Agent skill

Invoice Processing

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

Extract, validate, and categorize invoice data against purchase orders and GL codes.

MITAuto-check passedDocuments & Office

Install Invoice Processing

skills CLI
$ npx skills add seb1n/awesome-ai-agent-skills --skill invoice-processing -a claude-code

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

GitHub CLI
$ gh skill install seb1n/awesome-ai-agent-skills invoice-processing --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/invoice-processing .claude/skills/invoice-processing && 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
invoice-processing
GitHub stars
206
Token cost
~1.9k tokens
SKILL.md length
784 words
Files
1
Skills in repo
92
Repo updated
First seen
Licence
MIT

At a glance

Extract, validate, and categorize invoice data against purchase orders and GL codes.

  • Works in 6 steps: Receive and Parse Invoice → Extract Line Items and Totals → Validate Against Purchase Order → …
  • The user requests invoice processing
  • 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

Invoice Processing is an agent skill from seb1n/awesome-ai-agent-skills. Extract, validate, and categorize invoice data against purchase orders and GL codes. Use when the user requests invoice processing or provides relevant inputs for this workflow.

Its SKILL.md is about 1.9k 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 Documents & Office, covering Forms and invoices. 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 invoice processing
  • Provides relevant inputs for this workflow

Example prompts

  • “/invoice-processing”

Workflow steps

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

  1. Receive and Parse Invoice
  2. Extract Line Items and Totals
  3. Validate Against Purchase Order
  4. Categorize by GL Code
  5. Flag Discrepancies and Generate Output
  6. Generate Processing 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 json).

    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

Invoice Processing loads about 1.9k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 784 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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). 784 words, ~1,896 tokens.

Download SKILL.mdSave it as .claude/skills/invoice-processing/SKILL.md (or your agent's skills folder).
name
invoice-processing
description
Extract, validate, and categorize invoice data against purchase orders and GL codes. Use when the user requests invoice processing or provides relevant inputs for this workflow.
license
MIT
metadata.author
community
metadata.version
1.0

Invoice Processing

Extract structured data from invoices, validate fields against purchase orders and vendor records, categorize line items by general ledger (GL) codes, and flag discrepancies for review. This skill handles both single invoice processing and batch operations, producing clean, auditable output ready for import into accounting systems.

Workflow

  1. Receive and Parse Invoice Accept invoice data in any format — raw text, OCR output, structured JSON, or CSV. Identify the document type (standard invoice, credit memo, debit note, proforma) and extract the header block: invoice number, date, due date, vendor name, vendor address, and payment terms.

  2. Extract Line Items and Totals Parse each line item for description, quantity, unit price, extended amount, and tax. Validate that line item totals sum to the stated subtotal. Extract tax amounts, shipping charges, discounts, and the grand total. Flag any arithmetic inconsistencies between line items and totals.

  3. Validate Against Purchase Order Match the invoice to its corresponding PO by PO number, vendor, or line item descriptions. Compare quantities and unit prices. Compute a three-way match score across PO, goods receipt, and invoice. Flag invoices where price variance exceeds a configurable threshold (default: 2%) or quantities don't match.

  4. Categorize by GL Code Assign each line item to the appropriate general ledger account based on item description, vendor category, and historical patterns. Common mappings include office supplies → 6200, software subscriptions → 6500, professional services → 6300, raw materials → 5100. Apply department cost center codes where applicable.

  5. Flag Discrepancies and Generate Output Produce a structured record for each invoice with all extracted fields, validation status, GL assignments, and any flags. Group flags by severity: blocking errors (missing PO, total mismatch > 5%), warnings (minor price variance, missing fields), and informational (new vendor, first invoice from vendor).

  6. Generate Processing Summary For batch operations, produce a summary report showing total invoices processed, pass/fail counts, total dollar value, and a breakdown of flag types. List all blocked invoices requiring manual review with specific reasons.

Usage

Provide invoice data as text, structured data, or describe the invoices you need processed. Specify any PO data for validation and your GL code mapping preferences.

