An intelligent reimbursement management assistant that automates receipt recognition, travel allowance calculation, and organized document filing.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install expense-assistant
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install expense-assistant using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Expense Assistant?
Expense Assistant is a sophisticated AI agent skill designed to streamline the end-to-end workflow of business and travel expense reporting. By leveraging multimodal AI capabilities, it identifies key data from invoices, transport tickets, and consumption receipts, ensuring that every expense is accounted for and properly categorized. This Openclaw Skills integration helps professionals eliminate the manual drudgery of renaming files and calculating complex travel subsidies.
The skill excels at distinguishing between business hospitality costs and travel-related expenditures. It automatically applies corporate policies—such as calculating daily transport subsidies based on trip duration—and prepares a comprehensive reimbursement package. With its automated file naming and organizational structure, users can transition from a pile of digital receipts to a structured, audit-ready submission in seconds.
Expense Assistant Use Cases
- Automatically extracting data from business meal invoices, receipts, and menu photos for hospitality reporting.
- Calculating travel duration and associated transport subsidies from trip application screenshots.
- Managing complex transport reimbursement by distinguishing between direct travel tickets (flights/trains) and local transport subsidies (gas, tolls, parking).
- Bulk renaming and organizing receipt files for easy upload to corporate OA systems during monthly reimbursement cycles.
How Expense Assistant Works
- The user provides raw materials such as invoice PDFs, travel screenshots, or photos of physical receipts to the Openclaw Skills interface.
- The assistant parses the documents using OCR and multimodal LLM logic to extract dates, amounts, locations, and vendors.
- It classifies the expense into hospitality, travel, or transport subsidy categories based on predefined logic (e.g., train tickets are excluded from local transport allowance).
- The system calculates totals and subsidies according to trip duration (e.g., ¥1600 for ≥10 days, ¥800 for <10 days).
- Upon request, the skill renames all files according to a standardized format (Date-Location-Amount-Type) and generates a JSON-based summary report.
Expense Assistant Setup
To enable Expense Assistant, ensure your environment has the necessary PDF parsing utilities installed. This skill is part of the Openclaw Skills ecosystem.
# Ensure PDF text extraction tools are available
sudo apt-get install poppler-utils
# Initialize the expense directory
mkdir -p "Expense Assistant/Business Hospitality"
mkdir -p "Expense Assistant/Travel Expenses"
mkdir -p "Expense Assistant/Transport Subsidy"
Expense Assistant Data Schema & Taxonomy
The skill organizes data within the Expense Assistant/ directory using a structured JSON and file-based taxonomy:
| Directory | File Type | Purpose |
|---|---|---|
Business Hospitality/ |
record.json |
Stores meal dates, locations, and participant counts. |
Travel Expenses/ |
record.json |
Tracks trip duration and transport tickets (Flight/High-speed rail). |
Transport Subsidy/ |
record.json |
Logs加油 (Gas), taxi, and parking receipts used for allowance offsets. |
*/ (Subfolders) |
Named Files | Renamed source files: YYYYMMDD-Loc-Amt-Type.ext |
Expense Assistant Advanced Features
- Multi-modal recognition: Analyzes not just invoice text but also photos of dishes and water bills to validate business hospitality.
- Automated Policy Enforcement: Built-in logic to handle variable transport subsidy tiers based on travel length.
- Smart File Renaming: Automatically renames source files and moves them to relevant directories for a clean, exportable workspace.
- Custom Reimbursement Cycles: Supports default cycles (e.g., 26th of last month to 25th of current month) with user-defined overrides.
SKILL.md
Loading
Related Openclaw Skills
Universal Extractor
A multi-service content extraction tool that converts URLs, articles, and complex file formats into clean, structured text.
Sexy-Claw
Sexy-Claw is an automated AI agent skill that discovers and recommends high-value social media influencers and video content based on personalized aesthetic preferences.
AI Reliability Layer
A collection of three micro-services focused on repairing broken JSON, validating response rules, and generating guaranteed structured data for AI agents.
Data Model Selector
A technical decision framework for selecting between relational, document, and graph data models based on data shape and access patterns.
Stock Pulse
An intelligent A-share decision dashboard that transforms raw stock data into actionable AI-powered buy, sell, and hold signals.
ideas2tasks
An automated system that converts raw ideas into structured agile tasks using a virtual Scrum team.
Featured*
