Deploy It logo

Deploy It

Community
duncan-buildroom
deploy-it

Put whatever you just built on a real public web address for free, one click at a time, and save the link so you build a list of things you've shipped. Covers the GitHub step in plain English and fixes the three things that actually break for beginners. Use when the user says "/deploy-it", "put this online", "how do I get this on the internet", "deploy my site", "publish my page", "I need a link I can send someone", "make this live", "host my website free", "get this off my computer", "how do I share what I built", or "my site is live but the page is blank".

Overview

Publisherduncan-buildroom
Repositoryfreeskills
Skill namedeploy-it
Stars
65
Forks
15
Bundled files
Instructions only
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 duncan-buildroom on GitHub. Read the source before you install it.

Installation

Install the Deploy It 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/duncan-buildroom/freeskills/tree/main/deploy-it
  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/duncan-buildroom/freeskills.git /tmp/freeskills
mkdir -p .claude/skills
cp -r /tmp/freeskills/deploy-it .claude/skills/deploy-it
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deploy It 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 Deploy It 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 Deploy It 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.

Deploy It — from a file on your laptop to a link you can text

Right now the thing you built only exists on your computer. Nobody can see it, which means it doesn't count yet. This gets it onto a real web address for free, in about ten minutes, without you understanding anything about servers. Then you send that link to one person today.

Setup

None. This skill works out of the box.

Steps

1. Find what we're shipping and set expectations

Look in ~/sites/ and ~/games/ for folders with an index.html. If there's more than one, list them and ask which. If there's none, ask where the file is.

Then say this plainly:

  • This is free. No card, no trial, nothing to cancel.
  • You'll click through two websites and answer a few prompts. You will not write code.
  • Ugly but live beats pretty but local. We are not making it better today. We are making it real.
  • If anything looks scary, stop and tell me what you see on screen. You can't break anything.

2. Make it a Git repo, in plain English

Explain the GitHub step before doing it, because "repository" is the word that scares people off:

Git is a save system that keeps every version of your file. GitHub is a website that holds those saves online. Vercel — the free host — reads from GitHub and turns your file into a real web page. That's the whole chain. You're making a saved copy online, and then pointing a free host at it.

Then run it for them from inside their project folder:

bash
cd ~/sites/<slug>
git init
git add .
git commit -m "First version"

If Git asks for a name and email the first time, tell them it's a one-time thing and set it:

bash
git config --global user.name "Their Name"
git config --global user.email "their@email.com"

Now put it on GitHub. If they have the GitHub CLI, one command does everything:

bash
gh repo create <slug> --public --source=. --push

If that command isn't found, walk them through the browser instead, one step at a time — never more than one instruction per message:

  1. Go to github.com and sign in (make a free account if needed — email, username, password, that's it).
  2. Click the + at the top right, then New repository.
  3. Name it <slug>. Leave everything else alone. Click Create repository.
  4. GitHub shows a box of commands. Tell them: "Copy nothing — I'll handle it. Just paste me the URL at the top of that page."
  5. Take their URL and run the connect-and-push yourself.

3. Walk Vercel sign-in, one click at a time

Vercel is the free host. Give these one at a time, and wait for them to say done before the next:

  1. Go to vercel.com and click Sign Up.
  2. Choose Continue with GitHub. Use GitHub — it makes the rest automatic.
  3. Approve the permission screen. Vercel is asking to read your repositories so it can publish them. Say yes.
  4. Pick the Hobby plan when it asks. That's the free one. It will ask for your name; it will not ask for a card.
  5. On your dashboard, click Add New then Project.
  6. Find <slug> in the list and click Import.
  7. Don't change any settings. Click Deploy.
  8. Wait about 30 seconds. You'll get confetti and a link ending in .vercel.app.

Ask them to paste that link to you.

4. Fix the three things that actually go wrong

Check these before celebrating, because these are the three that trip up nearly every beginner:

1. The page is blank, or shows a file list. Almost always the file isn't named index.html, or it's sitting inside an extra folder. Check with:

bash
ls ~/sites/<slug>

If it's called site.html or Untitled.html, rename it to index.html. If it's one folder deeper, move it up. Then commit and push again — Vercel republishes automatically in seconds.

