Agent skill

Expense Categorization

by seb1n in seb1n/awesome-ai-agent-skills

Classify expenses by category, department, and tax deductibility from transaction data.

MITAuto-check passedBusiness, Finance & HR

Install Expense Categorization

skills CLI
$ npx skills add seb1n/awesome-ai-agent-skills --skill expense-categorization -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install seb1n/awesome-ai-agent-skills expense-categorization --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/finance-and-accounting/expense-categorization .claude/skills/expense-categorization && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
expense-categorization
GitHub stars
206
Token cost
~2.4k tokens
SKILL.md length
942 words
Files
1
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Classify expenses by category, department, and tax deductibility from transaction data.

  • Works in 6 steps: Receive Expense Data → Parse Description and Merchant → Classify Expense Category → …
  • The user requests expense categorization
  • SKILL.md covers Workflow, Usage, Examples and Best Practices, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Expense Categorization is an agent skill from seb1n/awesome-ai-agent-skills. Classify expenses by category, department, and tax deductibility from transaction data. Use when the user requests expense categorization or provides relevant inputs for this workflow.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Accounting and bookkeeping and Tax preparation. The repository describes itself as: 103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and other Agent Skills-compatible tools. Complete SKILL.md… The licence is MIT.

When your agent uses it

  • The user requests expense categorization
  • Provides relevant inputs for this workflow

Example prompts

  • “/expense-categorization”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Receive Expense Data
  2. Parse Description and Merchant
  3. Classify Expense Category
  4. Assign Department and Cost Center
  5. Flag Tax-Deductible Items
  6. Generate Categorized Summary

What it can do on your machine

Read from SKILL.md and the folder at commit 75865a5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are csv).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Expense Categorization loads about 2.4k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 942 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from seb1n/awesome-ai-agent-skills at commit 75865a5, republished under its MIT licence (© seb1n). 942 words, ~2,379 tokens.

Download SKILL.mdSave it as .claude/skills/expense-categorization/SKILL.md (or your agent's skills folder).
name
expense-categorization
description
Classify expenses by category, department, and tax deductibility from transaction data. Use when the user requests expense categorization or provides relevant inputs for this workflow.
license
MIT
metadata.author
community
metadata.version
1.0

Expense Categorization

Automatically classify business expenses into accounting categories, assign department cost centers, and flag tax-deductible items from raw transaction data. This skill processes credit card statements, bank feeds, and expense reports to produce clean, categorized output suitable for bookkeeping, tax preparation, and spend analytics.

Workflow

  1. Receive Expense Data Accept transaction data as CSV, bank statement text, or structured records. Required fields: date, amount, and description or merchant name. Optional fields: card last four digits, employee name, department, receipt notes. Normalize date formats and currency to a consistent standard.

  2. Parse Description and Merchant Extract the merchant name from the transaction descriptor, stripping out authorization codes, location suffixes, and card network prefixes. Map common merchant name variations to canonical names (e.g., "AMZN MKTP US" → "Amazon", "GOOGLE *GSUITE" → "Google Workspace"). Use the merchant category code (MCC) when available as a secondary signal.

  3. Classify Expense Category Assign each transaction to a primary category based on merchant identity, MCC, description keywords, and amount patterns. Standard categories: Travel & Lodging, Meals & Entertainment, Software & SaaS, Office Supplies, Professional Services, Advertising, Utilities, Insurance, Shipping & Postage, Equipment, Training & Education, Miscellaneous.

  4. Assign Department and Cost Center Route each expense to the appropriate department based on the cardholder, project codes in the description, or pre-configured rules. Apply default department assignments for known merchants (e.g., AWS charges → Engineering, HubSpot → Marketing).

  5. Flag Tax-Deductible Items Mark expenses that qualify for tax deduction based on category and business purpose. Apply IRS rules for meals (50% deductible for business meals, 100% for company events), home office, vehicle mileage, and professional development. Flag items that need substantiation — receipts, business purpose memo, or attendee lists.

  6. Generate Categorized Summary Output a categorized transaction list with totals by category, department, and tax status. Highlight any transactions that couldn't be confidently categorized (confidence < 80%) for manual review.

Usage

Provide transaction data in any tabular format. Specify any custom category mappings, department rules, or tax jurisdiction if not US federal.

Example prompt:

Categorize these November credit card transactions for our 15-person startup. We have Engineering, Marketing, and Operations departments. Flag tax-deductible items. Here's the CSV: [paste transactions]

Examples

Example 1: Monthly Credit Card Categorization

Input (CSV):

csv
date,amount,description,cardholder
2024-11-02,249.00,GITHUB TEAM PLAN,Sarah Chen
2024-11-03,1450.00,UNITED AIRLINES 0167823,Mike Torres
2024-11-03,189.50,MARRIOTT HOTEL CHI,Mike Torres
2024-11-05,42.67,UBER TRIP FKJE83,Mike Torres
2024-11-08,156.00,GOOGLE ADS 8834721,Lisa Park
2024-11-12,89.99,ZOOM VIDEO COMMS,Sarah Chen
2024-11-14,67.32,DOORDASH DASHER TIP,Operations
2024-11-18,4200.00,DELL TECHNOLOGIES,Sarah Chen
2024-11-22,350.00,COURSERA BUSINESS,Mike Torres
2024-11-25,23.45,STAPLES #1284,Operations

