Directives logo

Directives

OrganizationPopular
vercel-labs
directives

Pre-built custom directives for json-render — formatting, math, string manipulation, and i18n. Use when working with @json-render/directives, defining custom directives with defineDirective, or adding $format, $math, $concat, $count, $truncate, $pluralize, $join, or $t to specs.

Overview

Publishervercel-labs
Repositoryjson-render
Skill namedirectives
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 Directives 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/directives .claude/skills/directives
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Directives 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 Directives 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 Directives 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/directives

Pre-built custom directives for @json-render/core. Drop them into your catalog and renderer to add formatting, math, string manipulation, and i18n.

Quick Start

typescript
import { standardDirectives } from '@json-render/directives';

// Wire into prompt generation
const prompt = catalog.prompt({ directives: standardDirectives });

// Wire into the renderer (React example)
import { JSONUIProvider, Renderer } from '@json-render/react';

<JSONUIProvider registry={registry} directives={standardDirectives}>
  <Renderer spec={spec} registry={registry} />
</JSONUIProvider>

To add factory directives like createI18nDirective, spread the array:

typescript
import { standardDirectives, createI18nDirective } from '@json-render/directives';

const directives = [...standardDirectives, createI18nDirective(config)];

Defining Custom Directives

Use defineDirective from @json-render/core:

typescript
import { defineDirective, resolvePropValue } from '@json-render/core';
import { z } from 'zod';

const doubleDirective = defineDirective({
  name: '$double',
  description: 'Double a numeric value.',
  schema: z.object({
    $double: z.unknown(),
  }),
  resolve(value, ctx) {
    const resolved = resolvePropValue(value.$double, ctx);
    return (resolved as number) * 2;
  },
});

Rules:

  • Name must start with $
  • Name must not conflict with built-in keys ($state, $cond, $computed, $template, $item, $index, $bindState, $bindItem)
  • Resolvers should call resolvePropValue on sub-values to support composition

Built-in Directives

$format — Locale-aware value formatting

Formats values using Intl formatters. Supports date, currency, number, and percent.

json
{ "$format": "currency", "value": { "$state": "/cart/total" }, "currency": "USD" }
{ "$format": "date", "value": { "$state": "/user/createdAt" } }
{ "$format": "number", "value": 1234567, "notation": "compact" }
{ "$format": "percent", "value": 0.75 }
{ "$format": "date", "value": { "$state": "/post/createdAt" }, "style": "relative" }

Fields: $format (date | currency | number | percent), value (any expression), locale? (string), currency? (string, default "USD"), notation? (string), style? ("relative" for relative dates), options? (extra Intl options).

$math — Arithmetic operations

json
{ "$math": "add", "a": { "$state": "/subtotal" }, "b": { "$state": "/tax" } }
{ "$math": "round", "a": 3.7 }

Operations: add, subtract, multiply, divide, mod, min, max, round, floor, ceil, abs. Unary ops (round, floor, ceil, abs) only use a. Division by zero returns 0.

Fields: $math (operation enum), a? (first operand, default 0), b? (second operand, default 0).

$concat — String concatenation

json
{ "$concat": [{ "$state": "/user/firstName" }, " ", { "$state": "/user/lastName" }] }

Fields: $concat (array of values to resolve and join into a string).

$count — Array/string length

json
{ "$count": { "$state": "/cart/items" } }

Returns .length of arrays or strings, 0 for other types.

Fields: $count (value to count).

$truncate — Text truncation

json
{ "$truncate": { "$state": "/post/body" }, "length": 140, "suffix": "..." }

Fields: $truncate (value to truncate), length? (max chars, default 100), suffix? (string, default "...").

$pluralize — Singular/plural forms

json
{ "$pluralize": { "$state": "/cart/itemCount" }, "one": "item", "other": "items", "zero": "no items" }

Output: "3 items", "1 item", or "no items".

Fields: $pluralize (count value), one (singular label), other (plural label), zero? (zero label).

$join — Join array elements

json
{ "$join": { "$state": "/tags" }, "separator": ", " }

Fields: $join (array to join), separator? (string, default ", ").

createI18nDirective — Internationalization factory

typescript
import { createI18nDirective } from '@json-render/directives';

const tDirective = createI18nDirective({
  locale: 'en',
  messages: {
    en: { "greeting": "Hello, {{name}}!", "checkout.submit": "Place Order" },
    es: { "greeting": "Hola, {{name}}!", "checkout.submit": "Realizar Pedido" },
  },
  fallbackLocale: 'en',
});

Usage in specs:

json
{ "$t": "checkout.submit" }
{ "$t": "greeting", "params": { "name": { "$state": "/user/name" } } }

Fields: $t (translation key), params? (interpolation parameters, values accept expressions).

Config: locale (current locale), messages (Record<locale, Record<key, string>>), fallbackLocale? (fallback when key missing).

Composition

Directives compose naturally — each resolver calls resolvePropValue on its inputs, so directives can wrap other directives or built-in expressions:

json
{
  "$format": "currency",
  "value": { "$math": "multiply", "a": { "$state": "/price" }, "b": { "$state": "/qty" } },
  "currency": "USD"
}

Resolves inside-out: $state reads from state, $math multiplies, $format formats as currency.

Wiring into Renderers

All four renderers (React, Vue, Svelte, Solid) accept directives on their provider and createRenderer output:

tsx
// Provider pattern
<JSONUIProvider registry={registry} directives={directives}>
  <Renderer spec={spec} registry={registry} />
</JSONUIProvider>

// createRenderer pattern
const MyRenderer = createRenderer(catalog, components);
<MyRenderer spec={spec} directives={directives} />

For prompt generation, pass the same array:

typescript
const prompt = catalog.prompt({ directives });

Key Exports

ExportPurpose
formatDirective$format directive definition
mathDirective$math directive definition
concatDirective$concat directive definition
countDirective$count directive definition
truncateDirective$truncate directive definition
pluralizeDirective$pluralize directive definition
joinDirective$join directive definition
createI18nDirectiveFactory for $t i18n directive
standardDirectivesArray of all 7 non-factory directives
I18nConfigType for i18n configuration

Frequently asked questions

What does the Directives AI skill do?

Pre-built custom directives for json-render — formatting, math, string manipulation, and i18n. Use when working with @json-render/directives, defining custom directives with defineDirective, or adding $format, $math, $concat, $count, $truncate, $pluralize, $join, or $t to specs.

Why use Directives on TypingMind?

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

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

Which AI models can use Directives?

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 Directives?

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

Is the Directives 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 👇