Goey Toast logo

Goey Toast

CommunityPopular
anl331
goey-toast

Install and use goey-toast — a gooey, morphing React toast component built on Sonner with Framer Motion. Use when adding toast/notification UI to a React app (success/error/warning/info/promise toasts), or when the user mentions goey-toast / gooey toast.

Overview

Publisheranl331
Repositorygoey-toast
Skill namegoey-toast
Stars
1.3K
Forks
56
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anl331 on GitHub. Read the source before you install it.

Installation

Install the Goey Toast 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.
  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/anl331/goey-toast.git /tmp/goey-toast
mkdir -p .claude/skills
cp -r /tmp/goey-toast/skills/goey-toast .claude/skills/goey-toast
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Goey Toast 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 Goey Toast 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 Goey Toast 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.

goey-toast

A gooey, morphing React toast component built on Sonner with Framer Motion animations (pill → blob → pill). Use this skill to install the package and write correct usage code in any React project.

When to use

  • Adding toast / notification UI to a React app (React >= 18).
  • The user mentions "goey-toast", "gooey toast", or wants animated/morphing toasts.
  • Replacing raw sonner toasts with the gooey variant.

Install

bash
npm install goey-toast react react-dom framer-motion

Peer deps (must exist in the host app):

PackageVersion
react>= 18.0.0
react-dom>= 18.0.0
framer-motion>= 10.0.0

shadcn/ui projects

bash
npx shadcn@latest add https://goey-toast.vercel.app/r/goey-toaster.json

Installs a wrapper at components/ui/goey-toaster.tsx and auto-installs deps.

Two required steps to render toasts

  1. Mount <GooeyToaster /> once near the app root.
  2. Import the stylesheet once at the entry point. Without it toasts render unstyled.
tsx
import { GooeyToaster, gooeyToast } from 'goey-toast'
import 'goey-toast/styles.css' // REQUIRED — import once at app entry

function App() {
  return (
    <>
      <GooeyToaster position="bottom-right" />
      <button onClick={() => gooeyToast.success('Saved!')}>Save</button>
    </>
  )
}

API: gooeyToast

ts
gooeyToast(title, options?)         // default (neutral)
gooeyToast.success(title, options?) // green
gooeyToast.error(title, options?)   // red
gooeyToast.warning(title, options?) // yellow
gooeyToast.info(title, options?)    // blue
gooeyToast.promise(promise, data)   // loading → success/error
gooeyToast.update(id, options)      // update an existing toast in-place
gooeyToast.dismiss(idOrFilter?)     // dismiss one, by type, or all

Common options (2nd arg)

OptionTypeNotes
descriptionReactNodeString or component body
actionGooeyToastAction{ label, onClick, successLabel? }
iconReactNodeCustom icon (null clears in update)
durationnumberms
idstring | numberStable id (needed for update)
fillColor / borderColor / borderWidthcolors / pxBlob styling
spring / bounceboolean / numberbounce 0.050.8, default 0.4
preset'smooth' | 'bouncy' | 'subtle' | 'snappy'Animation preset
showProgressbooleanCountdown bar
showTimestampbooleanDefault true
onDismiss / onAutoClose(id) => voidDismiss callbacks

<GooeyToaster /> key props

position ('top-left'|'top-center'|'top-right'|'bottom-left'|'bottom-center'|'bottom-right', default 'bottom-right'), theme ('light'|'dark'), closeButton, showProgress, closeOnEscape, maxQueue, queueOverflow ('drop-oldest'|'drop-newest'), dir ('ltr'|'rtl'), spring, bounce, preset, swipeToDismiss, showTimestamp, gap, offset.

Recipes

Description + action button

tsx
gooeyToast.info('Share link ready', {
  description: 'Your link has been generated.',
  action: {
    label: 'Copy',
    onClick: () => navigator.clipboard.writeText(url),
    successLabel: 'Copied!', // morphs back to pill after click
  },
})

Promise toast

tsx
gooeyToast.promise(saveData(), {
  loading: 'Saving...',
  success: (data) => `Saved ${data.count} items`,
  error: (e) => `Failed: ${String(e)}`,
  description: { success: 'All changes synced.', error: 'Try again later.' },
  action: { error: { label: 'Retry', onClick: () => retry() } },
})

Update in place

tsx
const id = gooeyToast('Uploading...', { icon: <Spinner /> })
gooeyToast.update(id, { title: 'Done', type: 'success', icon: null })

Dismiss by filter

tsx
gooeyToast.dismiss(id)                       // one
gooeyToast.dismiss({ type: 'error' })        // all errors
gooeyToast.dismiss({ type: ['error','warning'] })
gooeyToast.dismiss()                         // all

Gotchas

  • Forgetting import 'goey-toast/styles.css' → unstyled toasts. Most common bug.
  • <GooeyToaster /> must be mounted exactly once, near the root.
  • update() requires the same id returned from the create call.
  • framer-motion is a peer dep — install it explicitly.
  • Backward-compat aliases exist (GoeyToaster, goeyToast) for v0.2.x; prefer the double-o names (GooeyToaster, gooeyToast).

Reference

Frequently asked questions

What does the Goey Toast AI skill do?

Install and use goey-toast — a gooey, morphing React toast component built on Sonner with Framer Motion. Use when adding toast/notification UI to a React app (success/error/warning/info/promise toasts), or when the user mentions goey-toast / gooey toast.

Why use Goey Toast on TypingMind?

Because you install it once and use it with any model. Goey Toast 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 Goey Toast in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anl331/goey-toast/tree/main/skills/goey-toast. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Goey Toast?

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 Goey Toast?

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

Is the Goey Toast AI skill free?

Yes. It is published on GitHub by anl331 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 👇