Output:

DateAmountMerchantCategoryDepartmentTax DeductibleNotes
2024-11-02$249.00GitHubSoftware & SaaSEngineeringYes (100%)
2024-11-03$1,450.00United AirlinesTravel & LodgingEngineeringYes (100%)Business travel
2024-11-03$189.50MarriottTravel & LodgingEngineeringYes (100%)Business travel
2024-11-05$42.67UberTravel & LodgingEngineeringYes (100%)Ground transport
2024-11-08$156.00Google AdsAdvertisingMarketingYes (100%)
2024-11-12$89.99ZoomSoftware & SaaSEngineeringYes (100%)
2024-11-14$67.32DoorDashMeals & EntertainmentOperationsYes (50%)Needs business purpose memo
2024-11-18$4,200.00DellEquipmentEngineeringDepreciationSection 179 eligible
2024-11-22$350.00CourseraTraining & EducationEngineeringYes (100%)
2024-11-25$23.45StaplesOffice SuppliesOperationsYes (100%)

Summary:

CategoryTotal% of Spend
Equipment$4,200.0061.5%
Travel & Lodging$1,682.1724.6%
Training & Education$350.005.1%
Software & SaaS$338.995.0%
Advertising$156.002.3%
Meals & Entertainment$67.321.0%
Office Supplies$23.450.3%
Total$6,817.93100%
Example 2: Flagging Misclassified Expenses

Input: Review existing categorizations for accuracy.

Output — Correction Report:

DateAmountMerchantCurrent CategoryCorrected CategoryReason
2024-11-07$320.00WeWorkOffice SuppliesRent & FacilitiesCo-working space is rent, not supplies
2024-11-10$85.00Blue ApronOffice SuppliesMeals & EntertainmentMeal delivery service miscoded
2024-11-16$599.00Adobe CreativeTrainingSoftware & SaaSCreative Cloud is a software subscription, not training
2024-11-29$175.00Lyft BusinessMiscellaneousTravel & LodgingBusiness ground transportation should be under travel

Impact: Reclassifying these 4 transactions shifts $1,179.00 across categories, affecting department budgets and tax deduction calculations. The Adobe correction reduces the Training & Education deduction by $599 and increases the Software & SaaS deduction by the same amount.

Show full SKILL.md (335 more words)Show less

Best Practices

  • Build and maintain a merchant-to-category mapping dictionary. Start with the 50 most common merchants in your transaction history and expand over time.
  • Set a confidence threshold (recommended: 80%) below which transactions are routed for human review rather than auto-categorized.
  • Review categorization accuracy monthly — track precision and recall by category to identify systematic errors.
  • Always separate personal and business expenses before categorization. Flag transactions from personal merchants (grocery stores, streaming services) for review.
  • Apply consistent rules for edge cases like meals during travel (Travel vs. Meals) and document the policy.
  • Keep tax deductibility rules current with the applicable tax year — IRS rules change frequently for categories like meals, entertainment, and vehicle expenses.

Safety Boundaries

  • Treat the output as analytical support, not individualized financial, tax, investment, or accounting advice.
  • Preserve source data and expose assumptions, formulas, units, and reconciliation checks so a reviewer can reproduce the result.
  • Do not initiate payments, transactions, journal entries, filings, or account changes without explicit user authorization.
  • Require a qualified professional to review material decisions, regulated filings, or conclusions based on incomplete data.

Edge Cases

  • Split transactions: A single purchase at a warehouse store may include both office supplies and snacks. If the receipt is available, split into separate line items with distinct categories.
  • Foreign currency transactions: Categorize based on the merchant and purpose, not the currency. Record both the original currency amount and the converted amount. Watch for duplicate entries from currency conversion fees.
  • Refunds and chargebacks: Match refunds to the original transaction and apply the same category as a negative entry. Don't create a new "refund" category — it distorts spend analytics.
  • Recurring vs. one-time: Identify recurring charges (same merchant, similar amount, monthly cadence) and flag any that stop unexpectedly or change amount by more than 10%.
  • Ambiguous merchants: When a merchant name maps to multiple possible categories (e.g., Amazon could be office supplies, software, or equipment), use the amount and cardholder's department as tiebreakers. Amounts under $100 from Amazon default to Office Supplies; over $500 default to Equipment.

© seb1n, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in finance-and-accounting/expense-categorization of seb1n/awesome-ai-agent-skills.

