statement analyzer

Financial statements are messy. Banks swap debit and credit columns, exports skip transactions, and transfers between accounts get counted as expenses. This skill processes raw bank statements, credit card exports, and expense app CSVs to provide a reconciled, categorized view of where money actually went.

What it does

• Multi-source reconciliation matches bank balances with transaction lists to ensure zero data loss.
• Deduplication removes internal transfers between your own accounts and credit card bill payments to avoid double-counting.
• Automated categorization uses a pattern-matching engine to sort spending into groups like family, investments, and utilities.
• Interactive profiling asks for context on recurring transfers and unknown payees to build a personalized financial map.
• Report generation produces a self-contained HTML dashboard and a JSON summary of all month-end balances.

How it works

1. Ingest statements by listing accounts, checking date coverage, and converting PDFs to structured CSVs.
2. Parse the raw data using provided scripts to verify that opening and closing balances match transaction totals.
3. Refine the analysis by answering specific questions about large unknown transactions and internal account names.
4. Generate the final HTML report and a summary markdown file containing the month-by-month financial breakdown.

Frameworks & tools

This skill uses Python 3 for data processing. It requires openpyxl for Excel files and pdfplumber for PDF extraction.

Why this beats prompting it yourself

LLMs often hallucinate arithmetic or lose track of transactions in long statements. This skill uses deterministic Python scripts to handle the math while using the AI only for categorization and user interaction, ensuring the final balance is always accurate.

Use cases

• Auditing a full year of spending across multiple bank accounts and cards.
• Identifying why a bank balance is lower than expected by tracking income versus all outflows.
• Visualizing the ratio of investments to discretionary spending.
• Preparing a clean summary of month-end balances for accounting or tax purposes.

Known limitations

Category accuracy depends on merchant name quality in bank exports. Users must manually remove passwords from encrypted PDF statements before processing.