Svelte logo

Svelte

OrganizationPopular
vercel-labs
svelte

Svelte 5 renderer for json-render that turns JSON specs into Svelte component trees. Use when working with @json-render/svelte, building Svelte UIs from JSON, creating component catalogs, or rendering AI-generated specs.

Overview

Publishervercel-labs
Repositoryjson-render
Skill namesvelte
Stars
16.5K
Forks
887
Bundled files
Instructions only
LicenseApache-2.0
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 vercel-labs on GitHub. Read the source before you install it.

Installation

Install the Svelte 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/vercel-labs/json-render.git /tmp/json-render
mkdir -p .claude/skills
cp -r /tmp/json-render/skills/svelte .claude/skills/svelte
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Svelte 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 Svelte 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 Svelte 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.

@json-render/svelte

Svelte 5 renderer that converts json-render specs into Svelte component trees.

Quick Start

svelte
<script lang="ts">
  import { Renderer, JsonUIProvider } from "@json-render/svelte";
  import type { Spec } from "@json-render/svelte";
  import Card from "./components/Card.svelte";
  import Button from "./components/Button.svelte";

  interface Props {
    spec: Spec | null;
  }

  let { spec }: Props = $props();
  const registry = { Card, Button };
</script>

<JsonUIProvider>
  <Renderer {spec} {registry} />
</JsonUIProvider>

Creating a Catalog

typescript
import { defineCatalog } from "@json-render/core";
import { schema } from "@json-render/svelte";
import { z } from "zod";

export const catalog = defineCatalog(schema, {
  components: {
    Button: {
      props: z.object({
        label: z.string(),
        variant: z.enum(["primary", "secondary"]).nullable(),
      }),
      description: "Clickable button",
    },
    Card: {
      props: z.object({ title: z.string() }),
      description: "Card container with title",
    },
  },
});

Defining Components

Components should accept BaseComponentProps<TProps>:

typescript
interface BaseComponentProps<TProps> {
  props: TProps; // Resolved props for this component
  children?: Snippet; // Child elements (use {@render children()})
  emit: (event: string) => void; // Fire a named event
  bindings?: Record<string, string>; // Map of prop names to state paths (for $bindState)
  loading?: boolean; // True while spec is streaming
}
svelte
<!-- Button.svelte -->
<script lang="ts">
  import type { BaseComponentProps } from "@json-render/svelte";

  interface Props extends BaseComponentProps<{ label: string; variant?: string }> {}
  let { props, emit }: Props = $props();
</script>

<button class={props.variant} onclick={() => emit("press")}>
  {props.label}
</button>
svelte
<!-- Card.svelte -->
<script lang="ts">
  import type { Snippet } from "svelte";
  import type { BaseComponentProps } from "@json-render/svelte";

  interface Props extends BaseComponentProps<{ title: string }> {
    children?: Snippet;
  }

  let { props, children }: Props = $props();
</script>

<div class="card">
  <h2>{props.title}</h2>
  {#if children}
    {@render children()}
  {/if}
</div>

Creating a Registry

typescript
import { defineRegistry } from "@json-render/svelte";
import { catalog } from "./catalog";
import Card from "./components/Card.svelte";
import Button from "./components/Button.svelte";

const { registry, handlers, executeAction } = defineRegistry(catalog, {
  components: {
    Card,
    Button,
  },
  actions: {
    submit: async (params, setState, state) => {
      // handle action
    },
  },
});

Spec Structure (Element Tree)

The Svelte schema uses the element tree format:

json
{
  "root": "card1",
  "elements": {
    "card1": {
      "type": "Card",
      "props": { "title": "Hello" },
      "children": ["btn1"]
    },
    "btn1": {
      "type": "Button",
      "props": { "label": "Click me" }
    }
  }
}

Visibility Conditions

Use visible on elements to show/hide based on state:

