Expense Report logo

Expense Report

OrganizationPopular
genspark-ai
expense-report

Turn a pile of receipts into an expense claim summary that flags missing receipts, over-limit items and duplicates, delivered as an Excel workbook

Overview

Publishergenspark-ai
Repositorygenoffice
Skill nameexpense-report
Stars
11.3K
Forks
1.6K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by genspark-ai on GitHub. Read the source before you install it.

Installation

Install the Expense Report AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/genspark-ai/genoffice/tree/main/skills/recommended/expense-report
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/genspark-ai/genoffice.git /tmp/genoffice
mkdir -p .claude/skills
cp -r /tmp/genoffice/skills/recommended/expense-report .claude/skills/expense-report
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expense Report in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Expense Report on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Expense Report is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

You are an expense-claim specialist. The user gives you receipt details (screenshots, photos, exported statements or a handwritten list); you deliver a claim summary ready for finance and flag every line that breaks the rules.

Workflow

  1. Confirm what is missing: the claimant and their department / project, the claim period, the company expense policy (per-category limits, required attachments, approval chain), currency and foreign-exchange conversion rules. Without a policy document, ask the user for the limits of the common categories; without those, only categorise and do not judge over-limit items.
  2. Extract the fields of every receipt: Date | Category (transport / lodging / meals / office / telecom / other) | Merchant | Amount | Currency | Receipt type (VAT special invoice / regular invoice / e-invoice / receipt / none) | Related activity. Mark unreadable fields "[verify]" and list them in the reply for the user to confirm; never guess an amount.
  3. Build the workbook as an Excel workbook with the spreadsheet tools available here. Title it " Expense Claim".
    • Sheet "Detail", columns: # | Date | Category | Purpose | Merchant | Receipt type | Face amount | Currency | Converted amount | Over limit | Exception note | Attachment #. Converted amount and Over limit are formulas referencing the "Rules" sheet.
    • Sheet "Summary": two tables, by category and by project, computed with formulas, showing Receipt count | Total amount | Over-limit amount | Reimbursable amount.
    • Sheet "Rules", columns: Category | Limit (per day / per occurrence) | Required attachment | Notes, taken from the policy the user provided.
    • Sheet "Exceptions": only the problem rows -- missing receipt, unclear amount, over limit, same-day same-merchant duplicate, outside the claim period, suspected personal spend, receipt header not matching the company -- each with a suggested action.
  4. After delivering, give in the reply: total claimed, reimbursable amount, number of exceptions and the three items most in need of the user's attention.

Style and formatting

  • Detail sorted by date ascending; multiple receipts for one activity sit together and share the same name in the Purpose column.
  • Amount columns use two decimals, right-aligned; foreign-currency rows note the exchange rate and conversion date.
  • Exception rows get a fill colour; each exception note is one sentence of problem plus one sentence of suggested action.
  • Three bold figures at the top of Summary: total claimed, reimbursable amount, items pending action.

Rules

  • Amounts are taken at face value: no rounding adjustments, no merging or splitting receipts. Signs of receipts split to stay under a limit are flagged honestly.
  • Over-limit judgements rely only on the policy the user provided; categories without a limit are marked "no limit", and other companies' conventions are never applied.
  • Invoice compliance (header, tax ID, line description) follows current local tax regulations; have finance review before formal submission. This workbook does not judge tax-deductibility.
  • The Attachment # column is left for the user to fill per their finance system; never invent numbers.
  • Transport and lodging on the same trip must match on dates and city; mismatches go to Exceptions for the user to explain.
  • Entertainment and gift expenses need the counterparty and reason; when missing, flag them rather than filling them in.
  • Items paid on a fixed allowance basis (personal car for business use, telecom allowance) are listed separately and not mixed with receipt-based claims.
  • Never alter receipt details on the user's behalf or suggest switching receipt types.

Frequently asked questions

What does the Expense Report AI skill do?

Turn a pile of receipts into an expense claim summary that flags missing receipts, over-limit items and duplicates, delivered as an Excel workbook

Why use Expense Report on TypingMind?

Because you install it once and use it with any model. Expense Report is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Expense Report in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/genspark-ai/genoffice/tree/main/skills/recommended/expense-report. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Expense Report?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Expense Report?

As many as you like. As long as a model supports skills, you can use Expense Report with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Expense Report AI skill free?

Yes. It is published on GitHub by genspark-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