Guided build · an evening
Workout plan for you
A plan built around your goal and whatever equipment you actually have.
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 plan built around your goal and whatever equipment you actually have.
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
- 1Nail the SETUP step first: you pick a goal (strength, lose weight, general fitness) and check off the equipment you actually own — and the plan it builds must only use that gear. Say 'only use equipment I checked' or you'll get barbell workouts with no barbell.
- 2Spell out the weekly view: one workout per day, each showing its exercises with sets and reps, a tap to mark the whole workout done, and a streak counter that grows as you keep training days. Decide yourself whether a missed day breaks the streak — say it either way.
- 3Ask for a per-exercise log where you type the weight and reps you ACTUALLY lifted, saved per date — that's separate from the planned sets/reps. This is the bit that makes it yours over weeks, so don't let it get dropped.
- 4Add 'everything stays on my device, big buttons I can tap with sweaty hands, no accounts' — 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 a workout app
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a workout planner. A setup screen where I pick my goal
(strength, lose weight, general fitness) and check off the
equipment I actually have. Then a weekly view with a workout per
day, each showing its exercises with sets and reps; I tap a
workout to mark it done and watch a streak counter grow. A
per-exercise log lets me type the weight and reps I actually
lifted, saved per date. Everything saves on my device, clean
readable dark theme, big buttons. 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 log the weight and reps I actually did you ▸ swap any exercise for one with the equipment I have you ▸ add a rest-day so the week isn't all training
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), run the setup once: pick a goal and check just a couple pieces of equipment.
- 2Look at the week it built — does every exercise actually use the gear you checked, and nothing you didn't? If a dumbbell move shows up and you only ticked bodyweight, that's your first fix.
- 3Tap a workout to mark it done and watch the streak counter go to 1; mark the next day too and confirm it climbs to 2.
- 4Open one exercise and log a real weight and reps for today, then refresh the page (F5 / Cmd-R). Is your logged set still there, and is the streak still counting? If they reset, 'saves on my device' isn't wired up — fix that next.
- 5Re-run the setup with a different goal and confirm the week's exercises actually change — that proves the goal isn't just a label.
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 plan uses equipment I didn't check — only build workouts from the gear I ticked in setup' you ▸ 'when I refresh the page my logged weights and my streak disappear — save them on my device so every set and the streak survive a refresh' you ▸ 'marking a workout done isn't moving the streak counter — increase the streak each day I complete a workout and reset it when I skip a day'
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 swap any single exercise for another that fits my goal and the equipment I have' — keeps the plan usable on days a machine is taken. you ▸ 'add a rest day to the week so it isn't all training, and don't break my streak on a planned rest day' — recovery is part of the plan, not a gap in it. you ▸ 'show me a small chart of the weight I'm lifting on one exercise over time' — seeing the line go up is what keeps people training. you ▸ 'add a warm-up set and a rest timer between sets' — turns a plan into something you follow live in the gym.
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 plan, the streak and your logged sets all run locally on your device.
- 2Want smarter exercise swaps that fit your goal and gear? That's the Claude API (a separate pay-as-you-go account) — ask Claude in this chat: 'how do I add an exercise-swap suggestion using the Claude API, and what will it cost me per use?'
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a workout planner 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
- 1Claude API — suggest exercise swaps that fit your goal and gear (separate pay-as-you-go account)
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