more, done check, signal, wifi, battery, format toolbar icons, keyboard glyphs)
examples/*.json6 reference notes covering every variation (title-only, mid-typing, long multi-paragraph, with checklist, with image, frame-1 lowercase-keyboard)
tests/run-all.shRender every example into tests/output/ for visual review
apple-notes-skill-build.htmlSide-by-side review board comparing reference video frames to generated PNGs

Quality Checks

Before declaring a note shippable:

  • Title renders as bold display headline, not regular weight.
  • Body text uses Apple's smart punctuation — ' is curly, " is curly, … is a single character.
  • Yellow cursor (#FFCC00) sits flush at the end of the target text, ~5px wide.
  • Body paragraphs are separated by one empty visual line (no manual <br>).
  • Autocorrect underlines are short yellow lines flush under the flagged token, with case-sensitive matching.
  • Status bar: time left, signal/wifi/battery right. Battery is red iff battery_low: true. No Dynamic Island.
  • Scroll mask: status bar and toolbar have opaque white backgrounds so body content scrolled by the molecule's driver doesn't bleed through. Verify by translating .note by -300px in DevTools and confirming the title is fully masked by the toolbar — not visible behind/through it.
  • Toolbar: floating back-chevron pill (left), white capsule with undo/share/more, yellow Done circle (right). All cast soft shadows.
  • Keyboard (when enabled): QWERTY layout matches shift casing, suggestion strip shows 3 words, formatting toolbar pill above keys, mic + globe at bottom.
  • Image blocks render with rounded corners (~18px) and respect the body left padding.
  • Checklist: filled yellow circles + strikethrough on checked items; gray outline circles otherwise.

Failure Modes

SymptomCauseFix
Body text wraps a word too early or too lateFont width differs from reference (Chromium picked up a non-SF fallback)Adjust font-size on .note-body in steps of 2px, or widen .note by reducing left/right padding
Title looks thin / not bold enoughHost doesn't have SF Pro Display; system falls back to a lighter faceSet font-weight: 900 (already the default) and check `fc-list
"Hello's", "Let's" render with straight quoteSmart-punctuation pre-processor disabledVerify smartQuotes() is called in generate.js before escapeHtml
Image doesn't render (blank space)Remote URL blocked or relative path didn't resolveUse a local file path; render.js inlines local images as base64
Autocorrect underline also matches "This" when only "this" was intendedRegex was case-insensitiveThe regex is case-sensitive by default. Pass exact-case strings in autocorrect_underline
Empty paragraph collapses (no cursor space)<p class="note-paragraph"></p> with no content has zero heightThe CSS sets margin: 0 0 84px 0 so an empty paragraph still occupies one paragraph gap; ensure you didn't strip the trailing margin
Yellow Done circle looks orangeCSS color driftPure Apple yellow is #FFCC00. Cursor + Done share the value; do not change to #FFC107 (Material amber)
Keyboard suggestion Hello's renders with straight apostropheSmart quotes not applied to suggestionsConfirmed applied via smartQuotes(s) in generate.js

Reference

The visual spec was extracted from apple-notes-typing.MP4 (a 36-second iPhone screen recording of typing into Apple Notes in light mode). See apple-notes-skill-build.html in this folder for the side-by-side proof — each example is shown alongside the reference frame it targets.

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 Create Apple Notes Mockup AI skill do?

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

Why use Create Apple Notes Mockup on TypingMind?

Because you install it once and use it with any model. Create Apple Notes Mockup 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 Create Apple Notes Mockup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gooseworks-ai/goose-skills/tree/main/skills/ads/packs/video-ad-formats/create-apple-notes-mockup. 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 Create Apple Notes Mockup?

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 Create Apple Notes Mockup?

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

Is the Create Apple Notes Mockup AI skill free?

Yes. It is published on GitHub by gooseworks-ai under the MIT license. 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 👇