Display Modes logo

Display Modes

OrganizationPopular
live-codes
display-modes

Configure how the playground is displayed: full, focus, simple, lite, editor, codeblock, and result modes. Load this skill when choosing display mode for embeddings, configuring read-only views, or showing only result or editor.

Overview

Publisherlive-codes
Repositorylivecodes
Skill namedisplay-modes
Stars
1.5K
Forks
271
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 live-codes on GitHub. Read the source before you install it.

Installation

Install the Display Modes 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/live-codes/livecodes/tree/develop/.agents/skills/livecodes/display-modes
  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/live-codes/livecodes.git /tmp/livecodes
mkdir -p .claude/skills
cp -r /tmp/livecodes/.agents/skills/livecodes/display-modes .claude/skills/display-modes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Display Modes 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 Display Modes 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 Display Modes 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.

This skill builds on configuration. Read it first for foundational concepts.

LiveCodes — Display Modes

Display modes control what UI elements are shown in the playground. Choose mode based on your embedding use case.

Setup

javascript
import { createPlayground } from 'livecodes';

// Via config object
createPlayground('#container', {
  config: { mode: 'simple' },
});

// Via query params
createPlayground('#container', {
  params: { mode: 'result' },
});

// Via URL
// https://livecodes.io/?mode=lite&template=react

Core Patterns

Full mode (default)

Complete playground with toolbars, all editors, result pane.

javascript
// Default mode - no need to specify
createPlayground('#container', {
  template: 'react',
});
// Mode is 'full' by default

Simple mode (embeds)

One editor + result. Ideal for embedded playgrounds with limited space.

javascript
createPlayground('#container', {
  config: {
    mode: 'simple',
    layout: 'vertical', // 'vertical' or 'horizontal'
    activeEditor: 'script',
    editor: 'monaco', // 'monaco' or 'codemirror' (default)
  },
  params: {
    js: 'console.log("Hello")',
    console: 'open',
  },
});

// With style editor
createPlayground('#container', {
  config: {
    mode: 'simple',
    layout: 'vertical',
    activeEditor: 'script',
    editor: 'monaco',
  },
});

Lite mode

Lightweight editor for faster loading. Minimal features.

javascript
createPlayground('#container', {
  config: { mode: 'lite' },
  template: 'react',
});

// Via URL
// https://livecodes.io/?mode=lite&template=react

Lite mode features:

  • Uses CodeJar editor (light-weight)
  • No minimap, no advanced autocomplete
  • Still supports all languages
  • Faster initial load

Editor mode (code only)

No result pane. Shows only the editors.

javascript
createPlayground('#container', {
  config: { mode: 'editor' },
  template: 'react',
});

Use for:

  • Code review interfaces
  • Teaching code patterns
  • Read-only snippet viewers

Codeblock mode (read-only)

Static code display with copy button on hover. No editing.

javascript
createPlayground('#container', {
  config: {
    mode: 'codeblock',
    editor: 'monaco', // Optional: use Monaco instead of CodeJar
  },
  params: { html: '<h1>Hello World</h1>' },
});

Use for:

  • Blog posts with code snippets
  • Documentation
  • One-way code display

Result mode (output only)

Shows only the result page with a drawer to open in full playground.

javascript
createPlayground('#container', {
  params: {
    mode: 'result',
    template: 'react',
  },
});

// Show console in result mode
createPlayground('#container', {
  params: {
    mode: 'result',
    tools: 'console|full',
    js: 'console.log("Hello World")',
  },
});

Use for:

  • Demo showcase
  • Embedded output
  • Presentations

Focus mode

Minimal UI: editors, result, console only. No menus or secondary controls.

javascript
createPlayground('#container', {
  config: { mode: 'focus' },
});

Toggle between focus and full in the app UI. Access via button in bottom-left corner.

Display Mode vs Default View

ConceptWhat it controls
ModeWhat UI elements are loaded
ViewWhich pane is shown by default
javascript
// Mode: 'editor' - Only editors exist, no result pane
createPlayground('#container', {
  config: { mode: 'editor' },
});

// Mode: 'full', View: 'editor' - All UI, editors shown by default
createPlayground('#container', {
  config: {
    mode: 'full', // Full UI
    view: 'editor', // Show editors first
  },
});

Common Mistakes

MEDIUM Confusing mode with view

Wrong:

javascript
// Want to show result by default but use full UI
createPlayground('#container', {
  config: { mode: 'result' }, // Result mode - no editors!
});

Correct:

javascript
// Use view for default visible pane
createPlayground('#container', {
  config: {
    mode: 'full', // Full UI with all elements
    view: 'result', // Show result by default
  },
});

mode determines what elements exist. view determines which element is visible first.

Source: docs/docs/features/display-modes.mdx — Display Mode vs Default View section

MEDIUM Tools not visible in result mode

javascript
// Console won't show in result mode by default
createPlayground('#container', {
  params: {
    mode: 'result',
    js: 'console.log("Hello")',
  },
});

Correct:

javascript
// Set tools to 'open' or 'full' in result mode
createPlayground('#container', {
  params: {
    mode: 'result',
    tools: 'console|full', // Show console in full height
    js: 'console.log("Hello")',
  },
});

In result mode, tools pane is hidden by default. Set tools: 'console|open' or tools: 'console|full' to show it.

Source: docs/docs/features/display-modes.mdx — Result mode section

Mode Reference

ModeShowsUse Case
fullAll UI (default)Full playground experience
focusEditors + result + consoleMinimal distractions
simpleOne editor + resultCompact embeds
liteLightweight editorFast loading, basic editing
editorOnly editorsCode review, teaching
codeblockStatic code with copyRead-only snippets
resultOnly result pageDemo showcase

View Reference

ViewDescription
splitEditors and result side by side (default)
editorEditors visible, result hidden
resultResult visible, editors hidden

Tools Configuration

javascript
const config = {
  tools: {
    enabled: ['console', 'compiled'],  // or 'all'
    active: 'console',    // Which tool is open
    status: 'open',       // 'open', 'full', 'closed', 'none'
  },
};

// Via params
params: {
  tools: 'console|open',     // Console open
  tools: 'compiled|full',     // Compiled code, full height
  console: 'open',            // Shorthand for console
}

Frequently asked questions

What does the Display Modes AI skill do?

Configure how the playground is displayed: full, focus, simple, lite, editor, codeblock, and result modes. Load this skill when choosing display mode for embeddings, configuring read-only views, or showing only result or editor.

Why use Display Modes on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/live-codes/livecodes/tree/develop/.agents/skills/livecodes/display-modes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Display Modes?

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 Display Modes?

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

Is the Display Modes AI skill free?

Yes. It is published on GitHub by live-codes 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 👇