skills.rest
openJiuwen-ai
openJiuwen-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

financial-document-parser

Extract financial fields and line items from invoices, receipts, and bank statements.

2.5k|422|Updated Mar 5, 2026
Search Tags:#financial documents#expense reporting#expense categorization#invoice parsing#receipt OCR#bank statement extraction#json to csv
One-click install
npx skills add https://github.com/openJiuwen-ai/jiuwenswarm --skill financial-document-parser-openjiuwen-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: financial-document-parser
Source: https://github.com/openJiuwen-ai/jiuwenswarm/tree/main/jiuwenswarm/resources/agent/workspace/skills/financial-document-parser
Command: npx skills add https://github.com/openJiuwen-ai/jiuwenswarm --skill financial-document-parser-openjiuwen-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdfplumber, pdf2image, pytesseract, tesseract-ocr.

What problem does it solve?

It removes the manual effort of reading invoices, receipts, and bank statements by extracting key fields and line items into structured, usable data for reporting and expense tracking.

Core Features & Use Cases

  • PDF/Images/CSV parsing: Extracts financial document text and table data from PDFs, receipt images, and CSV statements.
  • Structured extraction: Identifies document type, document number, vendor, date, subtotal, tax, total, currency, and payment context (when present).
  • Expense categorization & insights: Classifies line items into common expense categories and generates basic summaries (top category, large transactions, tax-related notes).
  • Exports for downstream use: Produces Markdown reports plus JSON output, and can export CSV for spreadsheets/accounting workflows.
  • Real-world use case: Upload a batch of monthly invoice PDFs and automatically get expense summaries by category and a CSV suitable for bookkeeping or reconciliation.

Quick Start

Ask the assistant to parse your attached financial document and return a Markdown report with extracted totals and categorized line items.

Frequently Asked Questions about financial-document-parser

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

FAQPage Schema
How do I extract expense data from PDF invoices and receipts?▼

To extract expense data from PDF invoices and receipts, this Skill parses document text and tables to identify fields like vendor, date, subtotal, tax, and total, then structures them into Markdown reports and JSON output.

Can I use OCR to parse scanned bank statements and receipts?▼

Yes, you can parse scanned bank statements and receipts using an optional OCR fallback powered by tesseract-ocr, which extracts text from images when standard PDF text extraction is unavailable.

What is the best way to categorize line items from bank statements automatically?▼

The best way to categorize line items from bank statements here is through automatic keyword matching, which classifies extracted transaction details into common expense categories and generates basic summaries.

How do I export parsed financial document data to CSV for bookkeeping?▼

To export parsed financial document data to CSV for bookkeeping, the Skill converts structured JSON outputs into CSV format, allowing seamless integration with spreadsheets and accounting workflows.

Does pdfplumber work with tesseract-ocr for processing receipt images?▼

Yes, pdfplumber works alongside tesseract-ocr for processing receipt images; pdfplumber handles native PDF text and table extraction, while tesseract-ocr provides an OCR fallback for scanned documents.

Related Skills

Explore More Finance & Accounting Skills→
dkyazzentwatwadkyazzentwatwa
86

ocr-document-processor

Extract text from images and scanned PDFs using OCR with structured output.

Community
Advanced
aibangjuxinaibangjuxin
2

finance-tracker

Manage bookkeeping, expense tracking, and financial reporting for businesses.

Community
Intermediate
Quill-AgentQuill-Agent
3

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced
legoutlegout
3

image-ocr

Extracts text and structured data from images using OCR engines.

Community
Advanced