Open the folder on GitHubat commit 75865a5

Compare with similar skills

Expense Categorization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Expense Categorization compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Expense Categorization this skillseb1n/awesome-ai-agent-skills206—~2.4kAutomated safety check: PassMIT
Invoice Organizerdavila7/claude-code-templates32k12 repos~2.9kAutomated safety check: PassMIT
Kanchi Dividend Us Tax Accountingtradermonty/claude-trading-skills3k1 repos~1.1kAutomated safety check: PassMIT
Payroll Operationscbrock84/headcount2k—~1.1kAutomated safety check: PassMIT
Financial Retentionmukul975/Privacy-Data-Protection-Skills295—~3.5kAutomated safety check: PassApache-2.0
Fondo Install Authjeremylongshore/tons-of-skills-marketplace2.8k—~883Automated safety check: PassMIT

Similar skills

  • Invoice Organizer

    davila7/claude-code-templates

    Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders.

    32k GitHub starsUsed in 12 repos~2.9k tokens
    Business, Finance & HRAuto-check passed
  • Kanchi Dividend Us Tax Accounting

    tradermonty/claude-trading-skills

    Provide US dividend tax and account-location workflow for Kanchi-style income portfolios.

    3k GitHub starsUsed in 1 repo~1.1k tokens
    Business, Finance & HRAuto-check passed
  • Payroll Operations

    cbrock84/headcount

    Runs the pay cycle so it is right, on time, and provable — the calendar and cutoffs, what feeds pay from the HRIS and time systems, gross-to-net and the deductions in it, multi-jurisdiction…

    2k GitHub stars~1.1k tokensUpdated 20 days ago
    Business, Finance & HRAuto-check passed
  • Financial Retention

    mukul975/Privacy-Data-Protection-Skills

    Implements financial records retention requirements across EU directives (5-7 years), SOX Section 802 (7 years), MiFID II (5-7 years), tax records, payment data, and AML obligations under AMLD.

    295 GitHub stars~3.5k tokensUpdated 6 mo ago
    Business, Finance & HRAuto-check passed
  • Fondo Install Auth

    jeremylongshore/tons-of-skills-marketplace

    Set up Fondo account and configure integrations with Gusto, QuickBooks, and bank accounts for automated startup bookkeeping and R&D tax credits.

    2.8k GitHub stars~883 tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Tax Ebookkeeping Context

    kazukinagata/shinkoku

    Background context for the Electronic Bookkeeping Act (電子帳簿保存法) in the shinkoku tax filing plugin.

    364 GitHub stars~242 tokensUpdated 29 days ago
    Business, Finance & HRAuto-check passed

More from seb1n/awesome-ai-agent-skills

All 91 skills in this repo
  • Agent Red Teaming

    seb1n/awesome-ai-agent-skills

    Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.

    206 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Eu AI Act Readiness

    seb1n/awesome-ai-agent-skills

    Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…

    206 GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Human In The Loop

    seb1n/awesome-ai-agent-skills

    Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows.

    206 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • MCP Server Building

    seb1n/awesome-ai-agent-skills

    Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests.

    206 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Skill Supply Chain Audit

    seb1n/awesome-ai-agent-skills

    Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk.

    206 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Spreadsheet Analysis

    seb1n/awesome-ai-agent-skills

    Inspect, profile, clean, reconcile, analyze, visualize, and verify spreadsheet data while preserving formulas, formatting, types, and source files.

    206 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Expense Categorization

What does Expense Categorization do?

Classify expenses by category, department, and tax deductibility from transaction data. Expense Categorization is an agent skill from seb1n/awesome-ai-agent-skills. Classify expenses by category, department, and tax deductibility from transaction data.

When should I use Expense Categorization?

Expense Categorization fits situations like: the user requests expense categorization; provides relevant inputs for this workflow.

How do I install Expense Categorization in Claude Code?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill expense-categorization -a claude-code`. Or copy the skill folder (finance-and-accounting/expense-categorization in seb1n/awesome-ai-agent-skills) into .claude/skills/expense-categorization in your project. Claude Code loads it when a task matches its description.

How do I install Expense Categorization in Codex?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill expense-categorization -a codex`. Or copy the skill folder (finance-and-accounting/expense-categorization in seb1n/awesome-ai-agent-skills) into .agents/skills/expense-categorization in your project. Codex loads it when a task matches its description.

Can I use Expense Categorization in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add seb1n/awesome-ai-agent-skills --skill expense-categorization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/expense-categorization, .gemini/skills/expense-categorization, .github/skills/expense-categorization and .opencode/skills/expense-categorization in your project.

What does Expense Categorization need to run?

SKILL.md names no scripts, command-line tools or credentials: Expense Categorization is instructions for the agent only.

Does Expense Categorization access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Expense Categorization safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Expense Categorization use?

Expense Categorization is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Expense Categorization use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Expense Categorization?

Skills that share tags, products or a category with Expense Categorization: Invoice Organizer (davila7/claude-code-templates, 32k stars), Kanchi Dividend Us Tax Accounting (tradermonty/claude-trading-skills, 3k stars), Payroll Operations (cbrock84/headcount, 2k stars) and Financial Retention (mukul975/Privacy-Data-Protection-Skills, 295 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Expense Categorization?

seb1n (a GitHub user) maintains it in seb1n/awesome-ai-agent-skills, which has 206 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on August 9, 2026.

Source: seb1n/awesome-ai-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.