Reconcile the Ledger Against Bank Feeds

Manual reconciliation means comparing two spreadsheets line by line, hunting for matches by date and amount. A single missing receipt or duplicate payment can take an hour to trace.

That is the gap this drop closes. It is a finance & admin skill built for Gemini, and it takes about ten minutes to set up the first time. After that it runs in under a minute.

Who should use it

Finance managers and bookkeepers who process monthly reconciliations and need to identify missing entries or duplicates

How it works

The skill file does five things, in this order.

1. Export both datasets as CSV. Download your bank statement and your accounting ledger for the same period, both in CSV format

2. Upload both files to Gemini. Attach the bank CSV and the ledger CSV in a single conversation thread

3. Request a three-way comparison table. Ask Gemini to produce a table showing matched transactions, unmatched bank entries, and unmatched ledger entries

4. Check for near matches by logic. Ask Gemini to identify pairs that match in amount but differ by one or two days, or match in date but differ by small rounding

5. Export the flagged discrepancies. Request a CSV of only the unmatched and near-match items for follow-up investigation

What comes back

A reconciliation report that shows exact matches, probable matches, and items needing manual review, condensing days of work into minutes

The mistake to avoid

If your ledger uses reference codes and your bank statement includes them in the description field, ask Gemini to prioritize matching by code first. This catches transfers and standing orders that might otherwise appear as near matches only.

Running it

Save the prompt as a Gem so it is reusable, or paste it into Gemini with your files attached. If the task touches Sheets, Docs or Gmail, run it from the Workspace side panel so it can read the file you already have open.

Where this fits

On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.

In the file

I have uploaded two CSV files: one is my bank statement and the other is my accounting ledger, both covering {month} {year}.

Bank statement columns: {list bank columns, e.g. Date, Description, Debit, Credit, Balance}
Ledger columns: {list ledger columns, e.g. Date, Reference, Vendor, Amount, Category}

Please perform a reconciliation:

1. Identify all exact matches where the date and absolute amount are identical in both files
2. Create a summary table with three sections:
   - Matched transactions (show date, amount, description from bank, reference from ledger)
   - Unmatched bank transactions (items in bank statement with no ledger equivalent)
   - Unmatched ledger entries (items in ledger with no bank equivalent)
3. Look for near matches: transactions that match in amount but differ by 1-2 days, or match in date but differ by less than {tolerance amount, e.g. 5 AED}
4. Flag any potential duplicates: multiple ledger entries that could match the same bank transaction
5. Provide a count of matched, unmatched, and near-match items

For near matches, indicate the likely reason for the discrepancy (timing difference, rounding, fees).

Present the unmatched and near-match items in a format I can copy into a new CSV for follow-up.