Vue logo

Vue

OrganizationPopular
vercel-labs
vue

Vue 3 renderer for json-render. Use when building Vue UIs from JSON specs, working with @json-render/vue, defining Vue component registries, or rendering AI-generated specs in Vue.

Overview

Publishervercel-labs
Repositoryjson-render
Skill namevue
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 Vue 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/vue .claude/skills/vue
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vue 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 Vue 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 Vue 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/vue

Vue 3 renderer that converts JSON specs into Vue component trees with data binding, visibility, and actions.

Installation

bash
npm install @json-render/vue @json-render/core zod

Peer dependencies: vue ^3.5.0 and zod ^4.0.0.

Quick Start

Create a Catalog

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

export const catalog = defineCatalog(schema, {
  components: {
    Card: {
      props: z.object({ title: z.string(), description: z.string().nullable() }),
      slots: ["default"],
      description: "A card container",
    },
    Layout: {
      props: z.object({}),
      slots: ["default", "header", "footer"],
      description: "Layout with named content regions",
    },
    Button: {
      props: z.object({ label: z.string(), action: z.string() }),
      description: "A clickable button",
    },
  },
  actions: {},
});

Define Registry with h() Render Functions

typescript
import { h } from "vue";
import { defineRegistry } from "@json-render/vue";
import { catalog } from "./catalog";

export const { registry } = defineRegistry(catalog, {
  components: {
    Card: ({ props, children }) =>
      h("div", { class: "card" }, [
        h("h3", null, props.title),
        props.description ? h("p", null, props.description) : null,
        children,
      ]),
    Layout: ({ slots }) =>
      h("div", null, [
        h("header", null, slots.header?.()),
        h("main", null, slots.default?.()),
        h("footer", null, slots.footer?.()),
      ]),
    Button: ({ props, emit }) =>
      h("button", { onClick: () => emit("press") }, props.label),
  },
});

Named Slots

Use children for the "default" slot. Use the element's top-level slots object for other slot names declared by the catalog:

json
{
  "type": "Layout",
  "props": {},
  "children": ["main"],
  "slots": {
    "header": ["heading"],
    "footer": ["actions"]
  }
}

Registry components receive Vue-native slot functions. Render them with slots.header?.(), slots.footer?.(), and so on. slots.default?.() renders the spec's children; the children context field is a convenience alias for that rendered result. In the JSON spec, keep default content in children rather than adding a default entry to slots.

Render Specs

vue
<script setup lang="ts">
import { StateProvider, ActionProvider, Renderer } from "@json-render/vue";
import { registry } from "./registry";

const spec = { root: "card-1", elements: { /* ... */ } };
</script>

<template>
  <StateProvider :initial-state="{ form: { name: '' } }">
    <ActionProvider :handlers="{ submit: handleSubmit }">
      <Renderer :spec="spec" :registry="registry" />
    </ActionProvider>
  </StateProvider>
</template>

Providers

ProviderPurpose
StateProviderShare state across components (JSON Pointer paths). Accepts initialState or store for controlled mode.
ActionProviderHandle actions dispatched via the event system
VisibilityProviderEnable conditional rendering based on state
ValidationProviderForm field validation

Composables

ComposablePurpose
useStateStore()Access state context (state as ShallowRef, get, set, update)
useStateValue(path)Get single value from state
useIsVisible(condition)Check if a visibility condition is met
useActions()Access action context
useAction(binding)Get a single action dispatch function
useFieldValidation(path, config)Field validation state
useBoundProp(propValue, bindingPath)Two-way binding for $bindState/$bindItem

Note: useStateStore().state returns a ShallowRef<StateModel> — use state.value to access.

External Store (StateStore)

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

Pass a StateStore to StateProvider to wire json-render to Pinia, VueUse, or any state management:

typescript
import { createStateStore, type StateStore } from "@json-render/vue";

const store = createStateStore({ count: 0 });
vue
<StateProvider :store="store">
  <Renderer :spec="spec" :registry="registry" />
</StateProvider>

Dynamic Prop Expressions

Props support $state, $bindState, $cond, $template, $computed. Use { "$bindState": "/path" } on the natural value prop for two-way binding.

Visibility Conditions

typescript
{ "$state": "/user/isAdmin" }
{ "$state": "/status", "eq": "active" }
{ "$state": "/maintenance", "not": true }
[ cond1, cond2 ]  // implicit AND

Built-in Actions

setState, pushState, removeState, and validateForm are built into the Vue schema and handled by ActionProvider:

json
{
  "action": "setState",
  "params": { "statePath": "/activeTab", "value": "settings" }
}

Event System

Components use emit(event) to fire events, or on(event) for metadata (shouldPreventDefault, bound).

Streaming

useUIStream and useChatUI return Vue Refs for streaming specs from an API.

BaseComponentProps

For catalog-agnostic reusable components:

typescript
import type { BaseComponentProps } from "@json-render/vue";

const Card = ({ props, children }: BaseComponentProps<{ title?: string }>) =>
  h("div", null, [props.title, children]);

Key Exports

ExportPurpose
defineRegistryCreate a type-safe component registry from a catalog
RendererRender a spec using a registry
schemaElement tree schema (from @json-render/vue/schema)
StateProvider, ActionProvider, VisibilityProvider, ValidationProviderContext providers
useStateStore, useStateValue, useBoundPropState composables
useActions, useActionAction composables
useFieldValidation, useIsVisibleValidation and visibility
useUIStream, useChatUIStreaming composables
createStateStoreCreate in-memory StateStore
BaseComponentPropsCatalog-agnostic component props type

Frequently asked questions

What does the Vue AI skill do?

Vue 3 renderer for json-render. Use when building Vue UIs from JSON specs, working with @json-render/vue, defining Vue component registries, or rendering AI-generated specs in Vue.

Why use Vue on TypingMind?

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

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

Which AI models can use Vue?

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 Vue?

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

Is the Vue 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 👇