invoice-scanner

Extract structured data from invoice images and PDFs into categorized Markdown reports.

598|75|Updated Jan 10, 2026
One-click install
npx skills add https://github.com/wlzh/skills --skill invoice-scanner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: invoice-scanner
Source: https://github.com/wlzh/skills/tree/main/invoice-scanner
Command: npx skills add https://github.com/wlzh/skills --skill invoice-scanner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the recognition and extraction of key information from invoices (transport, lodging, meals, etc.) and generates a structured, categorized report to simplify expense tracking and reimbursement.

Core Features & Use Cases

  • End-to-end invoice recognition: automatically identify invoice types (city transport, long-distance transport, lodging, and others) and extract fields such as date, amount, invoice number, merchant, and line items.
  • Smart categorization and reporting: aggregates data into four categories with totals, counts, and a Markdown report suitable for sharing.
  • Use Case: imagine a finance team receiving hundreds of receipts; run this Skill to automatically parse them, verify totals, and produce invoices.md with a consolidated summary.

Quick Start

Use the invoice-scanner to scan a directory or a ZIP file containing receipts, e.g. /receipts.

Frequently Asked Questions about invoice-scanner

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract data from multiple invoices in a ZIP file?

To extract data from invoice ZIP files, you can process directories or ZIP archives directly. The tool preprocesses local files using standard CLI tools to parse receipt images and PDFs without cloud services, generating a structured Markdown report.

Can I parse both PDF and image receipts for reimbursement reports?

Yes, you can parse both PDF and image receipts for reimbursement. The system recognizes domestic and international transport, lodging, and meal receipts, automatically extracting dates, amounts, invoice numbers, and merchants into categorized summaries.

What is the best way to categorize extracted invoice data for expense management?

The best way to categorize extracted invoice data is to aggregate parsed fields into four main categories. The system calculates totals and item counts, producing a Markdown expense report suitable for sharing and reimbursement tracking.

Does this invoice extraction tool require cloud services or external APIs?

No, this invoice extraction tool does not require cloud services or external APIs. It relies entirely on local file I/O, ZIP handling, and standard CLI tools to preprocess inputs and extract structured data from your receipts.

How do I automate expense reporting for hundreds of receipts?

You can automate expense reporting by running the scanner on a directory of receipts. It automatically identifies invoice types, verifies totals, extracts line items, and generates a consolidated invoices.md summary for your finance team.

What types of receipts are supported for automated data extraction?

Supported receipt types for automated data extraction include city transport, long-distance transport, lodging, and meals. The system identifies these domestic and international invoice types to extract key fields for expense management.