Markdown Integration logo

Markdown Integration

OrganizationPopular
live-codes
markdown-integration

Integrate LiveCodes with documentation sites using remark-livecodes, markdown-it-livecodes, gatsby-remark-livecodes, or marked-livecodes for Docusaurus, Astro, VitePress, Next.js, and Storybook.

Overview

Publisherlive-codes
Repositorylivecodes
Skill namemarkdown-integration
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 Markdown Integration 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/markdown-integration
  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/markdown-integration .claude/skills/markdown-integration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Markdown Integration 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 Markdown Integration 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 Markdown Integration 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 requires sdk-embedding. Read it first for foundational concepts.

LiveCodes — Integrate with Documentation Sites

Convert Markdown/MDX code blocks to interactive LiveCodes playgrounds using plugins for popular documentation frameworks.

Setup

Docusaurus (remark-livecodes)

bash
npm install -D remark-livecodes
javascript
// docusaurus.config.js
module.exports = {
  presets: [
    [
      'classic',
      {
        docs: {
          remarkPlugins: [
            [
              require('remark-livecodes'),
              {
                /* options */
              },
            ],
          ],
        },
      },
    ],
  ],
};

Astro (remark-livecodes)

bash
npm install -D remark-livecodes
javascript
// astro.config.mjs
import { defineConfig } from 'astro/config';
import mdx from '@astrojs/mdx';
import remarkLivecodes from 'remark-livecodes';

export default defineConfig({
  integrations: [mdx()],
  markdown: {
    remarkPlugins: [
      [
        remarkLivecodes,
        {
          /* options */
        },
      ],
    ],
  },
});

VitePress (markdown-it-livecodes)

bash
npm install -D markdown-it-livecodes
javascript
// .vitepress/config.js
import { defineConfig } from 'vitepress';
import markdownItLivecodes from 'markdown-it-livecodes';

export default defineConfig({
  markdown: {
    config: (md) => {
      md.use(markdownItLivecodes, {
        /* options */
      });
    },
  },
});

Next.js (remark-livecodes)

bash
npm install -D remark-livecodes
javascript
// next.config.js
import createMDX from '@next/mdx';
import remarkLivecodes from 'remark-livecodes';

const nextConfig = {
  pageExtensions: ['js', 'jsx', 'md', 'mdx', 'ts', 'tsx'],
};

const withMDX = createMDX({
  options: {
    remarkPlugins: [
      [
        remarkLivecodes,
        {
          /* options */
        },
      ],
    ],
  },
});

export default withMDX(nextConfig);

react-markdown

bash
npm install remark-livecodes
jsx
import Markdown from 'react-markdown';
import remarkLivecodes from 'remark-livecodes';

const markdown = '```jsx livecodes\nexport default () => <h1>Hello</h1>\n```';

<Markdown
  remarkPlugins={[
    [
      remarkLivecodes,
      {
        /* options */
      },
    ],
  ]}
>
  {markdown}
</Markdown>;

Storybook (remark-livecodes)

javascript
// storybook/main.js
import remarkLivecodes from 'remark-livecodes';

export default {
  addons: [
    {
      name: '@storybook/addon-docs',
      options: {
        mdxPluginOptions: {
          mdxCompileOptions: {
            remarkPlugins: [
              [
                remarkLivecodes,
                {
                  /* options */
                },
              ],
            ],
          },
        },
      },
    },
  ],
};

Gatsby (gatsby-remark-livecodes)

bash
npm install -D gatsby-remark-livecodes
javascript
// gatsby-config.js
module.exports = {
  plugins: [
    {
      resolve: 'gatsby-transformer-remark',
      options: {
        plugins: [
          {
            resolve: 'gatsby-remark-livecodes',
            options: {
              /* options */
            },
          },
        ],
      },
    },
  ],
};

Usage

Basic code block → Playground

markdown
```jsx livecodes
import { useState } from 'react';

function App() {
  const [count, setCount] = useState(0);
  return <button onClick={() => setCount((c) => c + 1)}>{count}</button>;
}

export default App;
```

Add livecodes to the code block language to render as an interactive playground.

Button or Link instead of embed

markdown
```jsx livecodes render=button
console.log('Edit in LiveCodes');
```
markdown
```jsx livecodes render=link
console.log('Edit in LiveCodes');
```
renderBehavior
playground (default)Embed playground in page
buttonShow code block + "Edit in LiveCodes" button
linkShow code block + "Edit in LiveCodes" link
metaAdd URL to data-livecodes-url attribute

Options

Configure plugin options to apply to all code blocks:

javascript
remarkPlugins: [
  [remarkLivecodes, {
    // Embed options
    loading: 'lazy',
    params: { console: 'open' },

    // Plugin options
    render: 'playground',  // 'playground' | 'button' | 'link' | 'meta'
    height: '400px',
    className: 'my-playground',
    auto: false,  // Auto-enable for all code blocks
  }],
],

Meta Parameters

Configure individual code blocks with meta parameters:

markdown
```jsx livecodes height=500px console=open theme=light
console.log('Hello World');
```
ParameterDescription
livecodesEnable playground rendering
renderRender mode: playground, button, link, meta
heightIframe height
classNameCSS class for iframe/button/link
langOverride language
<param>Any LiveCodes query parameter (e.g., console=open, theme=light)

Common Meta Parameters

markdown
```jsx livecodes render=button
// Button opens in LiveCodes
```

```py livecodes lang=py-wasm console=open
# Force Python (Wasm) language
print("Hello from Python")
```

```typescript livecodes theme=light editor=monaco
// Light theme, Monaco editor
const x: number = 1;
```

Common Mistakes

MEDIUM Not installing peer dependencies

bash
# Each plugin requires its host library
npm install remark remark-livecodes     # remark-livecodes
npm install marked marked-livecodes     # marked-livecodes
npm install markdown-it markdown-it-livecodes  # markdown-it-livecodes
npm install gatsby-plugin-remark gatsby-remark-livecodes  # Gatsby

Install the host library alongside the LiveCodes plugin. Each plugin wraps a specific Markdown processor.

Source: docs/docs/markdown-to-livecodes.mdx — Installation sections

LOW Forgetting livecodes parameter in code block

markdown
```jsx
// This is just a static code block (no livecodes parameter)
export default () => <h1>Hello</h1>;
```

```jsx livecodes
// This becomes an interactive playground
export default () => <h1>Hello</h1>;
```

Without the livecodes parameter, the code block renders as static Markdown. Add it to enable the playground.

Set auto: true in options to convert all code blocks automatically.

Source: docs/docs/markdown-to-livecodes.mdx — Meta Parameters section

Plugin Packages

PackageUse WithInstall
remark-livecodesDocusaurus, Astro, Next.js, Storybook, react-markdownnpm install -D remark-livecodes
markdown-it-livecodesVitePress, Eleventynpm install -D markdown-it-livecodes
marked-livecodesMarkednpm install -D marked-livecodes
gatsby-remark-livecodesGatsbynpm install -D gatsby-remark-livecodes

Frequently asked questions

What does the Markdown Integration AI skill do?

Integrate LiveCodes with documentation sites using remark-livecodes, markdown-it-livecodes, gatsby-remark-livecodes, or marked-livecodes for Docusaurus, Astro, VitePress, Next.js, and Storybook.

Why use Markdown Integration on TypingMind?

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

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

Which AI models can use Markdown Integration?

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 Markdown Integration?

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

Is the Markdown Integration 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 👇