Guided build · an evening
Flashcards from your notes
Turns your notes into spaced-repetition cards that make things stick.
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.
Turns your notes into spaced-repetition cards that make things stick.
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 flashcards tool, nail THREE things: the exact INPUT format (here: lines like 'term = definition'), what the STUDY loop is (show front, tap to flip, then 'knew it' / 'repeat'), and the spacing RULE in plain words ('cards I miss come back sooner, ones I know go further out').
- 2Decide the deck structure yourself — say you want to group cards into decks and see a 'due today' count on the start screen. Don't leave Claude to guess whether it's one big pile or sorted sets.
- 3Spell out that the scheduling is automatic: you never pick when a card returns, the 'knew it' / 'repeat' tap decides it. Otherwise you may get a dumb shuffle with no real spaced repetition.
- 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 flashcards
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a flashcards app with spaced repetition. An add screen
where I paste lines like 'term = definition' and it turns each
into a card. A study screen shows one card's front, taps to flip
to the back, then 'knew it' or 'repeat' buttons; cards I miss
come back sooner and ones I know are scheduled further out. The
start screen shows a 'due today' count and lets me group cards
into decks. Everything saves on my device, clean readable dark
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 ▸ let me paste a wall of notes and have it pull out the term = definition pairs for me you ▸ add a 'cards due today' count on the start screen you ▸ shuffle the order each round so I don't learn the sequence instead of the words
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 paste five lines of 'term = definition'. Check you now have five cards, not one blob.
- 2Start a study round: does the front show, and does a tap actually flip it to the back? If the back is blank or shows the wrong side, that's your first fix.
- 3Tap 'repeat' on one card and 'knew it' on another. The one you missed should come back sooner in the round — watch whether it actually reappears.
- 4Refresh the page (F5 / Cmd-R). Are your cards and your progress still there? If they vanish, 'saves on my device' isn't wired up — fix that next.
- 5Check the 'due today' count on the start screen: does it drop as you clear cards and make sense the next day? A count stuck at zero or never changing means the scheduling isn't really running.
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 spaced repetition isn't working — cards I tap repeat should come back sooner in the session and cards I knew should be scheduled further out' you ▸ 'when I refresh the page my cards and progress disappear — save everything on my device so it stays' you ▸ 'pasting term = definition only made one card — split it line by line so each line becomes its own card'
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 ▸ 'let me paste a wall of messy notes and pull out the term = definition pairs for me automatically' — turns ten minutes of typing into one paste. you ▸ 'shuffle the card order every round so I learn the words, not the sequence' — stops you memorising position instead of meaning. you ▸ 'add a reverse mode that shows me the definition and asks for the term' — drilling both directions makes recall far stronger. you ▸ 'show a little graph of how many cards I reviewed each day this week' — seeing the streak is what keeps you coming back.
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 — the cards and the spacing schedule all run locally on your device.
- 2Want it to read your notes and build cards for you? That needs an AI service (Claude or OpenAI) to turn paragraphs into clean term/definition pairs — it's pay-as-you-go and separate from the chat you build in.
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a flashcards study tool 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.
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) — turn messy paragraphs of notes into clean question/answer cards automatically (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