Example prompt:

Process this vendor invoice: Invoice #INV-2024-0847 from Acme Cloud Services, dated 2024-11-15, PO #PO-4521. Line items: 10x API Gateway licenses at $150/ea, 1x Premium Support at $2,400/yr. Tax 8.5%. Validate against PO and assign GL codes.

Examples

Example 1: Single Invoice Processing

Input:

Invoice #INV-2024-0847
Vendor: Acme Cloud Services (Vendor ID: V-1042)
Date: 2024-11-15 | Due: 2024-12-15 | Terms: Net 30
PO Reference: PO-4521

Line Items:
  1. API Gateway License (qty: 10, unit: $150.00) — $1,500.00
  2. Premium Support Annual (qty: 1, unit: $2,400.00) — $2,400.00

Subtotal: $3,900.00
Tax (8.5%): $331.50
Total: $4,231.50

Output:

json
{
  "invoice_number": "INV-2024-0847",
  "vendor": { "name": "Acme Cloud Services", "id": "V-1042" },
  "date": "2024-11-15",
  "due_date": "2024-12-15",
  "po_reference": "PO-4521",
  "line_items": [
    {
      "description": "API Gateway License",
      "quantity": 10,
      "unit_price": 150.00,
      "amount": 1500.00,
      "gl_code": "6500",
      "gl_name": "Software Subscriptions",
      "cost_center": "IT-200"
    },
    {
      "description": "Premium Support Annual",
      "quantity": 1,
      "unit_price": 2400.00,
      "amount": 2400.00,
      "gl_code": "6510",
      "gl_name": "Software Maintenance & Support",
      "cost_center": "IT-200"
    }
  ],
  "subtotal": 3900.00,
  "tax": 331.50,
  "total": 4231.50,
  "validation": {
    "arithmetic_check": "PASS",
    "po_match": "PASS",
    "price_variance": "0.0%",
    "three_way_match": "PASS"
  },
  "flags": []
}
Example 2: Batch Processing with Validation Errors

Input: 4 invoices from different vendors processed in batch.

Output — Error Report:

Invoice #VendorAmountStatusFlags
INV-2024-0847Acme Cloud Services$4,231.50PASS—
INV-2024-1193Delta Office Supply$892.40WARNINGUnit price $14.20 vs PO price $12.99 (+9.3%)
INV-2024-1205Spark Consulting$18,750.00BLOCKEDNo matching PO found
INV-2024-1210GreenLeaf Catering$1,345.00BLOCKEDLine item total $1,280 ≠ stated subtotal $1,345

Batch Summary:

  • Total Processed: 4
  • Passed: 1 (25%) — $4,231.50
  • Warnings: 1 (25%) — $892.40
  • Blocked: 2 (50%) — $20,095.00
  • Total Value: $25,168.90
  • Action Required: 2 invoices require manual review before payment authorization.
Show full SKILL.md (290 more words)Show less

Best Practices

  • Always verify arithmetic independently — never trust the stated totals without recalculating from line items.
  • Maintain a vendor-to-GL mapping table and update it as new vendors or expense types appear.
  • Set price variance thresholds appropriate to your industry: 2% for commodities, up to 10% for services with variable scope.
  • Require PO matching for all invoices above a configurable dollar threshold to prevent unauthorized spending.
  • Retain the raw invoice data alongside extracted fields for audit trail purposes.
  • Process invoices in batch during off-peak hours and route exceptions to AP staff immediately.

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

  • Invoices with no PO reference: Flag as requiring manual approval. Check if the vendor has a blanket PO or standing agreement that covers the charges.
  • Credit memos and negative amounts: Process as negative invoice entries. Validate that the credit references an existing invoice and that the credit amount doesn't exceed the original.
  • Multi-currency invoices: Extract the stated currency, apply the exchange rate as of invoice date, and record both the original and converted amounts.
  • Duplicate invoice detection: Check invoice number + vendor + amount + date against the last 90 days of records. Flag exact matches as likely duplicates and near-matches (same vendor + amount, different invoice number) as potential duplicates.
  • Partial shipments: When goods receipt quantity is less than PO quantity, validate the invoice against received quantity, not PO quantity. Hold remaining balance as open.

© 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/invoice-processing of seb1n/awesome-ai-agent-skills.

