Import Export logo

Import Export

OrganizationPopular
live-codes
import-export

Import code from GitHub gists/files/repos, GitLab, URLs, DOM, and local files. Export projects as HTML, JSON, ZIP, or to external services. Load this skill when loading projects from external sources or exporting project state.

Overview

Publisherlive-codes
Repositorylivecodes
Skill nameimport-export
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 Import Export 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/import-export
  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/import-export .claude/skills/import-export
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Import Export 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 Import Export 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 Import Export 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.

LiveCodes — Import and Export Code

LiveCodes imports code from external sources and exports projects in multiple formats.

Setup

javascript
import { createPlayground, getPlaygroundUrl } from 'livecodes';

// Import from URL
const playground = await createPlayground('#container', {
  import: 'https://github.com/user/repo/blob/main/src/index.js',
});

// Import from URL via query param
// https://livecodes.io/?x=https://github.com/user/repo

// Export to shareable URL
const shareUrl = await playground.getShareUrl();
const shortUrl = await playground.getShareUrl(true);

Core Patterns

Import from GitHub

javascript
// GitHub file
createPlayground('#container', {
  import: 'https://github.com/lodash/lodash/blob/master/isObject.js',
});

// GitHub directory
createPlayground('#container', {
  import: 'https://github.com/user/repo/tree/main/src',
});

// GitHub gist
createPlayground('#container', {
  import: 'https://gist.github.com/abc123',
});

// Specify files from multi-file source
createPlayground('#container', {
  import: 'https://github.com/user/repo/tree/main/src',
  params: { files: 'App.tsx,styles.css,index.html' },
});

Import from GitLab

javascript
// GitLab snippet
createPlayground('#container', {
  import: 'https://gitlab.com/-/snippets/12345',
});

// GitLab file
createPlayground('#container', {
  import: 'https://gitlab.com/user/repo/-/blob/main/src/index.js',
});

Import from URL

javascript
// Raw code URL
createPlayground('#container', {
  import: 'https://example.com/code.js',
});

// URL with language specified
createPlayground('#container', {
  params: {
    x: 'https://example.com/code',
    lang: 'typescript', // Force language
  },
});

// Import from Vue/TypeScript playgrounds
createPlayground('#container', {
  import: 'https://play.vuejs.org/#...',
});

Import from shared project

javascript
// Short URL
createPlayground('#container', {
  import: 'id/abc123', // Shared project ID
});

// Compressed config
createPlayground('#container', {
  import: 'code/...', // Compressed base64 config
});

// Via URL
// https://livecodes.io/?x=id/abc123
// https://livecodes.io/?x=code/...

Import from DOM

javascript
// HTML page with code blocks
createPlayground('#container', {
  import: 'https://example.com/blog-post',
});

// HTML must use specific structure:
// <code class="livecodes">
//   <pre data-lang="html">...</pre>
//   <pre data-lang="css">...</pre>
//   <pre data-lang="javascript">...</pre>
// </code>

Import via SDK config

javascript
// Set config with code
await playground.setConfig({
  markup: { language: 'html', content: '<h1>Hello</h1>' },
  style: { language: 'css', content: 'h1 { color: blue; }' },
  script: { language: 'javascript', content: 'console.log("hi")' },
});

// Set config from URL
await playground.setConfig('https://example.com/config.json');

Specify files from multi-file sources

javascript
// When importing directory or gist with multiple files
createPlayground('#container', {
  import: 'https://github.com/user/repo/tree/main/src',
  params: {
    files: 'Counter.tsx,counter.css,index.html',
    active: 'script', // Which editor to show: 'markup', 'style', 'script', or 0, 1, 2
  },
});

Export via SDK

javascript
const playground = await createPlayground('#container', {
  /* ... */
});

// Get share URL
const longUrl = await playground.getShareUrl(); // Long URL with compressed config
const shortUrl = await playground.getShareUrl(true); // Short URL

// Get config to save/export
const config = await playground.getConfig();

Export via URL

# Long URL (compressed config)
https://livecodes.io/#config/...

# Short URL
https://livecodes.io/?x=id/abc123

Common Import Sources

SourceURL PatternNotes
GitHub filegithub.com/user/repo/blob/...Single file
GitHub directorygithub.com/user/repo/tree/...Multiple files
GitHub gistgist.github.com/...Multi-file gists work
GitLab filegitlab.com/user/repo/-/blob/...Single file
GitLab snippetgitlab.com/-/snippets/...Snippet
JS Binjsbin.com/...JS Bin embeds
Vue Playgroundplay.vuejs.org/#...Vue SFC playground
TypeScript Playgroundtypescriptlang.org/play#...TS playground
Raw URLAny URLLanguage auto-detected
Local filesDrag & dropStandalone app only

File Selection Priority

When importing multiple files, LiveCodes prioritizes:

  1. Files named index.*, default.* (markup)
  2. Files named style.*, styles.* (style)
  3. Files named script.*, app.*, main.*, index.* (script)
  4. README and markdown files get lower priority
  5. Use files parameter to explicitly select files

SDK Import Methods

javascript
// Option 1: EmbedOptions.import
createPlayground('#container', {
  import: 'https://github.com/user/repo',
});

// Option 2: Query param x
createPlayground('#container', {
  params: { x: 'https://github.com/user/repo' },
});

// Option 3: URL
// https://livecodes.io/?x=https://github.com/user/repo

// Option 4: setConfig with URL
await playground.setConfig('https://example.com/config.json');

Frequently asked questions

What does the Import Export AI skill do?

Import code from GitHub gists/files/repos, GitLab, URLs, DOM, and local files. Export projects as HTML, JSON, ZIP, or to external services. Load this skill when loading projects from external sources or exporting project state.

Why use Import Export on TypingMind?

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

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

Which AI models can use Import Export?

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 Import Export?

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

Is the Import Export 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 👇