Bookkeeping Automation

Automate bookkeeping workflows by parsing bank statements (CSV/OFX/QIF), categorizing transactions using rules or an LLM, reconciling accounts, generating expense reports, and detecting duplicates. Use when: automating transaction categorization, building reconciliation pipelines, processing bank exports, or generating expense summaries without manual data entry.

213 stars 34 forksFinance & Crypto

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TerminalSkills/skills --skill bookkeeping-automation
Manual install
git clone --depth 1 https://github.com/TerminalSkills/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/bookkeeping-automation ~/.claude/skills/bookkeeping-automation

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Bookkeeping Automation

## Overview

Automate the repetitive parts of bookkeeping: import bank statements (CSV, OFX/QFX, QIF), categorize transactions with ordered keyword rules and an optional LLM for the leftovers, remove repeated rows safely, reconcile against the statement balance, and print an expense report. Money is always `Decimal`, never `float`. The code below was run on sample CSV, OFX (SGML, version 1.02) and QIF files with Python 3.12 and ofxtools 1.1.1. The output is a draft for a human to review before anything is posted to Xero, QuickBooks or a ledger; it is not tax or accounting advice.

## Instructions

1. Save the two modules below as `parser.py` and `pipeline.py` in a scratch folder and install the one dependency: `pip install ofxtools` (inside a virtual environment). The imports below assume those file names (the stdlib `parser` module was removed in Python 3.10, so there is no clash).
2. Look at the header row of the CSV export and pass its real column names, date format and (if the bank uses separate debit and credit columns) `debit_col`/`credit_col`. Banks differ and change their exports, so never assume a layout; check one row by eye.
3. Run `categorize_by_rules` first (free and deterministic). Rules are ordered and the first match wins, so list specific phrases above general ones. Rules only match whole words and respect direction (money in vs out).
Read the full skill on GitHub

Details

Skill name
bookkeeping-automation
Path
skills/bookkeeping-automation/SKILL.md
License
Apache-2.0
Repo updated
8 November 2026

FAQ

What does the Bookkeeping Automation skill do?

Automate bookkeeping workflows by parsing bank statements (CSV/OFX/QIF), categorizing transactions using rules or an LLM, reconciling accounts, generating expense reports, and detecting duplicates. Use when: automating transaction categorization, building reconciliation pipelines, processing bank exports, or generating expense summaries without manual data entry.

How do I install the Bookkeeping Automation skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TerminalSkills/skills --skill bookkeeping-automation. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Bookkeeping Automation popular?

It lives in TerminalSkills/skills, which has 213 GitHub stars and 34 forks.

Related skills

3dsmax Rendering

213

TerminalSkills/skills

Scripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.

Other34

3dsmax Scripting

213

TerminalSkills/skills

Covers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.

Productivity & Notes34

3proxy

213

TerminalSkills/skills

3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.

DevOps & Cloud34

Causal Inference Root Cause

200

lyndonkl/claude

Systematically investigates causal relationships to identify true root causes rather than correlations or symptoms. Distinguishes genuine causation from spurious associations, tests competing explanations, and designs interventions addressing underlying drivers. Use when investigating why something happened, debugging systems, analyzing failures, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?

Finance & Crypto25

Algo Trading

213

TerminalSkills/skills

Build algorithmic trading systems — backtesting, strategy development, live execution, and risk management. Use when tasks involve backtesting trading strategies, connecting to exchange APIs (Binance, Alpaca, Interactive Brokers), implementing technical indicators, portfolio optimization, order execution, risk management rules, market data processing, or building trading bots. Covers both crypto and traditional markets.

Finance & Crypto34

Concept Rediscovery Walk

200

lyndonkl/claude

Guides a learner to invent a math or ML concept themselves through a Socratic walk — a sequence of small guessable questions that ends with the learner stating the formal definition unprompted. The 3Blue1Brown signature move. Use when the learner is meeting a foundational concept (eigenvectors, gradient, attention, softmax, KL divergence) for the first time, when prior exposure produced memorization without understanding, or when the user says "explain it from scratch", "I want to really get it", "build it up for me", or "where does this come from".

Finance & Crypto25

Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.