Sidecar Website logo

Sidecar Website

CommunityPopular
marcus
sidecar-website

Writing and maintaining the Sidecar Docusaurus documentation site, including page structure, doc authoring, blog posts, styling, images, and deployment workflow. Use when writing documentation, updating the docs site, adding pages or blog posts, or working with Docusaurus configuration.

Overview

Publishermarcus
Repositorysidecar
Skill namesidecar-website
Stars
1.1K
Forks
82
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by marcus on GitHub. Read the source before you install it.

Installation

Install the Sidecar Website 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/marcus/sidecar/tree/main/.claude/skills/sidecar-website
  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/marcus/sidecar.git /tmp/sidecar
mkdir -p .claude/skills
cp -r /tmp/sidecar/.claude/skills/sidecar-website .claude/skills/sidecar-website
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sidecar Website 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 Sidecar Website 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 Sidecar Website 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.

Docusaurus Documentation Site

The documentation site lives in website/. It uses Docusaurus with Node.js >= 20.

Quick Start

bash
cd website
npm install    # First time only
npm start      # Dev server at http://localhost:3000

Project Structure

website/
├── docs/                    # Markdown documentation pages
├── blog/                    # Blog posts (date-prefixed markdown)
│   ├── authors.yml         # Blog author definitions
│   └── tags.yml            # Blog tag definitions
├── src/
│   ├── pages/              # Custom React pages (non-docs)
│   │   ├── index.js        # Front page (/)
│   │   └── index.module.css
│   ├── components/         # Reusable React components
│   └── css/
│       └── custom.css      # Global style overrides
├── static/                  # Static assets (copied as-is to build)
│   └── img/                # Images
├── docusaurus.config.js    # Main site configuration
├── sidebars.js             # Docs sidebar structure
└── package.json

Writing Documentation

Principles

  • User-first: Answer "what can I do?" before "how does it work?"
  • Scannable: Use headers, code blocks, tables for keyboard shortcuts
  • Progressive disclosure: Quick overview -> detailed usage -> full reference
  • Working examples: Every feature needs runnable code, not ... placeholders

Creating a New Doc

Add a Markdown file in website/docs/ with YAML frontmatter:

markdown
---
sidebar_position: 2
title: My New Page
---

# My New Page

Content here. Supports **Markdown** and MDX.

Frontmatter options:

  • sidebar_position: Order in sidebar (lower = higher)
  • sidebar_label: Override sidebar text
  • title: Page title
  • description: Meta description for SEO
  • slug: Custom URL path

Plugin Documentation Pattern

markdown
# Plugin Name

One-line description.

![Screenshot](../../docs/screenshots/plugin-name.png)

## Overview
Brief explanation of UI layout and core purpose.

## Feature Section
Description with keyboard shortcut table:

| Key | Action |
|-----|--------|
| `s` | Stage file |
| `d` | View diff |

## Navigation
How to move around.

## Command Reference
Complete shortcut list by context.

Organizing Docs in Folders

docs/
├── intro.md
├── guides/
│   ├── _category_.json    # Folder metadata
│   ├── installation.md
│   └── configuration.md

_category_.json controls folder appearance:

json
{
  "label": "Guides",
  "position": 2,
  "collapsible": true,
  "collapsed": false
}

Sidebar Configuration

Auto-generates from docs/ folder structure. To customize, edit sidebars.js:

javascript
const sidebars = {
  tutorialSidebar: [
    'intro',
    {
      type: 'category',
      label: 'Guides',
      items: ['guides/installation', 'guides/usage'],
    },
  ],
};

Using MDX

Docs support MDX (Markdown + JSX):

mdx
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';

<Tabs>
  <TabItem value="npm">npm install</TabItem>
  <TabItem value="yarn">yarn add</TabItem>
</Tabs>

Front Page

The front page is at website/src/pages/index.js -- a React component using Docusaurus Layout and theming.

jsx
export default function Home() {
  return (
    <Layout title="Home" description="...">
      <HomepageHeader />
      <main className="container">
        {/* Add content here */}
      </main>
    </Layout>
  );
}

Styling: index.module.css for page-specific, src/css/custom.css for global overrides.

Images and Screenshots

Website doc screenshots (for pages in website/docs/):

  • Store in: docs/screenshots/ (project root)
  • Reference: ![Alt text](../../docs/screenshots/filename.png)

README / repo doc screenshots:

  • Store in: docs/screenshots/ (project root)
  • Reference: ![Alt text](docs/screenshots/filename.png) (from repo root)

General website images (logos, icons):

  • Store in: website/static/img/
  • Reference: ![Alt text](/img/filename.png)

In JSX:

jsx
import screenshot from '@site/static/img/logo.png';
<img src={screenshot} alt="Logo" />

Blog Posts

Date-prefixed Markdown files in blog/:

markdown
---
slug: my-post
title: Post Title
authors: [default]
tags: [announcement, release]
---

Preview text shown in list.

<!-- truncate -->

Full content below the fold.

Style Guidelines

No Emoji Policy

Never use emoji in site content, components, or documentation. Use Lucide icons instead.

Icons (Lucide)

The site uses Lucide icon font (CDN import in docusaurus.config.js).

jsx
<i className="icon-terminal" />
<i className="icon-check" />
<i className="icon-git-branch" />

Common icons: icon-eye, icon-terminal, icon-rocket, icon-check, icon-copy, icon-external-link, icon-git-branch, icon-zap, icon-keyboard, icon-layers, icon-code.

Browse all: https://lucide.dev/icons

Terminal Aesthetic

  • Monospace fonts (JetBrains Mono, Google Sans Code)
  • Dark backgrounds with muted colors
  • Bright accents from Monokai palette (green, blue, pink, yellow)
  • Clean 1px borders, subtle gradients and glows

Building and Deploying

bash
cd website
npm run build      # Outputs to website/build/
npm run serve      # Preview built site locally

Deploys automatically via GitHub Actions when changes to website/ merge to main.

  • .github/workflows/deploy-docs.yml -- Deploys to GitHub Pages
  • .github/workflows/test-docs.yml -- Validates PR builds
  • Live site: https://marcus.github.io/sidecar

Common Tasks

TaskSteps
Add docs sectionCreate folder in website/docs/, add _category_.json, add Markdown files
Change theme colorsEdit src/css/custom.css (:root and [data-theme='dark'] variables)
Add custom componentCreate in src/components/MyComponent/index.js, import with @site/src/components/MyComponent

Troubleshooting

  • Build fails with broken links: Config uses onBrokenLinks: 'throw'. Temporarily change to 'warn' for local dev.
  • Styles not updating: npm run clear && npm start
  • GitHub Pages 404: Verify baseUrl matches repo name (/sidecar/).

Reference

For detailed site configuration (navbar, footer, theme config, future compatibility), see references/site-configuration.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sidecar Website AI skill do?

Writing and maintaining the Sidecar Docusaurus documentation site, including page structure, doc authoring, blog posts, styling, images, and deployment workflow. Use when writing documentation, updating the docs site, adding pages or blog posts, or working with Docusaurus configuration.

Why use Sidecar Website on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/marcus/sidecar/tree/main/.claude/skills/sidecar-website. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sidecar Website?

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 Sidecar Website?

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

Is the Sidecar Website AI skill free?

Yes. It is published on GitHub by marcus 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 👇