Receipt Scanner Master

Parse receipt images and PDFs into structured line-item data.

Updated Sep 22, 2025
One-click install
npx skills add https://github.com/EGAdams/planner --skill receipt-scanner-master
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Receipt Scanner Master
Source: https://github.com/EGAdams/planner/tree/main/nonprofit_finance_db/.claude/skills/receipt-scanner
Command: npx skills add https://github.com/EGAdams/planner --skill receipt-scanner-master

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydantic, fastapi, google-gemini-api.

What problem does it solve?

Master the receipt scanning workflow to extract line items from receipts via OCR, validate data, and load it into the expenses database with metadata.

Core Features & Use Cases

  • OCR-powered parsing: extracts items, totals, and merchant details from receipts via OCR.
  • Validation & QA: ensures extracted data matches expected totals and categories, and supports debugging OCR issues.
  • Database Integration: stores parsed receipts and line items in the expenses and receipt_metadata tables.

Quick Start

Start the API or CLI workflow to parse a sample receipt, then save it to the database. Example: run the API endpoint /api/parse-receipt and follow up with /api/save-receipt.

Frequently Asked Questions about Receipt Scanner Master

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

FAQPage Schema
How do I extract line items and totals from receipt images using OCR?

Receipt Scanner Master uses OCR to parse JPG, PNG, WebP, and PDF receipts, extracting merchant details, line items, and totals. The Skill applies a model sequence (gemini-2.5-flash first, then fallbacks) to accurately capture per-item data from receipt images for expense tracking.

Can I validate extracted receipt data against expected totals and categories?

Yes. The Skill includes validation and QA workflows that verify extracted data matches expected totals and assigned categories, with built-in OCR debugging to catch and correct extraction errors before database storage.

How do I save parsed receipts and line items to a database?

Receipt Scanner Master provides API endpoints and CLI workflows to parse receipts and persist them to the expenses and receipt_metadata database tables. Items auto-save on categorization, with full receipt metadata captured on final persistence.

What file formats and image types does receipt scanning support?

The Skill processes JPG, PNG, WebP image formats and PDF files within web interfaces and API pipelines, validating images before OCR extraction to ensure consistent per-line-item parsing and database reliability.

Do I need to set up a separate database to store receipts?

Receipt Scanner Master integrates directly with the expenses and receipt_metadata database tables for storage. The Skill handles per-item auto-save and final receipt persistence, so you need database access but the Skill manages schema integration.

What's the best way to debug OCR accuracy issues in receipt parsing?

The Skill includes OCR accuracy debugging features to validate extraction results against expected totals and categories. QA workflows identify parsing errors, allowing you to correct extraction issues before committing data to the database.