Intelligent Reimbursement Assistant (fb-expense-skill) for Openclaw

An intelligent finance skill that automates travel expense reporting, invoice OCR recognition, and corporate approval workflows.

gaogao605
v1.0.0
Mar 31, 2026
0
254
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install ocr-invoice

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install ocr-invoice 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 Intelligent Reimbursement Assistant (fb-expense-skill)?

The fb-expense-skill is a comprehensive financial management tool designed for AI coding agents to handle the complexities of corporate reimbursements. It provides a robust framework for recording various expense types—including transport, lodging, and meals—while ensuring strict adherence to company policies through automated compliance checks.

By integrating this tool into your Openclaw Skills library, you can empower AI agents to manage the entire lifecycle of an expense, from initial receipt capture and invoice verification to multi-stage approval routing and final payment tracking. It effectively eliminates manual data entry errors and speeds up the reimbursement cycle through intelligent automation.

Intelligent Reimbursement Assistant (fb-expense-skill) Use Cases

  • Automating the submission of travel expense reports after business trips.
  • Using OCR to extract data from uploaded flight or hotel invoices.
  • Monitoring reimbursement progress and sending reminders to approvers.
  • Performing regional budget analysis and checking expenses against employee rank standards.

How Intelligent Reimbursement Assistant (fb-expense-skill) Works

  1. The user provides expense data via text, voice, or by uploading an invoice image.
  2. The skill performs OCR to extract critical information like tax IDs, dates, and amounts.
  3. A compliance check is triggered to verify the invoice authenticity and check for duplicate submissions.
  4. The system matches the expense against pre-defined travel orders and city-tier spending limits.
  5. A structured reimbursement report is generated and submitted to the designated approval flow.
  6. Real-time updates are provided to the user as the report moves from pending to paid status.

Intelligent Reimbursement Assistant (fb-expense-skill) Setup

To utilize this skill, ensure you have python3 installed on your system.

# Verify python installation
python3 --version

# Install the skill via your agent manager
openclaw install fb-expense-skill

Intelligent Reimbursement Assistant (fb-expense-skill) Data Schema & Taxonomy

The skill organizes financial data into structured JSON objects. Key metadata fields include:

Field Description
expense_type Code for the category (TRANSPORT, HOTEL, MEAL, etc.)
invoice_info Nested object containing invoice number, code, and seller name
compliance_check Boolean flags for policy adherence and duplicate detection
approval_flow Array of steps detailing the approver name and current status
report_status Current state of the workflow (e.g., draft, pending_approval, paid)

Intelligent Reimbursement Assistant (fb-expense-skill) Advanced Features

  • Intelligent Deduplication: Prevents the same invoice from being reimbursed multiple times.
  • Multi-Level Approval Routing: Automatically escalates high-value or out-of-policy expenses to senior management.
  • Budget Execution Tracking: Provides real-time analytics on monthly spending against departmental budgets.
  • Policy Standard Enforcement: Automatically applies different spending caps based on employee rank and city tiers (e.g., Tier 1 cities vs. others).

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Bins python3
Github Stars: 0
forks: 0

Featured*