Open the folder on GitHubat commit 75865a5

Compare with similar skills

Invoice Processing 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.

Invoice Processing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Invoice Processing this skillseb1n/awesome-ai-agent-skills206—~1.9kAutomated safety check: PassMIT
Invoice Systemkazukinagata/shinkoku364—~778Automated safety check: PassMIT
Ar AgingWellApp-ai/Well345—~532Automated safety check: PassMIT
Clients Accountssickn33/agentic-awesome-skills47k1 repos~4.7kAutomated safety check: PassMIT
Payments Receivedsickn33/agentic-awesome-skills47k1 repos~3.5kAutomated safety check: PassMIT
Reading Invoicekazukinagata/shinkoku364—~525Automated safety check: PassMIT

Similar skills

  • Invoice System

    kazukinagata/shinkoku

    This skill should be used when the user asks about the invoice system (インボイス制度), qualified invoices (適格請求書), registration numbers (登録番号), input tax credits (仕入税額控除), the 20% special measure (2割特例)…

    364 GitHub stars~778 tokensUpdated 28 days ago
    Documents & OfficeAuto-check passed
  • Ar Aging

    WellApp-ai/Well

    Produce an accounts-receivable aging report and surface overdue invoices for a Well workspace.

    345 GitHub stars~532 tokensUpdated 7 days ago
    Documents & OfficeAuto-check passed
  • Clients Accounts

    sickn33/agentic-awesome-skills

    Client and account register: contacts, billing address, tax ID and basis, payment terms, invoice totals, amounts paid and outstanding balance.

    47k GitHub starsUsed in 1 repo~4.7k tokens
    Documents & OfficeAuto-check passed
  • Payments Received

    sickn33/agentic-awesome-skills

    Payments received log: reference, client and invoice, amount and currency, payment date and method, withholding tax, bank account, received-by and receipt-sent status.

    47k GitHub starsUsed in 1 repo~3.5k tokens
    Documents & OfficeAuto-check passed
  • Reading Invoice

    kazukinagata/shinkoku

    請求書の画像を読み取り構造化データを返す. An agent skill from kazukinagata/shinkoku.

    364 GitHub stars~525 tokensUpdated 28 days ago
    Documents & OfficeAuto-check passed
  • Fee Billing

    JoelLewis/finance_skills

    Build and manage advisory fee billing operations from fee schedule design through calculation, collection, revenue recognition, and compliance disclosure.

    205 GitHub stars~6.8k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from seb1n/awesome-ai-agent-skills

All 92 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
  • PDF Processing

    seb1n/awesome-ai-agent-skills

    Inspect, extract, OCR, create, merge, split, reorder, rotate, annotate, fill, redact, compress, secure, and verify PDF documents while preserving source files and visual fidelity.

    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

Questions about Invoice Processing

What does Invoice Processing do?

Extract, validate, and categorize invoice data against purchase orders and GL codes. Invoice Processing is an agent skill from seb1n/awesome-ai-agent-skills. Extract, validate, and categorize invoice data against purchase orders and GL codes.

When should I use Invoice Processing?

Invoice Processing fits situations like: the user requests invoice processing; provides relevant inputs for this workflow.

How do I install Invoice Processing in Claude Code?

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

How do I install Invoice Processing in Codex?

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

Can I use Invoice Processing 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 invoice-processing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/invoice-processing, .gemini/skills/invoice-processing, .github/skills/invoice-processing and .opencode/skills/invoice-processing in your project.

What does Invoice Processing need to run?

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

Does Invoice Processing 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 Invoice Processing 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 Invoice Processing use?

Invoice Processing 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 Invoice Processing use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 Invoice Processing?

Skills that share tags, products or a category with Invoice Processing: Invoice System (kazukinagata/shinkoku, 364 stars), Ar Aging (WellApp-ai/Well, 345 stars), Clients Accounts (sickn33/agentic-awesome-skills, 47k stars) and Payments Received (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Invoice Processing?

seb1n (a GitHub user) maintains it in seb1n/awesome-ai-agent-skills, which has 206 GitHub stars. The repository holds 92 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.