Guided build · an evening
Math game for your kid
A tiny game tuned to their age and what they love — space, dinosaurs, whatever.
No commands. No code. You're about to build this by SAYING what you want — in your own language. The only skill is describing the result well. Here's the whole thing, start to finish.
A tiny game tuned to their age and what they love — space, dinosaurs, whatever.
First, how to actually talk to the agent
- 1Describe the RESULT, not the tech: what's on screen, what each button does, what gets saved. The agent handles the 'how'.
- 2Be concrete about screens and fields — 'a form with amount, category and date' beats 'let me add expenses'.
- 3Ask for the smallest working version first. You grow it by talking afterwards — that's Step 2, not the first message.
- 4Decide what's YOURS, not the agent's: name the categories, colours, rules. Don't make it guess what only you know.
Step 1 — Build it live
Prompting for this kind of tool
- 1For a kids' game, nail FOUR things: the exact maths (addition and subtraction up to 20), how a question looks on screen (big number, three large tap buttons), what happens on a right vs wrong answer, and that it saves progress and works offline.
- 2Decide the reward yourself and make it concrete — 'rocket goes a little higher, a happy sound, a burst of stars'. 'Make it fun' gives Claude nothing; a rocket and stars give it something to build.
- 3Spell out the difficulty curve in plain words: 'start easy and grow the number range slowly as she gets answers right' — otherwise it either stays trivial or jumps to hard and she quits.
- 4Always end with the magic line: 'build the whole thing and tell me exactly how to open it; don't stop to ask questions.'
claude --dangerously-skip-permissions
Open the terminal and run this (if Claude is already running, type /exit first). Then ask it to make a folder for this project and work inside it.
✕ what most people type
you ▸ make an educational game
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a math game for my 7-year-old who loves space. It asks
addition and subtraction questions up to 20, shown big with
three large answer buttons to tap. Each right answer launches
the rocket a little higher with a happy sound and a burst of
stars; a wrong one gently shows the right answer and lets her
try the next. Track a score and a best streak, keep the numbers
easy at first and grow the range slowly as she gets them right.
Works offline and saves progress on my device, bright friendly
look. Build the whole thing and tell me exactly how to open it;
don't stop to ask questions.Say it in YOUR language — Russian, Spanish, anything. Claude understands.
Build it now — tick as you go
0/6Step 2 — It's built. Now make it yours
Don't panic at the techy link. Claude tells you one of two things. Either a file like index.html — find it in your project folder and double-click it; it opens in your browser. Or a web address starting with http://localhost — copy it into your browser's address bar and press Enter. 'localhost' just means 'this is running on your own computer right now'. That's your tool. It's real.
Now tweak it until YOU like it — just talk
This is the part that makes it YOURS. Don't accept the first version — change it by saying what you want, right there in the same chat. Claude rebuilds and you refresh. Keep going until it fits how you actually work. For this tool, try things like:
you ▸ add multiplication once she's good at adding you ▸ change the theme from space to dinosaurs you ▸ add a happy sound and a star burst when she gets one right
I don't type long messages. I open voice-to-text (the mic in ChatGPT, or your phone keyboard), and just TALK through everything I think about what it built — what's wrong, what I want next — then select-all, copy, and paste the whole brain-dump into Claude Code. Messy spoken thoughts work fine; the agent sorts them out. It's several times faster than writing.
Step 2.5 — Test it like a real thing (it won't be perfect first try)
The truth no one tells beginners: the first build is a DRAFT. The agent makes something, you run it, you find what's off, you tell it — and THAT loop is the actual work. Don't read the code. Use the tool like a stranger would and watch where it lets you down. For this tool, check exactly this:
- 1Open it (Claude gives a localhost link or an index file — see Step 2) and answer a few questions the way a 7-year-old would — tap the big buttons, including a wrong one on purpose.
- 2Get one right: does the rocket move up, does a sound play, do the stars burst? The reward is the whole point — if nothing happens, that's your first fix.
- 3Get one wrong on purpose: does it gently show the right answer and let you move on, instead of scolding or freezing?
- 4Answer ten in a row correctly: do the numbers slowly get harder, and does the score and best streak go up?
- 5Refresh the page (F5 / Cmd-R). Is the best streak still there? If progress vanishes, 'saves on my device' isn't wired up — fix that next.
