ar-health
Skill0 starsChanged 3 months agoMITView on GitHub
Run an accounts receivable health check. Use when the user asks "how's our AR?", "who owes us money?", "what's our outstanding balance?", "show me overdue invoices", "are there unapplied payments?", or wants an AR aging summary.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ap-healthSkill
- doc-doctorSkill
- recent-recordsSkill
- three-way-matchSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Field names are never guessed: Use only names from describe_entity (or the exact queries below).
- Very specific: line 19
Paginate: Default top is 50. If a call returns exactly top rows, repeat with skip= until a short page comes back - never report a full page …
- Distinctive: line 21
Large results may arrive as a file path: instead of inline JSON. Read the file and aggregate (jq / Python).
- Distinctive: line 147
Update date literals to today before running.
- Very specific: line 150
After identifying high-balance customers, use get_record(entity="Customer", id="<CustomerID>") to get their name and contact info.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Acumatica - AR Health Check
A multi-query accounts receivable audit. Run all steps and compile into a single report.
Acumatica mechanics (read first)
- Field names are never guessed. Use only names from
describe_entity(or the exact queries below). A wrong name infilter=/select=returns HTTP 500KeyNotFoundException. $orderbyis silently ignored. For "most recent", filter a narrow date window and widen (14 -> 30 -> 90 days), then sort client-side:filter="Date gt datetimeoffset'2026-06-22T00:00:00-04:00'"(compute the date from today).- Decimal literals fail in filters.
Amount gt 0returns "Type conversions are not supported" - drop the numeric clause and filter client-side. - Paginate. Default
topis 50. If a call returns exactlytoprows, repeat withskip=until a short page comes back - never report a full page as the complete total. - Large results may arrive as a file path instead of inline JSON. Read the file and aggregate (jq / Python); do not re-run the query hoping it shrinks.
- Always pass
select=with only the fields you need. StockItem and ItemWarehouse are enormous without it. - Link every document. Render the primary identifier (RefNbr / OrderNbr / ID) as a
Markdown hyperlink using the record's
browser_urlfield. - On any error, read the
hintfield in the tool response - the server translates common 500s into the corrective action. - Invoice
DueDatefilters can be dropped silently by the server - if you filter onDueDate, verify the returned rows actually honor the bound (or queryBillinstead for AP). This skill avoids the problem by pulling open invoices and bucketing byDueDateclient-side. - Payment's date field is
ApplicationDate, notDate- filteringPaymentonDatereturns 500.
Step 1 - Open invoices (AR balance)
list_records(
entity="Invoice",
filter="Type eq 'Invoice' and Status eq 'Open'",
select="ReferenceNbr,Customer,Date,DueDate,Amount,Balance,Description",
top=1000
)From results, compute client-side:
- Total open AR balance = sum of all
Balancevalues - Aging buckets by
DueDaterelative to today:- Current (not yet due)
- 1-30 days overdue
- 31-60 days overdue
- 61-90 days overdue
- 90+ days overdue
- Top 10 largest open balances (customer + amount)
Step 2 - Unapplied / open payments
list_records(
entity="Payment",
filter="Type eq 'Payment' and Status eq 'Open'",
select="ReferenceNbr,CustomerID,ApplicationDate,PaymentAmount,PaymentMethod,Description",
top=200
)These are received payments not yet applied to an invoice - may reduce net AR.
Total = sum of PaymentAmount.
Step 3 - Open prepayments / deposits
list_records(
entity="Payment",
filter="Type eq 'Prepayment' and Status eq 'Open'",
select="ReferenceNbr,CustomerID,ApplicationDate,PaymentAmount,Description",
top=200
)Deposits on file from customers - expected to offset future invoices.
Total = sum of PaymentAmount.
Step 4 - Open credit memos
list_records(
entity="Invoice",
filter="Type eq 'Credit Memo' and Status eq 'Open'",
select="ReferenceNbr,Customer,Date,Amount,Balance,Description",
top=200
)Pending credits that will reduce AR when applied.
Step 5 - Customer concentration (top debtors)
From the Step 1 results, group open balances by Customer and rank by total balance. Identify:
- Top 5 customers by outstanding balance
- Any single customer representing >20% of total AR (concentration risk)
Output format
AR HEALTH REPORT - [today's date]
==================================================
TOTAL OPEN AR: $[amount] ([N] invoices)
Unapplied Payments: -$[amount] ([N] payments on file)
Open Prepayments: -$[amount] ([N] deposits on file)
Open Credit Memos: -$[amount] ([N] credits pending)
--------------------------------------------------
NET AR EXPOSURE: $[amount]
AGING BREAKDOWN:
Current (not due): $[amount] ([N] invoices)
1-30 days overdue: $[amount] ([N] invoices)
31-60 days overdue: $[amount] ([N] invoices)
61-90 days overdue: $[amount] ([N] invoices)
90+ days overdue: $[amount] ([N] invoices) ⚠️
TOP 5 OUTSTANDING BALANCES:
1. Customer [ID/Name] $[balance] ([days] days outstanding)
2. ...
⚠️ ANOMALIES:
- [N] invoices 90+ days overdue (total: $[amount])
- [N] unapplied payments sitting idle
- Customer [X] has [N] separate open invoices - possible billing issueTips
- Update date literals to today before running.
Balanceon an Invoice is the remaining unpaid amount;Amountis the original total.Customeron the Invoice entity is the CustomerID string.- After identifying high-balance customers, use
get_record(entity="Customer", id="<CustomerID>")to get their name and contact info. - Net AR Exposure = Total Open AR - Unapplied Payments - Open Prepayments - Open Credit Memos.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

