Guided build · an evening
Review collector
Asks happy clients for reviews and gathers them in one place.
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.
Asks happy clients for reviews and gathers them in one place.
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 review collector, nail THREE distinct surfaces: the client form (name, a 1-to-5 star picker, a comment box, then a thank-you screen), the private owner dashboard (every review with stars and date, filter by rating, a publish toggle on each), and the public wall (only the published ones, as clean cards).
- 2Decide the publish rule yourself: by default a review is NOT public until you flip its toggle. Say that plainly, or you risk a one-star rant going live on your wall the moment it's submitted.
- 3Spell out the star picker as actual tappable stars, not a number you type — and that the comment box is optional so a quick 5-star takes one second to leave.
- 4End 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 ▸ get me five-star reviews
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a review collector. A client-facing form with a name
field, a 1-to-5 star picker and a comment box, followed by a
thank-you screen once they submit. A private owner dashboard
lists every review with its stars and date, lets me filter by
rating, and gives each one a 'publish' toggle. A separate 'wall
of reviews' page shows only the published ones, laid out as
clean cards for new clients to see. It works in the browser and
keeps everything in browser storage for now. Clean readable
design. 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 ▸ if someone leaves 4 or 5 stars, show a button to also post it on Google; if fewer, just send it privately to me you ▸ let me add a photo of the client's result next to their review you ▸ make a 'wall of reviews' page I can show off the published ones on
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 submit two reviews as a client — one 5-star, one 2-star — using the form. Do you land on a thank-you screen each time?
- 2Open the owner dashboard: are both reviews listed with their stars and the date? Filter by rating — does the 2-star drop out when you show only 4-5?
- 3Flip the publish toggle on the 5-star one only. Now open the wall page — does it show ONLY the published 5-star, and NOT the unpublished 2-star?
- 4Refresh the page (F5 / Cmd-R). Are all your reviews and their publish states still there? If they vanish, browser storage isn't wired up — fix that next.
- 5Check the wall on a narrow window (phone width) — do the review cards still look tidy, since that's the page strangers will actually see?
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 review showed up on the public wall before I approved it — keep everything unpublished until I flip its publish toggle myself' you ▸ 'the star picker makes me type a number — make it five tappable stars instead' you ▸ 'when I refresh the page my reviews disappear — save them and their publish state in browser storage 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 ▸ 'put the client form online and give me a short shareable link I can text to a client right after the job' — the whole point is a link they open on their own phone; on your laptop it collects nothing. you ▸ 'when someone leaves 4 or 5 stars, show them a button to also post it on Google; if fewer, just send it privately to me' — public praise grows, quiet complaints reach you first. you ▸ 'email me an alert with the stars and text the moment any review comes in, and drop every response into a Google Sheet' — you react to a bad one fast and keep a sortable record of all of them. you ▸ 'let me add a photo of the client's result beside their review on the wall' — before/after pictures sell harder than words for new clients.
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 form, dashboard and wall all run in the browser on your device.
- 2Gmail or the Telegram Bot API (both free) are perfect for 'new review' alerts and for auto-sending the review link to a client after a job; the Google Sheets API (free) collects every response in a sortable spreadsheet.
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a review collector 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
- 1Gmail — email the review link to a client automatically right after the job
- 2Google Sheets — collect every response in a spreadsheet you can sort and filter
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)
The whole point is to send clients a link they open on their own phone — that needs to be online; then you publish the best ones for new clients to see.
Buy a server and a domain — like ordering groceries
- 1Server: sign up at a host (Hetzner, DigitalOcean…), click 'Create Server', pick Ubuntu + the cheapest size + PASSWORD login. SAVE the IP address and password it gives you. (Don't be scared — it's a few dollars a month, cancel anytime.)
- 2Domain: buy a name at any registrar (Namecheap, Cloudflare…). Then add ONE 'A record': Type = A, Host = @, Value = your server's IP. That's the whole DNS part — ignore every other field.
- 3Hand it to Claude: back in your terminal, say — 'deploy my project to my server. IP: <the ip>, password: <the password>, domain: <yourname.com>. Set up HTTPS and basic security, do it all yourself.' Claude installs everything, secures it, and makes it live. You configure nothing.
- 4DNS can take minutes to a couple of hours to wake up — if Claude says the domain isn't answering yet, that's the wait, not a mistake. Come back later and say 'try again'.
Step 5 — Keep your keys (so you can come back)
Save the server's IP, the password (or SSH key), and your domain somewhere safe — a notes app, a password manager. Why it matters: any day later you can open the terminal, connect to the server, start Claude right there, and keep improving the live tool by talking — fix a bug, add a feature, change the look. Tip: tell Claude 'save the server details in a file in this project folder' so a future chat already knows them.
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