Guided build · ~15 min
Habit & wellbeing tracker
Tick your habits and log how you feel — watch streaks grow and patterns appear. Yours, private, no ads.
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.
Tick your habits and log how you feel — watch streaks grow and patterns appear. Yours, private, no ads.
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
- 1This is two tools in one row of the same screen, so name both halves clearly: the HABITS side (your own habits, each ticked once a day, with a current-streak flame and a best-ever) and the WELLBEING side (mood 1-5 with faces, energy 1-5, hours of sleep — one entry per day). Spell out both or Claude builds only the half it noticed first.
- 2Decide the rules yourself: a tick is once per day (not a counter you can spam), a streak counts consecutive ticked days and breaks on a miss, and the daily feel-log is one record per date that you can overwrite. Say this plainly so streaks and logs behave the way you expect.
- 3Say what the THREE views show: a 'today' list up top of just what's left to tick, a month grid of ticked-vs-missed at a glance, and a two-week chart that plots mood and sleep together so a pattern can surface. Without that last one you get tracking but no insight.
- 4Add 'everything stays on my device, this is a private diary, no accounts and nothing sent anywhere' — then 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 healthy
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a habit and wellbeing tracker. I add my own habits
(start with about five), each a row I tick once per day, with a
current-streak flame and a best-ever streak. A 'how I feel
today' panel lets me log mood 1-5 with face icons, energy 1-5,
and hours of sleep. A month grid shows ticked vs missed days at
a glance; a two-week chart plots mood and sleep together so
patterns surface; and a today view up top lists just what's left
to tick. I can add, rename and remove habits. Everything saves
on my device, calm dark theme, big readable text. 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 tags field on the daily log for triggers like 'coffee' or 'poor sleep' you ▸ show which tag shows up most on my low-mood days you ▸ let me export the last month as text to take to my doctor
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 five habits of your own, then tick three of them for today.
- 2Look at the 'today' list: did the three you ticked drop off it, leaving only what's left? And did a streak flame appear on the ticked ones?
- 3Open the 'how I feel today' panel and log a mood, an energy level and a sleep number — then check the two-week chart actually plots those points instead of staying empty.
- 4Refresh the page (F5 / Cmd-R). Are your habits, your ticks and today's feel-log all still there? If the streaks reset to zero or the log vanishes, 'saves on my device' isn't wired up — fix that first.
- 5Untick one habit you ticked. The streak should drop and it should reappear in the 'today' list — that confirms ticking is reversible and the streak is honest.
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 ▸ 'a streak should only count days in a row — right now it keeps the flame even after I miss a day, so reset the streak to zero on any missed day' you ▸ 'when I refresh the page my ticks and my mood log disappear — save everything on my device so streaks and the daily log survive a refresh' you ▸ 'the two-week chart is empty even though I logged my mood and sleep — plot each day's mood and sleep as points on it'
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 a tags field on the daily feel-log for triggers like coffee or a bad night, and let me pick a few each day' — turns a diary into something you can actually mine. you ▸ 'show me which tag shows up most on my low-mood days' — this is the payoff: the tool starts answering why, not just what. you ▸ 'let me export the last month — habits and feelings — as plain text I can take to my doctor' — your private data becomes useful outside the app. you ▸ 'add a gentle weekly summary: longest streak this week and my average mood and sleep' — a small recap 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 — every habit, tick, streak and feel-log lives locally on your device, and that's exactly right for a private diary.
- 2This isn't medical software and shouldn't pretend to be: keep it as your own log, not advice. If you later want a fitness band's sleep numbers in here, ask Claude — 'what's the simplest free way to pull my sleep data in, and does it need a key?'
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a habit and wellbeing tracker 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.