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

Clean up and maintain data

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 Bash tasks

The same task, four prompts

today's deadline · the next reviewer · the stuck moment · the pattern
AExecute — do the immediate taskRemove all duplicate entries in the 'user_emails.csv' file based on the email column, keeping…+
Remove all duplicate entries in the 'user_emails.csv' file based on the email column, keeping the first occurrence. Overwrite the original file with the cleaned data.
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 import this new customer data into the CRM, clean it up. Standardize all phone numbers…+
Before I import this new customer data into the CRM, clean it up. Standardize all phone numbers to a 'XXX-XXX-XXXX' format, remove any leading/trailing whitespace from names, and flag any rows where the 'email' field is empty or not a valid email address.
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
CDecide — diagnose the stuck momentAfter the recent CRM migration, I'm finding duplicate customer records with conflicting…+
A recent data migration introduced inconsistencies, and I'm unsure which record is the 'source of truth'.
After the recent CRM migration, I'm finding duplicate customer records with conflicting information in the 'address' and 'phone' fields. I'm unsure which version is the most current or accurate, and merging them incorrectly could lead to bad sales outreach. What's the best way to identify the 'golden record' for these customers, and what's the safest approach to reconcile the data without losing critical information?
when the reply comes backPush once: ask it to sharpen the weakest part, and to say what it assumed. Helpful?
DBecome — change the patternI'm constantly fixing minor data entry errors—like inconsistent date formats or misspelled…+
I frequently spend too much time manually correcting data entry errors from various sources.
I'm constantly fixing minor data entry errors—like inconsistent date formats or misspelled company names—that come from different external partners. It's a repetitive and error-prone task. What habit should I change to proactively catch and standardize this incoming data before it even hits our main systems?
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.