Found something wrong? Say it like this
You fix nothing yourself — you DESCRIBE what's wrong in plain words and the agent fixes it. Be specific: what you saw vs. what you expected. Real examples for this tool:
you ▸ 'the numbers are too hard for a 7-year-old straight away — start much easier and only grow the range after several right answers in a row' you ▸ 'nothing happens when she gets one right — make the rocket jump up, play a happy sound and show a burst of stars' you ▸ 'when I refresh the page the best streak resets to zero — save the score and streak on my device so they stay'
Don't stop at v1 — grow it
A tool you built in ten minutes is a starting point, not the finish line. The people who get hooked keep saying 'now also…'. Each line below is one sentence you paste into the same chat to level this tool up:
you ▸ 'add multiplication and division as a harder mode I can switch on once she's confident with adding' — the game grows with the child instead of being outgrown in a week. you ▸ 'let me change the theme from space to dinosaurs or unicorns with one tap' — the same maths, a brand-new game for a kid with new obsessions. you ▸ 'add a grown-up screen showing which kinds of question she gets wrong most' — turns a game into a quiet read on where she needs help. you ▸ 'give two kids their own name and saved progress so they can take turns' — one tool covers the whole household.
Step 3 — Connect it to the world (optional)
Free data & APIs for this one
An API is just how your tool pulls in outside data or sends things out — many are free. You rarely need to research them yourself; the move that works for ANY idea is to ask the agent to find them:
- 1No API is needed to start — all the maths, scoring and rewards run locally and it works fully offline, which is exactly what you want for a kid's game.
- 2Want spoken questions or praise read aloud? Browsers have a built-in free text-to-speech voice (Web Speech API) — no key, no account; ask Claude to use it.
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a kids' maths game and tell me which actually need a key.' It will list them; you pick.
About paying for the AI parts
- 1You don't pay for Claude twice. With a Claude subscription you create an API key right in the terminal and use it inside your projects — within your plan.
- 2From June 15 the rule splits: automation through that key gets its own monthly credit — about $20 on Pro, $100 or $200 on Max. Stay under it and it works as before.
- 3Run out and you pay per use (pay-as-you-go); unused credit doesn't roll over. So check your account and see whether the included credit already covers what you're building.
This tool needs no keys to be great — it runs entirely on your computer. Add one only if you later want it to reach out to a service.
Step 4 — Put it online (only if someone else needs it)
Just for you, on your computer? You're already done — skip this step with a clear conscience. Put it online only if someone ELSE should open it, or you want to reach it from your phone away from home.
Step 6 — Stay safe (two easy habits)
- 1Back up anything you'd hate to lose. If the tool holds real data (your budget, health log, client list), ask Claude early: 'add an export/backup button' — one click saves your data to a file. Do it before you ever rebuild from scratch or move the folder.
- 2Don't hand Claude the keys to dangerous rooms. Keep it pointed at this project's own folder. Never connect a learning project to your bank, your crypto, or anything irreversible. Receipts and calendars — yes. Savings — no.
- 3Think before you ask. Claude does what you say in the folder you're in. 'Optimize my photos' optimizes them; it won't delete them — unless you ask for something reckless. Sane requests, clean workspace, and there's simply nothing scary left.
The mistakes that stop most people
- 1Asking for something vague ('make me an app') and getting something vague back. Name the screens, the buttons, what gets saved.
- 2Cramming in ten features at once. Ask for the tiniest working version first — then grow it with follow-up requests.
- 3Stopping at the first error. An error isn't failure — paste it to Claude or describe what you see, and it fixes it. That loop IS the work.
- 4Deciding you need to 'learn programming first'. You don't need to understand the code Claude writes. You need to describe the result.
- 5Forgetting the magic line — 'build the whole thing, don't stop to ask questions' — then wondering why it keeps pausing.
- 6Building for an imaginary audience. Build the version YOU will open tomorrow. Polish never; use immediately.
Normal. Tell Claude what's wrong in plain words ('the button does nothing', 'the page is blank') or paste the red error text. It finds and fixes it. You check. Repeat until it works.
That's it. You built a real tool.
Notice what just happened: no commands, no code — words. This is the entire skill. The people who 'can build things' are just people who describe what they want and let Claude do the typing.
More to build