home / skills / benchflow-ai / skillsbench / financial-document-parser

financial-document-parser skill

/registry/terminal_bench_2.0/full_batch_reviewed/terminal_bench_2_0_financial-document-processor/environment/skills/financial-document-parser

This skill extracts and analyzes data from invoices, receipts, and statements to categorize expenses, track patterns, and generate structured expense reports.

npx playbooks add skill benchflow-ai/skillsbench --skill financial-document-parser

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
4.8 KB
---
name: financial-document-parser
description: Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
---

# Financial Document Parser

Extract structured data from financial documents with automatic categorization and analysis.

## When to Use This Skill

Activate when the user:
- Provides invoices, receipts, or bank statements
- Asks to "parse this invoice" or "extract data from this receipt"
- Needs expense categorization
- Wants to track spending patterns
- Asks to generate expense reports
- Mentions financial document analysis
- Provides PDF or image of financial documents

## Instructions

1. **Identify Document Type**
   - Invoice (business to business)
   - Receipt (point of sale)
   - Bank statement
   - Credit card statement
   - Expense report
   - Tax document

2. **Extract Core Information**

   **For Invoices:**
   - Invoice number
   - Invoice date and due date
   - Vendor/supplier name and contact
   - Client/recipient name
   - Line items (description, quantity, unit price, total)
   - Subtotal, tax, and grand total
   - Payment terms
   - Payment methods accepted

   **For Receipts:**
   - Merchant name and location
   - Date and time
   - Items purchased
   - Individual prices
   - Subtotal, tax, total
   - Payment method
   - Last 4 digits of card (if present)

   **For Bank/Credit Card Statements:**
   - Statement period
   - Account number (last 4 digits)
   - All transactions (date, description, amount, balance)
   - Beginning and ending balance
   - Total credits and debits
   - Fees or interest charges

3. **Categorize Expenses**
   - Business expenses: Office supplies, software, equipment
   - Travel: Transportation, lodging, meals
   - Utilities: Internet, phone, electricity
   - Professional services: Legal, accounting, consulting
   - Marketing: Advertising, subscriptions
   - Entertainment: Client meals, events
   - Other: Miscellaneous

4. **Identify Patterns**
   - Recurring charges (subscriptions)
   - Duplicate charges
   - Unusual or high-value transactions
   - Tax-deductible expenses
   - Foreign currency transactions

5. **Generate Structured Output**
   - Create CSV-ready format
   - Summarize totals by category
   - Flag items needing attention
   - Calculate tax implications (if relevant)

## Output Format

```markdown
# Financial Document Analysis

## Document Details
- **Type**: Invoice / Receipt / Statement
- **Date**: [Date]
- **Vendor/Merchant**: [Name]
- **Document Number**: [Number]
- **Total Amount**: $X,XXX.XX

## Line Items
| Description | Quantity | Unit Price | Total |
|-------------|----------|------------|-------|
| [Item] | X | $XX.XX | $XX.XX |

## Financial Summary
- **Subtotal**: $X,XXX.XX
- **Tax**: $XXX.XX
- **Total**: $X,XXX.XX
- **Payment Method**: [Method]

## Expense Categorization
| Category | Amount | Items |
|----------|--------|-------|
| Software | $XXX | Slack, GitHub |
| Office | $XX | Supplies |

## Insights
- ✓ Tax-deductible business expenses: $X,XXX
- ⚠ Recurring charges detected: 3 subscriptions ($XXX/month)
- ℹ Foreign transaction fees: $XX

## Flagged Items
- [ ] Large expense ($X,XXX) - verify approval
- [ ] Duplicate charge detected on [date]

## Export Data (CSV Format)
```csv
Date,Vendor,Description,Category,Amount,Tax Deductible
2025-01-15,Adobe,Creative Cloud,Software,52.99,Yes
```

## Recommendations
- Track recurring $XXX/month for [subscription]
- Consider negotiating bulk discount with [vendor]
- Set up payment reminder for [invoice due date]
```

## Examples

**User**: "Extract data from this invoice PDF"
**Response**: Parse PDF → Extract vendor info, line items, totals → Categorize as business expense → Format as structured data → Generate CSV export

**User**: "Analyze my bank statement and categorize expenses"
**Response**: Extract all transactions → Categorize each (dining, software, travel) → Identify recurring charges → Calculate totals by category → Flag unusual transactions → Generate spending report

**User**: "Parse these 10 receipts and create an expense report"
**Response**: Process each receipt → Extract merchant, date, amount, items → Categorize expenses → Calculate totals → Generate consolidated report → Create CSV for expense submission

## Best Practices

- Preserve exact amounts (don't round)
- Maintain currency symbols and formats
- Note when data is unclear or illegible
- Flag suspicious or duplicate transactions
- Provide tax-relevant categorization
- Use standard expense categories
- Generate export-ready formats (CSV, JSON)
- Protect sensitive info (mask account numbers)
- Identify missing information (no date, unclear vendor)
- Calculate totals and verify against document
- Note discrepancies or calculation errors
- Include exchange rates for foreign currency

Overview

This skill extracts and analyzes data from invoices, receipts, bank and credit card statements, and other financial documents. It converts scanned PDFs and images into structured, export-ready data, categorizes expenses, detects recurring or suspicious charges, and produces concise expense summaries and recommendations.

How this skill works

Upload or provide a PDF/image and the skill identifies the document type, extracts core fields (vendor, dates, line items, totals, account identifiers), and preserves exact amounts and currencies. It automatically maps line items to standard expense categories, flags duplicates or unusual transactions, and outputs CSV/JSON-ready records plus a human-readable summary and action flags.

When to use it

  • You have invoices, receipts, or bank/credit statements to digitize and analyze
  • You need an expense report or CSV export for accounting or reimbursement
  • You want to identify recurring subscriptions or unexpected charges
  • You need to categorize transactions for tax or budget purposes
  • You must verify totals, flag duplicates, or check for calculation errors

Best practices

  • Provide the highest-quality scans or PDFs available to reduce OCR errors
  • Preserve original currency symbols and exact amounts; do not round
  • Mask or redact full account numbers; keep only last 4 digits when needed
  • Note illegible fields explicitly and flag items requiring user confirmation
  • Use standard expense categories and include tax-deductible tags where relevant

Example use cases

  • Parse a single invoice PDF to extract vendor, invoice number, line items, and due date, then export a CSV row
  • Process a batch of receipts to create a consolidated expense report grouped by category and date
  • Analyze a bank statement to list all transactions, flag recurring subscriptions, and highlight unusual high-value entries
  • Create a tax-focused summary that totals deductible expenses and identifies applicable taxes and fees

FAQ

What file types are supported?

PDFs and common image formats (JPEG, PNG); higher resolution improves accuracy.

How are sensitive numbers handled?

Full account numbers are masked by default; the last four digits may be kept for identification.

Can it detect recurring subscriptions?

Yes — it identifies repeated charges by merchant and amount pattern and summarizes frequency.