Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsCrypto Payment Reconciliation & Settlement Auditor
Automated crypto payment auditor for reconciling blockchain transactions, merchant invoices, and settlement reports.
$24.99
Crypto Payment Reconciliation & Settlement Auditor
Example session with this skill installed
Audit these two files: invoices.csv (Order_101, $500 USDC) and settlement_export.json (Tx_0xabc, 498.50 USDC). Check for fee discrepancies and match confidence.
- Read your context and instructions
- Compiled the crypto payment reconciliation
- Generated the data export
I have completed the reconciliation between the provided invoice record and the settlement export. The analysis identified a match with a minor value discrepancy due to network fees.
Crypto Payment Reconciliation & Settlement Audit
Period: 2023-10-27
Chains / assets: Ethereum (USDC)
Data sources and retrieval time: invoices.csv, settlement_export.json (Manual Upload)
Matching policy / tolerances: Exact Reference ID match; 1% amount tolerance
Evidence coverage: Complete for provided IDs
Executive Summary
One invoice was matched to one on-chain transaction. A total discrepancy of 1.50 USDC was detected, primarily attributed to network fees. No duplicate records were found.
Reconciliation Metrics
| Metric | Count | Amount / denomination | Notes |
|---|---|---|---|
| Total Invoices | 1 | 500.00 USDC | |
| Matched Payments | 1 | 498.50 USDC | |
| Net Discrepancy | 1 | -1.50 USDC | Explained by fees |
Invoice-to-Payment Matches
| Invoice ID | Candidate transaction / reference | Expected | Received | Difference | Match type / confidence | Status |
|---|---|---|---|---|---|---|
| Order_101 | 0xabc...efg | 500.00 | 498.50 | -1.50 | Exact ID / High | Settled |
Exceptions Register
| ID | Exception type | Invoice / transaction | Evidence | Amount | Severity | Recommended action |
|---|---|---|---|---|---|---|
| EXC-001 | Fee Discrepancy | Order_101 | Tx_0xabc | -1.50 USDC | Low | Review fee policy |
Network-Fee Review
| Observed Fee | Expected Fee | Denomination | Source | Difference | Caveats |
|---|---|---|---|---|---|
| 1.50 | 0.00 | USDC | Processor Export | 1.50 | Network fees deducted from net |
Next steps
- Verify if the merchant agreement requires the customer to cover the 1.50 USDC gas fee.
- Update the internal ledger for Order_101 to reflect the net settlement of 498.50 USDC.
- Archive this report for the monthly finance review.
invoices.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
Manual crypto reconciliation is a nightmare of fragmented data, shifting gas fees, and mismatched decimals. This skill automates the audit of merchant invoices against blockchain transactions and settlement exports to find the truth behind your payments.
What it does
- Multi-source reconciliation matches invoice IDs and order references against on-chain transaction hashes and processor settlement batches.
- Discrepancy detection flags underpayments, overpayments, and network fee anomalies with precise asset-specific math.
- Duplicate auditing identifies redundant settlement records and conflicting ledger entries across different data exports.
- Asset normalization handles chain-specific decimal precision, token contract verification, and fiat-to-crypto conversion tracking.
- Exception reporting generates a structured register of unresolved payments, ambiguous matches, and pending confirmations.
How it works
- Inventory and normalize raw data from invoices, block explorers, and payment processor exports.
- Execute matching hierarchy by prioritizing exact hashes and reference IDs before falling back to amount-time similarity.
- Calculate differences to isolate network fees, merchant fees, and net settlement amounts for every transaction.
- Produce audit deliverables including an executive summary, reconciliation metrics, and a prioritized remediation plan.
Frameworks & tools
This skill works with blockchain transaction exports (CSV/JSON), payment processor settlement reports (BitPay, Coinbase Commerce, etc.), and standard merchant accounting systems.
Why this beats prompting it yourself
Standard LLM prompts struggle with token decimal math and often hallucinate matches based on vague similarities. This skill enforces a strict matching hierarchy and specific normalization rules to ensure financial accuracy without initiating unauthorized on-chain actions.
Use cases
- Monthly close audits to reconcile a high volume of crypto orders against merchant bank settlements.
- Fee leakage analysis to detect if network gas costs or processor fees are exceeding expected margins.
- Payment troubleshooting for customers claiming they paid while the dashboard shows a pending status.
- Data integrity checks after migrating between payment processors or accounting sub-ledgers.
Known limitations
Does not perform live blockchain lookups; relies entirely on supplied or tool-retrieved evidence. Cannot execute refunds or move funds. Matches are restricted to the provided data window.
Requires provided data exports or explorer evidence. Cannot move funds or sign transactions. Matching accuracy depends on timestamp consistency across datasets.
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 any payment.
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 20 days ago
Permissions
No special permissions declared or detected