$ ls -la drwxr-xr-x docs/ $ run script
◆ Bash

Set variables from command output

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

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskI need to grab the latest build number from the 'build-info.log' file, which is always the last…+
I need to grab the latest build number from the 'build-info.log' file, which is always the last line, and then set that as the BUILD_VERSION for my deployment script. Then, use that BUILD_VERSION to tag the new release in our artifact repository.
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 push this new release, I need to make sure my script is reliably pulling the correct…+
Before I push this new release, I need to make sure my script is reliably pulling the correct version. Right now, it's just taking the last line of a log file, but sometimes there are error messages there. How can I make sure I'm always extracting the actual version string, which looks like 'v1.2.3-beta.4', even if there's noise in the log?
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 new build script just failed, saying BUILD_VERSION was empty. I thought 'tail -1…+
The new build script just failed because it tried to use an empty BUILD_VERSION.
The new build script just failed, saying BUILD_VERSION was empty. I thought 'tail -1 build-info.log' would always give me something, but clearly not. The build-info.log file might be empty, or the last line might not be a version. I'm afraid of pushing a broken deployment. What's the most robust way to extract the version and ensure it's not empty before proceeding, or fail cleanly if it is?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI keep losing time because I manually eyeball log files for specific patterns or values before…+
I keep having to manually check log files for specific patterns before I can proceed with the next step in a script.
I keep losing time because I manually eyeball log files for specific patterns or values before I can proceed with the next step in a script. This feels clunky and error-prone. What habit should I change to automate this pattern extraction reliably, so I don't miss critical info or waste time confirming it?
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 Bash'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.