◆ HTML

Build a to-do list application

This is real work, not a feature someone invented — it comes from real job ads and real questions people asked. Below are four ready AI prompts: get it done, make it easy for the next person to say yes to, work out the right move when you are stuck, and stop it coming back.

4prompts
See the prompt↓All HTML tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskBuild a basic to-do list with items that can be added and marked as…+
Build a basic to-do list with items that can be added and marked as complete.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
BImprove — make it easier to acceptBefore I show this to the project manager, build the to-do list so new items appear at the top,…+
Before I show this to the project manager, build the to-do list so new items appear at the top, and completed items move to a 'Done' section, making it easy to see progress at a glance.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentThe team just asked to add due dates and priority levels to the to-do list, which means storing…+
The team wants to add due dates and priorities to the to-do list, but I'm unsure how to store this data reliably.
The team just asked to add due dates and priority levels to the to-do list, which means storing more data. I've only built the basic add/complete functionality so far. I'm afraid of choosing a data structure that will be hard to scale later or make filtering difficult. What's the best way to structure the data for each to-do item, considering future needs like sorting and filtering?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI consistently build initial versions of features, like this to-do list, that meet immediate…+
I keep building basic features that become hard to extend when new requirements come in.
I consistently build initial versions of features, like this to-do list, that meet immediate needs but then become rigid when new requirements, like adding due dates, appear. I'm constantly refactoring. What habit should I change to anticipate common extensions and build more flexible foundations from the start, so I stop wasting time on constant rewrites?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?

Questions people actually ask

honest answers, no sign-up

Every task here was seen in the real world. Someone doing the job named it, a real job ad asked for it, or a lot of people asked about it online.

If nothing real showed a task, it is not on the page. That is the whole rule.

They are the same job approached four ways, because what you need depends on where you are.

Get it done today. Make it easy for the next person to say yes to. Work out the right move when you are stuck. Learn the pattern so the job stops coming back.

For most of these jobs it can carry the heavy thinking - draft it, sort it, check it, rehearse it with you.

It cannot sit in your chair, take the blame when a number is wrong, or notice what nobody wrote down. Let it do the first 80%. Keep the last 20% that is truly yours.

No. Copy any prompt and paste it into the AI you already use. No account, no score, no wall in the way.

Any of them. The prompts describe the work rather than naming a product, so they are not tied to one assistant.

That is also why they keep working when you switch.

Change it freely. Every prompt is a starting line, not a rule.

Put in your real numbers, your real names and your real deadline. The more you make it yours, the better the answer comes back.

The tasks come from real job ads, published job data and the questions people ask in public forums.

The steps come from HTML's own documentation, with practitioner sources for the traps the manual does not mention.

Push once. Ask it to sharpen the weakest part and to say what it assumed.

Most wrong answers come from a missing detail rather than a bad prompt - tell it the thing it could not know.