2. The repo doesn't show up in Vercel's import list. Either it was created as private with limited access, or Vercel wasn't given permission to that repo. On the import screen there's an Adjust GitHub App Permissions link — click it and grant access to all repositories. Refresh.

3. They pushed to GitHub and the live site didn't change. Two usual causes. Either the change was never committed — run git status and if it lists files in red, they weren't saved yet. Or their browser is showing the old cached page — tell them to open the link in a private window to check for real.

If they hit something not on this list, ask for one sentence describing exactly what they see on screen. Don't ask them to read logs.

5. Open it on your phone, then send it to a human

Two things, in this order, both today:

  1. Open the link on your phone. Not the laptop. This is where you find the real problems — text too small, a button off the edge, an image pushing the layout sideways. Note what's wrong and fix it in a later session. Do not start fixing it now.
  2. Send the link to one real person. A friend, your partner, someone in a group chat. Not for feedback, not for praise. The rep is the sending. Something you made now exists at an address anyone in the world can open, and you did it in an evening.

If they want a nicer address later, mention that a custom domain is about $12 a year and Vercel walks you through it — but not today.

6. Save the link to your list

Append to ~/my-links.md (create it if it doesn't exist). Keep one line per shipped thing, newest at the bottom:

markdown
# Things I've shipped

- 2026-07-30 — Treat Chase (game) — https://treat-chase.vercel.app — local: ~/games/treat-chase

Tell them the path and why it exists: in three months this file is the answer to "what have you actually built," and that list is worth more than any certificate.

Output — save it

  • ~/my-links.md — a running list of every live thing they've shipped: date, name, live URL, and the local folder.
  • The project folder is now a Git repo connected to GitHub and auto-publishing to Vercel on every push.

State the live URL and the path to ~/my-links.md. Single next action: open it on their phone, then send the link to one person today.

Example (input → output)

Input: "I made that snake game with my dog in it. How do I get it online so my sister can play it?"

Output:

Live at https://treat-chase.vercel.app in about 9 minutes. One snag along the way: the first deploy showed a blank page because the file was named game.html — renamed it to index.html, pushed, and it came back in 20 seconds.

Appended to ~/my-links.md:

markdown
- 2026-07-30 — Treat Chase (game) — https://treat-chase.vercel.app — local: ~/games/treat-chase

Next: open it on your phone, then text the link to your sister and ask for her score.

Notes / edge cases

  • The failure this prevents: building something good and never showing it to anyone, so it never becomes real and the momentum dies.
  • Give one instruction per message during sign-up. A numbered list of eight steps pasted at once is where beginners get lost and quit.
  • Never ask them to read an error log or a stack trace. Ask what they see on the screen, in one sentence, and translate it yourself.
  • If they have no GitHub account, that's a two-minute signup, not a blocker. Say so before they assume it's a big deal.
  • Every future change is: tell me what to fix, then git add . && git commit -m "..." && git push and the live link updates itself. Say this once so they know it gets easier.
  • Hand off: first-website, landing-page, link-in-bio, sales-page, or simple-game if there's nothing built yet to deploy.

Frequently asked questions

What does the Deploy It AI skill do?

Put whatever you just built on a real public web address for free, one click at a time, and save the link so you build a list of things you've shipped. Covers the GitHub step in plain English and fixes the three things that actually break for beginners. Use when the user says "/deploy-it", "put this online", "how do I get this on the internet", "deploy my site", "publish my page", "I need a link I can send someone", "make this live", "host my website free", "get this off my computer", "how do I share what I built", or "my site is live but the page is blank".

Why use Deploy It on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/duncan-buildroom/freeskills/tree/main/deploy-it. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Deploy It?

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 Deploy It?

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

Is the Deploy It AI skill free?

It is published on GitHub by duncan-buildroom. Check the repository for licensing terms. 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 👇