Stella
PDFs and Excel

Remove duplicate rows in Excel, including the ones it misses

A 229-row mailing list down to its 180 real people, phone numbers kept.

Download StellaFree with the plan you already have.

A real run on 13 November 2026, on a Linux computer, using Claude Code with Opus, on a Claude plan. The waiting is sped up; it took 1 min 49 s in real time.

The short answer.

Data, Remove Duplicates only removes rows that match exactly, so “Jo@Mail.com ” and “jo@mail.com” both stay. Add a helper column with =LOWER(TRIM(C2)) on the email, then run Remove Duplicates on that column only, on a copy of the file. Stella (stella.sh) makes a clean copy where each email appears once, keeps the details from whichever duplicate had them, and keeps different people who share a name.

Stella does this on Windows, Mac and Linux.

What happened.

180 people from 229 rows in under 2 minutes. Checked afterwards against an answer key written before the run: exactly 180 people, everyone still there, nobody twice, both Sam Taylors kept, no phone number lost when only a duplicate had it, emails tidied, and the original list unchanged.

The newsletter, its subscribers and their details are fictitious, made for this run. The work is sped up 5×.

How Stella does it.

  1. Opens the mailing list in Documents (229 rows) and treats emails that differ only by capitals or spaces as the same person
  2. Merges each person's copies into one row, keeping the phone number from whichever copy had it and the name that isn't in all capitals
  3. Keeps each person's earliest sign-up date, which also dropped five dates set in the future
  4. Keeps people who share a name but have different emails, such as two Sam Taylors, as separate people
  5. Saves “Newsletter mailing list (deduplicated).xlsx” next to the original, with emails tidied to lower case, and lists names worth a human look

The prompt.

My newsletter mailing list spreadsheet in Documents has loads of people on it twice, sometimes with their email in capitals or with a space in it. Make me a clean copy where everyone is only on it once.

Paste it into Stella and press Enter.

This is the exact prompt from the recording. If your files are somewhere else, say where.

Do it yourself.

  1. Work on a copy

    Save the file under a new name first. Remove Duplicates deletes rows, and once you save there's no undo.

  2. Decide what makes a duplicate

    For a mailing list, the email address. Names aren't safe: two different people can share one. Dates and phone formats vary between copies of the same person.

  3. Add a clean key column

    Next to the data, add a column with =LOWER(TRIM(C2)) (C being the email) and fill it down. This removes leading and trailing spaces and capitals. For spaces inside an email, wrap it in SUBSTITUTE(…," ","").

  4. Keep the best copy

    Sort so the most complete copy of each person comes first (for example, sort the Phone column so filled cells come before blanks). Remove Duplicates keeps the first row it meets.

  5. Remove Duplicates on the key

    Select the data, Data, Remove Duplicates, untick every column except the key, and click OK. Excel says how many it removed. Delete the key column after, or keep it to check.

Where it stops.

  • Stella decided who is the same person by email address. People with no email, or one person with two addresses, need a rule from you; it listed eight same-name, different-email pairs rather than guess.
  • It made a copy and left the original as it was. Ask for the duplicates on a separate tab if you want to see what was merged.
  • The list's names, emails and phone numbers go to the AI model you use in Stella. The clean-up runs on your computer.
  • Recorded on Linux with a free Python library; the clean copy is a normal .xlsx for Excel or Numbers. The same works for CSV files.

Questions.

Why isn't Remove Duplicates removing my duplicates?

The rows aren't exactly the same: a capital letter, a space or a different phone format makes Excel treat them as different. Normalise a key column first (above).

How do I remove duplicates based on one column?

In the Remove Duplicates box, untick every column except that one. Excel keeps the first row for each value and deletes the rest of the row.

How do I just highlight duplicates instead?

Home, Conditional Formatting, Highlight Cells Rules, Duplicate Values. It has the same exact-match limit, so use the clean key column.

Can I combine two lists and then de-duplicate?
Is Stella free for this?

Yes. Free with the ChatGPT or Claude plan you already have. Sign in with your ChatGPT plan, or use your Claude plan through Claude Code, and this task costs nothing extra. New accounts also get a small free trial of Stella’s own models.

Can I control what Stella changes on my computer?

Yes. Stella works on Windows, Mac and Linux with your own files and shows each step in the chat, so you can watch it and stop it at any point. Tell it what it may not do, as the prompts on these pages do (“don't delete anything without asking”). In the Downloads recording it deleted nothing until it was told to go ahead. It also refuses commands that would wipe a whole disk, your home folder or system folders.

Checked against these sources on 13 November 2026.

Stella