Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    receipt expense report

    1

    Transform raw receipts and mileage into formatted, policy-checked expense reports with automated file renaming.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    receipt expense report

    receipt expense report

    Example session with this skill installed

    I have 5 receipts from my London trip in the 'receipts' folder. Please process them for my May expense report in USD. The mileage was 45 miles. My company limit is $50 for meals.

    • Read your context and instructions
    • Compiled the receipt expense report
    • Generated the document

    I have analyzed the 5 receipts provided and calculated the mileage. I identified one meal receipt that exceeds your company policy limit and flagged it for your review.

    Expense report · London Trip May 2024 · ⚠️ 1 check

    CategoryAmount (GBP)RateAmount (USD)
    Transport (Uber)18.501.2723.50
    Meal (Pret A Manger)12.401.2715.75
    Meal (Dishoom)48.001.2760.96
    Hotel (The Hoxton)185.001.27234.95
    Supplies (Waterstones)15.001.2719.05
    Mileage (45 miles)-0.6730.15
    Total$384.36

    Summary:

    • Total Expenses: $384.36
    • Company Card: $234.95 (Hotel)
    • To be reimbursed: $149.41

    Checks:

    • ⚠️

    Policy Violation: Dishoom receipt ($60.96) exceeds the $50.00 meal limit. Please provide a business justification or confirm if I should cap this at $50.00.

    • ✅ Duplicates: No duplicate receipts found.
    • ✅ Files: All 5 receipts mapped and renamed.

    Files generated:

    • expense-report.xlsx
    • expense-report.html
    • receipts/ (01 to 05 renamed files)

    Next steps

    1. Provide a justification for the Dishoom meal over-limit.
    2. Confirm if any of these were paid with a company card other than the hotel.
    3. Run the final build command to export the XLSX file.

    expense-report.xlsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Expense reporting is a manual grind of reading faded receipts, calculating exchange rates, and renaming files. This skill automates the extraction and validation of expense data, generating audit-ready reports that finance teams actually accept.

    What it does

    • Data Extraction reads dates, merchants, totals, and VAT from photos, PDFs, or emails.
    • Multi-currency Handling applies specific exchange rates from card statements or prescribed company rates with full rounding support.
    • Policy Validation flags duplicates, weekend expenses, missing receipts, and limit violations before submission.
    • File Organization renames and numbers receipt copies to match report line items exactly.
    • Automated Calculations handles mileage, advances, and splits personal items from corporate bills.

    How it works

    1. Ingest by providing receipt files; the agent extracts core data and asks for missing context like business purpose or payment method.
    2. Configure by setting the report currency, period, and any specific company policy limits or mileage rates.
    3. Build using the provided Python script to generate the structured report and the organized receipt folder.
    4. Audit the generated checks for warnings or errors, fixing data or providing justifications until the report is clean.

    Frameworks & tools

    Uses a specialized Python 3.8 script (expenses.py) for processing. Works within environments supporting image analysis and local file system operations like Claude Code or Desktop.

    Why this beats prompting it yourself

    Generic prompts often hallucinate currency conversions or fail to maintain a strict one-to-one mapping between files and report lines. This skill uses a local execution script to ensure mathematical precision and physical file management that chat-only prompts cannot perform.

    Use cases

    • Business Travel to compile a week of foreign currency receipts into a single reimbursement request.
    • Monthly Filing for freelancers or employees managing recurring hardware and software subscriptions.
    • Tax Prep to extract VAT data and organize supporting documentation for accountants.

    Known limitations

    Requires Python 3.8+ for report generation. The script does not have network access, so users must provide exchange rates or card statements manually.

    Requires Python 3.8+ environment. No automatic network-based exchange rate fetching. User must manually provide business purpose and cost centers.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Python

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill includes the specialized 'expenses.py' Python script, the AI agent prompt configuration, and a structured template for generating audit-ready reports.

    Unlike generic AI prompts that may struggle with math or file organization, this skill uses a local Python script to ensure 100% mathematical accuracy and physical file renaming for your receipts.

    This skill requires a Python 3.8+ environment and works best with agents that have local file system access, such as Claude Code or Desktop, to facilitate receipt organization.

    The skill supports image files (JPG, PNG), PDFs, and text-based email receipts, extracting key data like VAT, merchant names, and dates from each.

    For security and privacy, the script does not have network access; you simply provide your specific company rates or card statement totals during the configuration step.

    Yes, the agent is designed to flag potential issues like duplicate entries, weekend transactions, or missing documentation before you finalize the report.

    New in Workflow Automation