Tailscale logo

Tailscale

CommunityPopular
alsk1992
tailscale

Tailscale VPN sharing, Serve, and Funnel for remote access

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill nametailscale
Stars
3K
Forks
353
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 alsk1992 on GitHub. Read the source before you install it.

Installation

Install the Tailscale 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/alsk1992/CloddsBot/tree/main/src/skills/bundled/tailscale
  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/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/tailscale .claude/skills/tailscale
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tailscale 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 Tailscale 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 Tailscale 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.

Tailscale - Complete API Reference

Share local services via Tailscale Serve (private) and Funnel (public internet access).


Chat Commands

Share Local Services (Private)

/tailscale serve 3000                       Share port on tailnet
/tailscale serve 3000 --path /api           Share at specific path
/tailscale serve stop 3000                  Stop sharing port
/tailscale serve status                     View active shares

Public Access (Funnel)

/tailscale funnel 3000                      Expose to internet
/tailscale funnel 3000 --https              Force HTTPS
/tailscale funnel stop 3000                 Stop public access
/tailscale funnel status                    View funnels

Network Status

/tailscale status                           Network status
/tailscale ip                               Show Tailscale IP
/tailscale peers                            List connected peers
/tailscale ping <peer>                      Ping a peer

File Transfer

/tailscale send <file> <peer>               Send file to peer
/tailscale receive                          Receive incoming files

TypeScript API Reference

Create Tailscale Client

typescript
import { createTailscaleClient } from 'clodds/tailscale';

const tailscale = createTailscaleClient({
  // Auth (optional if already logged in)
  authKey: process.env.TAILSCALE_AUTHKEY,

  // Socket path
  socketPath: '/var/run/tailscale/tailscaled.sock',
});

Serve (Private Sharing)

typescript
// Share local port on tailnet
await tailscale.serve({
  port: 3000,
  protocol: 'https',  // 'http' | 'https'
});

console.log(`Shared at: https://${tailscale.hostname}:3000`);

// Share at specific path
await tailscale.serve({
  port: 8080,
  path: '/api',
  protocol: 'https',
});

// Share with custom hostname
await tailscale.serve({
  port: 3000,
  hostname: 'clodds',  // clodds.tailnet-name.ts.net
});

// Stop sharing
await tailscale.serveStop(3000);

// Get serve status
const serves = await tailscale.serveStatus();
for (const serve of serves) {
  console.log(`Port ${serve.port} → ${serve.url}`);
}

Funnel (Public Internet)

typescript
// Expose to public internet
await tailscale.funnel({
  port: 3000,
  protocol: 'https',
});

console.log(`Public URL: https://${tailscale.hostname}.ts.net`);

// With custom domain (if configured)
await tailscale.funnel({
  port: 3000,
  hostname: 'api.example.com',
});

// Stop funnel
await tailscale.funnelStop(3000);

// Get funnel status
const funnels = await tailscale.funnelStatus();
for (const funnel of funnels) {
  console.log(`Port ${funnel.port} → ${funnel.publicUrl}`);
}

Network Status

typescript
// Get status
const status = await tailscale.status();

console.log(`Hostname: ${status.hostname}`);
console.log(`IP: ${status.ip}`);
console.log(`Tailnet: ${status.tailnet}`);
console.log(`Online: ${status.online}`);

// List peers
const peers = await tailscale.peers();
for (const peer of peers) {
  console.log(`${peer.hostname} (${peer.ip})`);
  console.log(`  OS: ${peer.os}`);
  console.log(`  Online: ${peer.online}`);
  console.log(`  Last seen: ${peer.lastSeen}`);
}

// Ping peer
const ping = await tailscale.ping('other-machine');
console.log(`Latency: ${ping.latencyMs}ms`);

File Transfer

typescript
// Send file to peer
await tailscale.sendFile({
  file: '/path/to/file.zip',
  peer: 'other-machine',
});

// Receive files (returns when file received)
const received = await tailscale.receiveFile({
  savePath: '/downloads',
  timeout: 60000,
});

console.log(`Received: ${received.filename}`);
console.log(`From: ${received.sender}`);
console.log(`Size: ${received.size} bytes`);

Get Tailscale IP

typescript
const ip = await tailscale.getIP();
console.log(`Tailscale IP: ${ip}`);  // 100.x.x.x

Serve vs Funnel

FeatureServeFunnel
AccessTailnet onlyPublic internet
AuthTailscale identityNone (public)
URLmachine.tailnet.ts.netmachine.ts.net
Use caseInternal toolsPublic APIs

URL Formats

TypeFormat
Servehttps://machine.tailnet-name.ts.net:port
Funnelhttps://machine.ts.net
Custom domainhttps://your-domain.com

Use Cases

Share Dev Server

typescript
// Share local dev server with team
await tailscale.serve({ port: 3000 });
// Team can access at https://your-machine.tailnet.ts.net:3000

Expose Webhook Endpoint

typescript
// Make webhook publicly accessible
await tailscale.funnel({ port: 3000, path: '/webhooks' });
// External services can POST to https://your-machine.ts.net/webhooks

Share Bot with Phone

typescript
// Access bot from phone while away from desk
await tailscale.serve({ port: 18789 });
// Open https://your-machine.tailnet.ts.net:18789/webchat on phone

Requirements

  • Tailscale installed and running
  • Logged into a Tailnet
  • For Funnel: Funnel enabled in Tailscale admin

Best Practices

  1. Use Serve for internal — Keep private services private
  2. Use Funnel sparingly — Only for truly public endpoints
  3. Add authentication — Funnel bypasses Tailscale auth
  4. Monitor access — Check who's connecting
  5. Stop when done — Don't leave services exposed

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 Tailscale AI skill do?

Tailscale VPN sharing, Serve, and Funnel for remote access

Why use Tailscale on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/tailscale. 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 Tailscale?

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 Tailscale?

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

Is the Tailscale AI skill free?

Yes. It is published on GitHub by alsk1992 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 👇