← Back

Skills · Union Square Donuts

Skills for the donut shop.

A skill is a written procedure Claude follows — a workflow described once, in enough detail that it runs the same way every time. These seventeen cover most of the recurring finance work at a nine-location food business: two point-of-sale systems, cash counted by hand at every store, tips owed across both, bank and balance sheet reconciliations, the recurring journal entries, and a meals tax filing. Together they're what made a twenty-hour month-end close into a three-hour one.

These used to end in an import file I ran myself. They post straight to the books now, through an MCP connection — but only after I approve that specific entry. The skill shows me the draft, I say yes, it posts, and then it reads the entry back to prove it landed the way it was built.

Month-end close

square-sales-sync

Builds a balanced, QuickBooks-ready journal entry for multi-location Square sales over any date range. It pulls live from the Square reporting API, excludes third-party delivery apps, rolls locations up to accounting classes, maps product categories to revenue accounts, splits cash from card settlement, and books service charges and over/short — then writes a balanced entry and posts it once I've approved it.

This one took the longest to get right, and not because of the code. Five commercial products were demoed first. None of them got the mapping exactly right, and none were as fast.

Replaced $600 a month of software. The skill took ninety minutes to write.
  • Fires on "run the Square JE", "build the Square sales journal entry" for a date range
  • Produces A balanced journal entry, posted and read back, with the backup behind it as .xlsx
  • You step in You review the entry and its backup before it posts. Nothing lands without that yes
fenway-payout-summary

The food hall runs on a different point-of-sale system, so it reports separately. This pulls a sales-and-payment summary day by day — orders, gross, discounts, net, tax, tips, total collected — with a payment-by-tender breakdown underneath and totals that tie out.

Replaced Downloading the report out of the food hall's POS and rebuilding the calculations by hand in Excel formulas.
  • Fires on "pull the payout summary", "Toast sales for these dates", or month-end for that location
  • Produces A formatted workbook, one row per business day, with the tender breakdown reconciled
payroll-je

Takes the payroll reports package as it arrives — a PDF — plus the account mapping, and produces the journal entry with payroll detail broken out by department. At month end it also produces the accrual.

Replaced Multiple reports reconciled in Excel. District managers carry cost allocations across stores and employees work in more than one location — a payroll-to-QuickBooks sync on its own can't express either.
  • Fires on Uploading a payroll PDF, or "run the payroll JE", "accrue the payroll"
  • Produces An Excel workbook with departmental detail, and the entry posted with that workbook attached as backup
  • You step in The workbook is the review copy. You approve that payroll before the entry posts
tips-reconciliation-usd

Tips arrive from two different point-of-sale systems across every location. This pulls both, for whatever dates you specify, and reconciles them against each other so the two systems agree before anyone gets paid.

Replaced Pulling reports out of both POS systems by hand and combining them into Excel schedules.
  • Fires on "reconcile tips", "tips by location" — and it refuses to pull anything until you supply the dates
  • Produces A reconciliation table and a formatted summary workbook, every run
month-end-deposits-in-transit

Two separate reconciliations that both live in the gap between a month ending and the money arriving: physical cash collected but not yet deposited, and card payouts on the month's revenue that settle to the bank the following month. They're kept as distinct reconciliations in one workbook rather than netted together, because they break for different reasons.

Replaced The same manual routine — reports pulled from both POS systems and combined into Excel schedules.
  • Fires on Month-end close, "cash in transit", "payouts crossing month-end"
  • Produces One workbook, two reconciliations, each tying to its own ledger account
  • Access Read-only against every system it touches
depreciation-scheduler

Maintains the fixed asset register and the depreciation schedule behind it — additions, disposals, the monthly depreciation run, and the tie-out back to the fixed asset accounts in the general ledger.

Replaced An Excel sheet kept up by hand.
  • Fires on "add a new asset", "run depreciation", "process a disposal", "what's the NBV of our assets"
  • Produces An updated register and schedule, reconciled to the ledger

Reconciliations

The monthly tie-outs. Each of these ends in a number that has to agree with something outside the ledger — a bank statement, a drawer count, a signed lease — and says so plainly when it doesn't.

usd-bank-reconciliations

Reconciles the month across three operating accounts at two banks, reading the statements as they arrive as PDFs rather than waiting on a feed. It ties each account to the ledger and delivers all three as one formatted workbook, filed to the project and to Drive so the backup is where the next person would look for it.

Replaced Reconciling three bank accounts by hand each month, matching statement lines against the ledger one at a time.
  • Fires on "run the bank recs for September", or the statements landing in the Drive folder
  • Produces One workbook, one tab per account, each tied out to the ledger with the outstanding items listed
safe-drawer-reconciliation

Reconciles the cash that never leaves the building — safe and drawer balances at every location — against the ledger. It reads the counts by location from the cash tracker, compares them to what the books say should be sitting there, and proposes the entry for the difference.

