Import Transactions Agent Skill
> Import transactions from CSV, OFX, or QIF bank exports and deduplicate.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/openaccountant/skills --skill import-transactionsThe instruction itself
9 sections, as written by the authorImport Transactions
Overview
Import financial transactions from bank export files. Automatically detects file format by extension (.csv, .ofx, .qif) and identifies the bank (Chase, Amex, BofA, or generic) by inspecting column headers. Previews parsed transactions, deduplicates against existing data, and inserts new records.
Wilson Tools Used
transaction_search— check for existing transactions to prevent duplicatescategorize— apply categorization rules to newly imported transactions
Workflow
- Ask the user for the file path to their bank export.
- Detect the file format by extension:
.csv— parse as CSV, inspect headers to identify bank.ofx/.qfx— parse as OFX (Open Financial Exchange).qif— parse as QIF (Quicken Interchange Format)- For CSV files, identify the bank by header patterns:
- Chase:
Transaction Date,Post Date,Description,Category,Type,Amount,Memo - Amex:
Date,Description,Amount(orReference,Date,Description,Card Member,Amount) - Bank of America:
Date,Description,Amount,Running Bal. - Generic: any CSV with recognizable date, description, and amount columns
- Preview the first 5 parsed transactions for the user to confirm.
- Deduplicate by matching date + amount + description against existing transactions.
- Report how many new vs. duplicate transactions were found.
- Insert new transactions into the database.
- Offer to run
categorizeon the newly imported transactions.
Without Wilson
You can import transactions manually into any spreadsheet or accounting tool:
Downloading Exports
Chase:
- Log in at chase.com
- Go to the account > Statements & Documents
- Click Download account activity (top right of transaction list)
- Select date range and format: CSV, OFX/QFX, or QIF
- File downloads to your computer
American Express:
- Log in at americanexpress.com
- Go to Statements & Activity
- Click Download your Transactions (right side or under the kebab menu)
- Select date range, choose CSV or OFX/QFX
- Download
Bank of America:
- Log in at bankofamerica.com
- Go to the account > Information & Services tab
- Click Download transactions
- Select date range and format: Microsoft Excel (.csv), Quicken (.qfx), or QuickBooks (.qbo)
- Download
Generic / Other Banks:
Most banks offer CSV or OFX export from their transaction history page. Look for "Download," "Export," or a download icon near the date range selector.
Manual Import into a Spreadsheet
- Open the CSV in Excel or Google Sheets.
- Normalize columns to:
Date,Description,Amount,Category. - Make amounts negative for expenses, positive for income/credits.
- Remove duplicate rows using Data > Remove Duplicates (Excel) or the
=UNIQUE()function (Sheets). - Sort by date.
OFX/QIF Files
- OFX files are XML-based. You can open them in a text editor to inspect, or import directly into GnuCash, Quicken, or YNAB.
- QIF files are plain text. Each transaction starts with
D(date),T(amount),P(payee). You can convert QIF to CSV with online tools like qif2csv.com.
Important Notes
- Chase CSV exports use negative amounts for payments/credits and positive for charges. Wilson normalizes this (negative = expense, positive = income).
- Amex CSV has amounts where charges are positive. Wilson inverts the sign on import.
- OFX files contain a date range in the header — Wilson uses this to scope deduplication.
- Deduplication is based on date + amount + description. If you manually edited a transaction description in your bank's app, the edited version may import as a new record.
- Large imports (1000+ transactions) are batched in groups of 500 for performance.
Other skills for the same job
different authors, same section of the catalogue
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
How to use it
Take openaccountant/import-transactions from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.