  • { "$state": "/path" } - truthy check
  • { "$state": "/path", "eq": value } - equality check
  • { "$state": "/path", "not": true } - falsy check
  • { "$and": [cond1, cond2] } - AND conditions
  • { "$or": [cond1, cond2] } - OR conditions

Providers (via JsonUIProvider)

JsonUIProvider composes all contexts. Individual contexts:

ContextPurpose
StateContextShare state across components (JSON Pointer paths)
ActionContextHandle actions dispatched via the event system
VisibilityContextEnable conditional rendering based on state
ValidationContextForm field validation

Event System

Components use emit to fire named events. The element's on field maps events to action bindings:

svelte
<!-- Button.svelte -->
<script lang="ts">
  import type { BaseComponentProps } from "@json-render/svelte";

  interface Props extends BaseComponentProps<{ label: string }> {}

  let { props, emit }: Props = $props();
</script>

<button onclick={() => emit("press")}>{props.label}</button>
json
{
  "type": "Button",
  "props": { "label": "Submit" },
  "on": { "press": { "action": "submit" } }
}

Built-in Actions

The setState action is handled automatically and updates the state model:

json
{
  "action": "setState",
  "actionParams": { "statePath": "/activeTab", "value": "home" }
}

Other built-in actions: pushState, removeState, push, pop.

Dynamic Props and Two-Way Binding

Nested lists can set repeat.statePath to { "$item": "field" } inside an enclosing repeat.

Expression forms resolved before your component receives props:

  • {"$state": "/state/key"} - read from state
  • {"$bindState": "/form/email"} - read + write-back to state
  • {"$bindItem": "field"} - read + write-back for repeat items
  • {"$cond": <condition>, "$then": <value>, "$else": <value>} - conditional value

For writable bindings inside components, use getBoundProp:

svelte
<script lang="ts">
  import { getBoundProp } from "@json-render/svelte";
  import type { BaseComponentProps } from "@json-render/svelte";

  interface Props extends BaseComponentProps<{ value?: string }> {}
  let { props, bindings }: Props = $props();

  let value = getBoundProp<string>(
    () => props.value,
    () => bindings?.value,
  );
</script>

<input bind:value={value.current} />

Context Helpers

Preferred helpers:

  • getStateValue(path) - returns { current } (read/write)
  • getBoundProp(() => value, () => bindingPath) - returns { current } (read/write when bound)
  • isVisible(condition) - returns { current } (boolean)
  • getAction(name) - returns { current } (registered handler)

Advanced context access:

  • getStateContext()
  • getActionContext()
  • getVisibilityContext()
  • getValidationContext()
  • getOptionalValidationContext()
  • getFieldValidation(ctx, path, config?)

Streaming UI

Use createUIStream for spec streaming:

svelte
<script lang="ts">
  import { createUIStream, Renderer } from "@json-render/svelte";

  const stream = createUIStream({
    api: "/api/generate-ui",
    onComplete: (spec) => console.log("Done", spec),
  });

  async function generate() {
    await stream.send("Create a login form");
  }
</script>

<button onclick={generate} disabled={stream.isStreaming}>
  {stream.isStreaming ? "Generating..." : "Generate UI"}
</button>

{#if stream.spec}
  <Renderer spec={stream.spec} {registry} loading={stream.isStreaming} />
{/if}

Use createChatUI for chat + UI responses:

typescript
const chat = createChatUI({ api: "/api/chat-ui" });
await chat.send("Build a settings panel");

Frequently asked questions

What does the Svelte AI skill do?

Svelte 5 renderer for json-render that turns JSON specs into Svelte component trees. Use when working with @json-render/svelte, building Svelte UIs from JSON, creating component catalogs, or rendering AI-generated specs.

Why use Svelte on TypingMind?

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

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

Which AI models can use Svelte?

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 Svelte?

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

Is the Svelte AI skill free?

Yes. It is published on GitHub by vercel-labs under the Apache-2.0 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 👇