Invoice Processing

Invoice Processing

When to Use

• Extracting data from PDF invoices
• Validating Factur-X or UBL structured invoices
• Classifying invoices by type, vendor, or account
• Detecting anomalies (duplicates, unusual amounts, missing fields)
• Mapping invoice fields to accounting entries

Extraction Pipeline

1. INPUT: PDF / Factur-X / UBL / image
2. DETECT FORMAT: structured XML embedded? → parse directly
   No XML? → OCR + field extraction
3. EXTRACT FIELDS: map to canonical schema
4. VALIDATE: required fields, amounts, VAT consistency
5. CLASSIFY: expense category, accounting account, vendor
6. OUTPUT: structured JSON + confidence scores

Canonical Invoice Schema

{
  "invoice_number": "FA-2026-042",
  "invoice_date": "2026-04-15",
  "due_date": "2026-05-15",
  "supplier": {
    "name": "Fournisseur SAS",
    "tax_id": "FR12345678901",
    "address": "12 rue Example, 75001 Paris"
  },
  "buyer": {
    "name": "Client SARL",
    "tax_id": "FR98765432109"
  },
  "lines": [
    {
      "description": "Prestation conseil",
      "quantity": 5,
      "unit_price": 200.00,
      "vat_rate": 20.0,
      "line_total": 1000.00
    }
  ],
  "subtotal": 1000.00,
  "vat_amount": 200.00,
  "total": 1200.00,
  "currency": "EUR",
  "payment_terms": "30 jours net"
}

Validation Rules

| Rule | Check | Severity | |------|-------|----------| | Required fields | invoicenumber, date, supplier, total | Critical | | Math consistency | sum(lines) = subtotal, subtotal + VAT = total | Critical | | VAT rate validity | Rate matches country standard rates | Warning | | Duplicate detection | Same number + supplier + amount | Critical | | Date logic | duedate >= invoice_date | Warning | | Currency | Valid ISO 4217 code | Warning |

Anomaly Detection

| Anomaly | Signal | Action | |---------|--------|--------| | Duplicate invoice | Same number + supplier + amount +/- 5% | Block, flag for review | | Round amount | Total is exact round number (1000, 5000) | Flag (common in fraud) | | Weekend/holiday date | Invoice dated on non-business day | Flag | | Unusual amount | > 3 standard deviations from vendor average | Flag for review | | Missing VAT | Taxable transaction with 0% VAT | Flag, check exemption |

What This Skill Does NOT Do

• Does not perform OCR (uses existing OCR output or structured XML)
• Does not approve or pay invoices (validation and extraction only)
• Does not connect to ERP systems (outputs structured data)
• Does not handle tax compliance (see fr-comptabilite)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: BuilderCed
• Source: BuilderCed/agent-skills
• License: MIT
• Homepage: https://skills.sh/BuilderCed/agent-skills

Install and usage instructions live in the source repository linked above.