Nine sites each holding float is nine ways for a balance to drift quietly, and a drawer that has been wrong since March is a much worse problem than one that was wrong last week.

Replaced Pulling safe and drawer counts for every location off the cash tracker and comparing them to the ledger by hand.
  • Fires on "reconcile the safes", or month-end for cash on hand
  • Produces The reconciliation by location and the entry for the variance
security-deposit-rec

Rolls the security deposit schedule forward to month end, by location, and ties it to the ledger. Deposits sit on the balance sheet for years and get touched twice a decade, which is exactly the kind of balance that turns out to be wrong during diligence.

Replaced Hand-rolling the by-location security deposit schedule forward each month and re-tying it to the ledger.
  • Fires on "roll the security deposits", or month-end close
  • Produces The updated by-location schedule tied to the ledger, filed to the project and Drive

Reporting & planning

location-pnl-allocations

Produces the fully-loaded P&L by location. A store's own P&L is the easy part; the useful part is pushing commissary and overhead costs out to the stores that actually drive them, following the management allocation methodology rather than splitting evenly.

Replaced Complex Excel files whose formulas broke.
  • Fires on "run the May allocation report", "fully-loaded P&L by location", "month-end allocations"
  • Produces A three-sheet workbook plus a refreshed allocation dashboard
usd-projection-update

Once a month closes, its actuals replace the forecast in the three-statement model and the projection rolls forward. Doing this by hand is where models quietly drift out of agreement with the books.

Replaced nothing This was the first five-year projection the business ever had. It didn't automate an existing process — it made one easier to build, iterate on, and keep updated.
  • Fires on "we closed August, update the projections", "refresh the model with actuals"
  • Produces The updated model with the closed month actualized and the forecast rolled

Recurring journal entries

Four entries that recur every month and were each, at one point, something I rebuilt by hand because the rule behind it lived in my head rather than anywhere a system could read.

square-ar-entry

Handles the month-end catering cutoff. Catering gets invoiced and paid on its own schedule, which has nothing to do with when the food was actually delivered, so it reads the invoices by service date and sorts them: unpaid invoices for work already delivered accrue to receivables, invoices already paid for work not yet delivered get deferred to customer deposits.

Both entries reverse the following month, so the cutoff corrects itself rather than needing to be remembered and unwound.

Replaced Pulling two reports by hand and making both entries manually — the accrual and the deferral — every month end.
  • Fires on "run the catering cutoff", or month-end close
  • Produces Two reversing entries with an Excel backup listing every invoice and its service date
honeycart-sales-reclass-entry

Online catering orders land in the ledger as income with no location and a generic sales account, because the ordering platform has no concept of either. This moves that revenue to the right location and the right sales account every month, so location reporting — which is how the business is actually managed — isn't quietly missing a channel.

Replaced Finding the unclassified online catering revenue each month and moving it to the right location and account by hand.
  • Fires on "run the online catering reclass", or month-end close
  • Produces The reclass entry, with the backup filed to Drive
kitchen-fee-reclass-entry

The point-of-sale system collects a kitchen fee and lands it in the same bucket as sales tax, where it sits looking like money owed to the state. It isn't — it's income. This moves it out of the tax liability and into income every month, which keeps the amount actually remitted to the state equal to the amount actually collected for it.

Replaced Pulling the report by hand each month and keying the journal entry.
  • Fires on "run the kitchen fee reclass", or month-end close
  • Produces The adjusting entry with an Excel backup
loan-interest-accrual

Accrues monthly interest on outstanding loans, day-weighted so a loan funded mid-month accrues from the day the money arrived rather than from the first of the month. Loan interest is the sort of accrual that gets skipped for three months and then booked as a lump, which makes every monthly P&L in between wrong.

Replaced Calculating the accrual by hand each month and keying the entry.
  • Fires on "accrue the loan interest", or month-end close
  • Produces A one-sheet summary showing the day-weighting, and the entry

Operations

square-donut-count-grab

Reconstructs what was actually on the shelf at any store at any past moment, by taking current inventory and replaying the change log backwards to the time in question. Answers the question you can't otherwise answer after the fact: how many did we have left, and of what.

Replaced nothing Nobody was doing this by hand, because it wasn't practical enough to ask. It's a question the business didn't previously have a way to answer.
  • Fires on "how many donuts did we have left", "what was on the shelf Saturday morning", "inventory snapshot at 3pm"
  • Scope Individual donuts by flavor, any location, any date or time
creditapps

Vendor credit applications all ask for the same thirty fields in a different order — entity details, banking, trade references. This fills them from a saved business profile instead of retyping them each time a new supplier wants net terms.

Replaced Filling out every new vendor application by hand, references and all.
  • Fires on Uploading a credit application, vendor form, or net-terms application PDF
  • You step in You review and sign before anything goes to the supplier

The other side of the same method — thirteen skills for a digital agency →