expense-tracker
Just say what you spent — your AI logs it, categorizes it, and tracks it against your budget. No apps, no forms, no friction. Supports natural language like 'spent $45 at Costco' or 'split a $90 dinner with Jake'. 16 auto-categories, monthly budget alerts, weekly and monthly reports. Runs entirely local — your spending data stays on your machine.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/nicholasrae/nicholasrae-expense-trackerExpense Tracker Skill
Track, categorize, and budget personal expenses through natural conversation. Users text expenses in plain language and the AI logs them, tracks budgets, and generates reports.
Skill Directory
skills/expense-tracker/
├── SKILL.md # This file — AI instructions
├── references/
│ ├── categories.json # Category definitions + keyword matching
│ └── budgets.json # Monthly budget limits (user-editable)
├── scripts/
│ ├── add-expense.sh # Add expense to ledger
│ ├── query.sh # Query/filter expenses
│ └── budget-check.sh # Check spending vs budget
├── templates/
│ ├── weekly-report.md # Weekly report template
│ └── monthly-report.md # Monthly report template
└── expenses/
└── ledger.json # Transaction data (auto-created)
1. Parsing Natural Language Expenses
When a user mentions spending money, extract these fields:
| Field | Required | How to Extract |
|---|---|---|
| amount | Yes | Dollar amounts: "$45", "45 dollars", "forty-five bucks", "45.99" |
| vendor | Yes | Named entity after "at", "from", "to", or contextual merchant name |
| category | Auto | Match vendor/context against references/categories.json keywords |
| date | Default today | "today", "yesterday", "last Tuesday", "on 2/14", explicit dates |
| notes | Optional | Anything extra the user adds — "for the party", "work expense" |
Parsing Examples
| User Says | amount | vendor | category | date | notes |
|---|---|---|---|---|---|
| "spent $45 at Costco" | 45 | Costco | Groceries | today | |
| "grabbed lunch for $18 at Chipotle yesterday" | 18 | Chipotle | Dining | yesterday | |
| "$120 electric bill" | 120 | Electric company | Utilities | today | |
| "filled up the tank, 55 bucks at Shell" | 55 | Shell | Gas/Transport | today | |
| "Netflix $15.99" | 15.99 | Netflix | Subscriptions | today | |
| "dropped $200 at Target for birthday stuff" | 200 | Target | Shopping | today | birthday stuff |
| "refund from Amazon $35" | -35 | Amazon | Shopping | today | refund |
| "paid rent $2000" | 2000 | Rent/Landlord | Housing | today | |
| "spent $5.50 at starbucks yesterday" | 5.50 | Starbucks | Dining | yesterday | |
| "vet visit for the dog, $280" | 280 | Vet | Pets | today | |
| "car insurance $180" | 180 | Car insurance | Insurance | today | |
| "groceries and some clothes at Target $150" | 150 | Target | Shopping | today | groceries and clothes (ask user to split or pick) |
| "got reimbursed $45 for work lunch" | -45 | Work | Dining | today | reimbursement |
Ambiguous Categories
When a vendor could match multiple categories (e.g., "Walmart" could be Groceries or Shopping):
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-nicholasrae-nicholasrae-expense-tracker": {
"enabled": true,
"auto_update": true
}
}
}Tags
Related Skills
vynn-backtester
Run trading strategy backtests with natural language — powered by Vynn
q-kdb-code-review
AI-powered code review for Q/kdb+ — catch bugs in the most terse language in finance
olo-sec-scanner
SEC EDGAR filing analysis for M&A due diligence — extract financials, detect risks, and track corporate events from 10-K, 10-Q, and 8-K filings
decision-ledger
从纪要、聊天或项目材料中提取决策、负责人、截止时间、前提假设与撤销条件。；use for decision, meeting, governance workflows；do not use for 编造不存在的决策, 替代法律审计.
candidate-tracker
候选人追踪系统。触发场景：用户要求管理候选人池，记录状态、设置提醒、生成标签。