- Home
- Skills
- Finance & Accounting
- AI Accounts Reconciliation Investigation Agent
Works with the AI Agents you already use
AI Accounts Reconciliation Investigation Agent
Investigate accounting mismatches and reconcile financial records with traceable evidence and exception reporting.
$39.99
AI Accounts Reconciliation Investigation Agent
Example session with this skill installed
Reconcile these two files: 'Jan_Bank_Statement.csv' and 'GL_Cash_Account.csv'. The currency is USD. Ignore differences under $0.05. Identify why the closing balances don't match.
- Read your context and instructions
- Compiled the ai accounts reconciliation
- Generated the data export
I have analyzed 452 transactions from Jan_Bank_Statement.csv and 448 transactions from GL_Cash_Account.csv. I have identified 412 exact matches, 18 probable matches within the $0.05 tolerance, and 26 exceptions requiring review.
Reconciliation Investigation Report
Executive Summary
- Period: January 2024
- Source A (Bank): 452 rows | Total Credits: $142,500.00 | Total Debits: ($128,400.00)
- Source B (GL): 448 rows | Total Credits: $141,800.00 | Total Debits: ($127,200.00)
- Net Residual Unexplained: $450.00
Exception Register
| Exception ID | Type | Source A Ref | Source B Ref | Amount Diff | Priority | Facts/Hypothesis |
|---|---|---|---|---|---|---|
| EXC-001 | Missing in GL | CHK-8821 | - | ($350.00) | High | Check cleared bank Jan 31; likely outstanding at month-end. |
| EXC-002 | Amount Mismatch | DEP-990 | DEP-990 | $100.00 | Med | Bank shows $1,200, GL shows $1,100. Possible data entry error. |
| EXC-003 | Fee | BANK_FEE_JAN | - | ($50.00) | Low | Monthly service charge not yet recorded in general ledger. |
| EXC-004 | Duplicate | TXN-5521 | TXN-5521 | $0.00 | High | Two identical entries in GL for one bank credit. |
Control Total Bridge
- GL Closing Balance: $24,600.00
- Add: Outstanding Checks: $350.00
- Less: Unrecorded Bank Fees: ($50.00)
- Adjusted GL Balance: $24,900.00
- Bank Statement Balance: $25,350.00
- Remaining Unexplained: ($450.00)
Next steps
- Review GL for duplicate entry TXN-5521 and prepare a reversal.
- Confirm if DEP-990 was a manual entry error or a bank processing error.
- Post the $50.00 monthly bank fee to the interest/bank charges account.
Jan_Bank_Statement.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Financial data mismatches, missing entries, and timing gaps can stall month-end closes and hide operational errors. This skill investigates accounting reconciliation differences across bank statements, general ledgers, and subledgers to provide a traceable audit trail for human review.
What it does
- Multi-source comparison matches transactions between ledger exports, bank statements, vendor reports, and payment processor data.
- Explainable matching uses a staged strategy to identify exact, composite, probable, and split/aggregate matches with confidence labels.
- Exception classification categorizes findings into missing entries, amount mismatches, currency differences, and timing gaps.
- Reconciliation bridging calculates the movement from opening to closing balances, separating explained timing items from unexplained residuals.
- Investigation reporting generates a structured exception register with observed facts, plausible hypotheses, and recommended next steps.
How it works
- Evidence profiling identifies data quality issues like duplicate rows or malformed amounts in your source files.
- Data normalization standardizes dates, currency codes, and amount signs without altering original source values.
- Automated matching applies your defined date and amount tolerances to link records across datasets.
- Exception analysis prioritizes mismatches based on materiality, age, and operational impact.
Frameworks & tools
Works with CSV, Excel, or JSON exports from ERP systems like NetSuite, SAP, and QuickBooks, as well as bank statements and payment processor settlement reports.
Why this beats prompting it yourself
Generic prompts often force-match similar amounts or hallucinate missing data to "fix" the balance. This skill uses a disciplined accounting workflow that separates evidence from hypothesis and maintains a strict audit trail, ensuring every finding is grounded in your provided files.
Use cases
- Bank reconciliation identifying outstanding checks, deposits in transit, and bank fees.
- Intercompany settlement matching cross-entity balances and identifying FX conversion errors.
- Vendor statement audits finding duplicate invoices or unapplied credits in accounts payable.
- Payment processor audits reconciling Stripe or PayPal settlements against internal order logs.
Known limitations
Does not independently approve journal entries or certify financial statements. Requires a second source dataset for cross-source reconciliation. Cannot prove a transaction never occurred, only that it is missing from provided files.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
Requires two or more datasets for reconciliation. Does not interface directly with ERP APIs; works on exported data. Cannot authorize journal entries or official financial filings.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 8 days ago