Guided build · an evening
Language practice buddy
Dialogues and words tuned exactly to your level.
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.
Dialogues and words tuned exactly to your level.
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 language trainer, nail THREE things: what ONE entry holds (word, translation, example sentence), the two PRACTICE modes (flashcard that flips word↔translation, and typing mode that hides the word and makes you spell it), and the daily ritual ('daily 10' picks ten due words, scores you at the end, keeps a 7-day streak).
- 2Decide the streak rule yourself: it counts a day done when you finish the daily 10, and breaks if you skip. Spell that out or Claude may add a vague counter that means nothing.
- 3Say what the HOME screen shows up front: total word count, today's streak, and one big 'start daily review' button — so it opens straight into action, not a menu.
- 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 me fluent in English
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a language trainer. An add screen where I enter a word,
its translation and an example sentence. A flashcard mode flips
between word and translation; a typing mode hides the word and
makes me spell it. A 'daily 10' review picks ten words due,
scores me at the end, and keeps a 7-day streak counter so I
don't skip. The home screen shows my word count, today's streak
and a big 'start daily review' button. Everything saves on my
device, clean readable theme. 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 a typing mode where I have to spell the word, not just recognise it you ▸ show an example sentence with each word so I see how it's used you ▸ keep a 7-day streak counter so I don't skip my daily 10
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 add about a dozen words, each with a translation and an example.
- 2Run flashcard mode: does it flip cleanly between word and translation both ways? Then run typing mode — does it actually hide the word and check your spelling, marking a typo wrong?
- 3Start the 'daily 10': do you get exactly ten due words and a score at the end? Fewer or no score means the review loop isn't finished.
- 4Finish today's review and check the streak ticks to 1. Refresh the page (F5 / Cmd-R) — are your words AND your streak still there? If they vanish, 'saves on my device' isn't wired up — fix that next.
- 5Come back the next day (or change your device clock) — does it offer a fresh daily 10, and does skipping a day reset the streak as it should?
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 ▸ 'when I refresh the page my words and my streak disappear — save everything on my device so it stays' you ▸ 'typing mode accepts wrong spellings — it should only count it right when I spell the word exactly' you ▸ 'the daily 10 gives me the same words every time — pick ten that are actually due and rotate them'
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 ▸ 'auto-generate an example sentence for each word so I don't have to write them' — fills the hardest field for you (needs an AI service). you ▸ 'add audio so I hear each word pronounced' — hearing it locks pronunciation far better than reading alone. you ▸ 'group words into lists like travel and work so I can drill one set at a time' — focused sets beat one giant pile. you ▸ 'show which words I keep getting wrong and drill those harder' — your weak spots get the practice, not the easy ones.
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:
- 1To start you need NO external API — your words, the modes and the streak all run locally on your device.
- 2Want example sentences written for you, or definitions filled in? That needs an AI service (Claude or OpenAI) — pay-as-you-go and separate from the chat you build in.
- 3For audio, free dictionary APIs exist (the Free Dictionary API gives pronunciations and audio with no key) — but ask Claude first: 'what's the simplest free way to add word audio and example sentences to my language trainer?'
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.
A tool gets superpowers when it can talk to other services — send you a message, read a sheet, pull live data. Each service hands out an 'API key' (a long password that says 'this is me'). For THIS tool, the useful ones are:
Which keys this tool can use
- 1An AI service (Claude or OpenAI) — auto-generate an example sentence for each word so you don't write them yourself (pay-as-you-go, separate from the chat you build in)
Getting any key is the same recipe: log into the service → find Settings → 'API' or 'Developers' → 'Create key' → copy it → paste it to Claude once ('here's my key: …'). Claude stores it and you never touch it again.
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