$ ~/registry/skill/anthropics-small-business-skills-close-month

SKILL

close-month

Name: close-month
Author: anthropics

Automate monthly close reconciliation, variance checks, P&L commentary, and packet export.

Stars

★ 22,528

Source

GitHub

Updated

2026-07-11

// securityCaution

Prompt only, no code
Open source

Summary

The material indicates an open-source, prompt-only workflow with no declared secrets, remote endpoints, or local code execution, so overall risk is low. Its business logic references QuickBooks, payment processors, and file export; if actual runtime relies on external connectors, related data-access and egress risks would stem from the host environment rather than this skill text itself.

CredentialsLow risk

The material explicitly states no required secrets or environment variables. The skill text itself does not ask the user for API keys or other credentials; if QuickBooks/Stripe/PayPal/Square/cloud-drive connectors are used at runtime, those credentials would be handled by the host connectors rather than collected directly by this skill.

Network egressLow risk

The system marks this as prompt-only and the metadata lists no remote endpoint hosts. Although the description references QuickBooks, PayPal, Stripe, Square, Google Drive, and OneDrive, the material does not show this skill directly implementing or configuring outbound connections, so there is no standalone egress red flag in the skill itself.

Code executionLow risk

There are no installation commands, script execution steps, binary downloads, or local process instructions. As a prompt-only skill, the material provides no evidence of local command execution or system-level capabilities.

Data accessCaution

By design, the workflow intends to handle sensitive financial data: QuickBooks transactions, processor settlements, receipt attachments, P&L data, and trial balances, and it may export files to local desktop or cloud storage. This appears to be a normal business scope rather than clear overreach, but it still warrants attention due to the sensitivity of the financial records and file export behavior.

Supply chainLow risk

The source is an open-source GitHub repository, making it auditable, and it is hosted under anthropics/knowledge-work-plugins. While the missing license, 0 stars, and unknown maintenance status create some continuity uncertainty, there is no indication of a closed-source payload, broken provenance, or obviously suspicious distribution, so the overall supply-chain risk remains low.

Recommendations

If enabling this skill in a host platform, apply least-privilege permissions to QuickBooks, payment-processor, and cloud-storage connectors.
Before exporting to desktop or cloud storage, verify that the output files do not include unnecessary customer-sensitive data or full credential-bearing attachments.
Review the repository source to confirm the skill is only a prompt template and to identify which external connectors are actually invoked.
Validate the workflow and exported artifacts with a test ledger or redacted data before using it in production finance operations.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "close-month" skill from askskill:
1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/small-business/skills/close-month/SKILL.md
2. Save it as ~/.claude/skills/close-month/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Run this month’s close

Prompt

Please run this month’s close: reconcile QuickBooks against all payment processors, flag all discrepancies, generate a P&L narrative, and export the full close packet.

Expected

Returns the monthly reconciliation results, discrepancy list, P&L commentary, and exported close packet.

Close a specific month and save it

Prompt

Please complete the monthly close for December 2024, produce reconciliation results and P&L analysis, and save the close packet to /Finance/Close/2024-12/.

Expected

Generates the close report and packet for the specified month and saves them to the given folder.

Investigate payment discrepancies

Prompt

Please run last month’s close, focusing on QuickBooks versus Stripe and PayPal transactions. List unmatched items, amount variances, possible causes, and include a brief P&L summary.

Expected

Outputs a payment-channel variance analysis, likely issue causes, and a concise financial performance summary.

// docs

Run the month-end close workflow. Reconcile, flag gaps, narrate the P&L, and export the close packet for the owner's records (and their accountant).

Parse arguments:

--month (default: previous calendar month) — YYYY-MM format
--save-to (default files) — files (Google Drive / OneDrive), desktop (local), or both

Step 1 — Reconcile

Trigger the month-end-prep skill workflow:

Pull all QuickBooks transactions for the target month.
Pull settlements from each connected payment processor (PayPal, Stripe, Square) for the same month.
Match QB entries to processor settlements by amount + date (±2 days).
Surface three gap categories:
- Unmatched processor settlements — money came in via PayPal/Stripe/Square but never landed in QB
- Unmatched QB deposits — QB shows income with no processor record (cash? wire? misclassified?)
- Variance lines — matched but amount differs (fees, refunds split)

Step 2 — Flag suspicious entries

Surface in the same report:

Uncategorized transactions — QB entries with no category
Suspicious duplicates — same amount, same vendor, within 3 days
Missing receipts — QB entries above $75 with no attachment

For each, recommend an action: categorize as X, delete duplicate, attach receipt from inbox.

Wait for owner to triage flagged items before generating the narrative. Do not auto-categorize or auto-delete.

Step 3 — P&L narrative

After triage, generate a plain-English P&L narrative:

{Month YYYY} closed at ${revenue} revenue ({+/-}{X}% vs prior month).
Top driver: {category/customer}. Biggest swing: {category} {direction} ${amount}
because {reason inferred from transactions}.

Margin: {X}% ({+/-}Y pts vs prior). {Cost-side commentary}.

Three notable items:
1. ...
2. ...
3. ...

Numbers come from QB; the why comes from cross-referencing top transactions, vendor names, and prior-month deltas.

Step 4 — Export the close packet

Generate two files:

close-packet-{YYYY-MM}.xlsx — multi-tab workbook:
- Reconciliation — QB ↔ processor match table with gap rows highlighted
- Flagged — uncategorized / duplicates / missing receipts
- P&L — formatted income statement with prior-month delta column
- Trial Balance — accounts + ending balances
close-packet-{YYYY-MM}.pdf — one-page summary: P&L narrative + top-line numbers + gap count

Save both to the chosen --save-to location. Filename format: close-packet-2026-04.xlsx etc.

Connector failures

If QuickBooks is unreachable, stop — reconciliation requires QB as the source of truth. If a payment processor (PayPal, Stripe, Square) is unreachable, run reconciliation against the available processors and note "PayPal not connected — PayPal settlements skipped from reconciliation" (or whichever is missing). If all processors are missing, run QB-only analysis and flag it.

Approval gates

Never auto-fix flagged items. Always show the gap, recommend an action, wait for the owner.
Never delete duplicates without explicit confirmation. Show both records side-by-side.
Saving the packet is auto — it goes to the owner's own drive.

Output

End the run with a one-paragraph recap: revenue, margin, gap count remaining (if any), file paths to the saved packet. If gaps were not all resolved, list them so the owner can revisit.