FreePublished on GitHub

extract-w-4-data

Extract structured fields from w-4 documents.

The English summary is being prepared. Showing the original description.

iterationlayer/skills

Works withn8n

See how to install

Files included (1)

SKILL.md13.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Extract W-4 Data

Tax and finance teams use this recipe to extract W-4 fields from official forms into structured JSON for review, routing, and downstream filing preparation.

APIs Used

Document Extraction (1 credit per page)

Prerequisites

You need an Iteration Layer API key. Get one at platform.iterationlayer.com during the 7-day trial.

For full integration guidance (SDKs, auth, MCP, error handling), see the Iteration Layer Integration Guide.

Implementation

curl -X POST https://api.iterationlayer.com/document-extraction/v1/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "files": [
    {
      "type": "url",
      "name": "w-4.pdf",
      "url": "https://example.com/documents/w-4-sample.pdf"
    }
  ],
  "schema": {
    "fields": [
      {
        "name": "employee_name",
        "type": "TEXT",
        "description": "Employee full name"
      },
      {
        "name": "social_security_number",
        "type": "TEXT",
        "description": "Employee Social Security number"
      },
      {
        "name": "address",
        "type": "ADDRESS",
        "description": "Employee address"
      },
      {
        "name": "filing_status",
        "type": "TEXT",
        "description": "Selected filing status"
      },
      {
        "name": "dependents_amount",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 3 dependent and other credits amount"
      },
      {
        "name": "other_income",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(a) other income"
      },
      {
        "name": "deductions",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(b) deductions"
      },
      {
        "name": "extra_withholding",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(c) extra withholding"
      },
      {
        "name": "is_signed",
        "type": "BOOLEAN",
        "description": "Whether the employee signature is present"
      },
      {
        "name": "signature_date",
        "type": "DATE",
        "description": "Date signed"
      }
    ]
  }
}'

import { IterationLayer } from "iterationlayer";

const client = new IterationLayer({ apiKey: "YOUR_API_KEY" });

const result = await client.extractDocument({
  "files": [
    {
      "type": "url",
      "name": "w-4.pdf",
      "url": "https://example.com/documents/w-4-sample.pdf"
    }
  ],
  "schema": {
    "fields": [
      {
        "name": "employee_name",
        "type": "TEXT",
        "description": "Employee full name"
      },
      {
        "name": "social_security_number",
        "type": "TEXT",
        "description": "Employee Social Security number"
      },
      {
        "name": "address",
        "type": "ADDRESS",
        "description": "Employee address"
      },
      {
        "name": "filing_status",
        "type": "TEXT",
        "description": "Selected filing status"
      },
      {
        "name": "dependents_amount",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 3 dependent and other credits amount"
      },
      {
        "name": "other_income",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(a) other income"
      },
      {
        "name": "deductions",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(b) deductions"
      },
      {
        "name": "extra_withholding",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(c) extra withholding"
      },
      {
        "name": "is_signed",
        "type": "BOOLEAN",
        "description": "Whether the employee signature is present"
      },
      {
        "name": "signature_date",
        "type": "DATE",
        "description": "Date signed"
      }
    ]
  }
});

from iterationlayer import IterationLayer

client = IterationLayer(api_key="YOUR_API_KEY")

result = client.extract_document(**{
  "files": [
    {
      "type": "url",
      "name": "w-4.pdf",
      "url": "https://example.com/documents/w-4-sample.pdf"
    }
  ],
  "schema": {
    "fields": [
      {
        "name": "employee_name",
        "type": "TEXT",
        "description": "Employee full name"
      },
      {
        "name": "social_security_number",
        "type": "TEXT",
        "description": "Employee Social Security number"
      },
      {
        "name": "address",
        "type": "ADDRESS",
        "description": "Employee address"
      },
      {
        "name": "filing_status",
        "type": "TEXT",
        "description": "Selected filing status"
      },
      {
        "name": "dependents_amount",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 3 dependent and other credits amount"
      },
      {
        "name": "other_income",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(a) other income"
      },
      {
        "name": "deductions",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(b) deductions"
      },
      {
        "name": "extra_withholding",
        "type": "CURRENCY_AMOUNT",
        "description": "Step 4(c) extra withholding"
      },
      {
        "name": "is_signed",
        "type": "BOOLEAN",
        "description": "Whether the employee signature is present"
      },
      {
        "name": "signature_date",
        "type": "DATE",
        "description": "Date signed"
      }
    ]
  }
})

package main

import il "github.com/iterationlayer/sdk-go"

func main() {
	client := il.NewClient("YOUR_API_KEY")

	result, err := client.ExtractDocument(il.ExtractDocumentRequest{
		Files: []il.FileInput{
			il.FileInput{
				Type: "url",
				Name: "w-4.pdf",
				Url: "https://example.com/documents/w-4-sample.pdf",
			},
		},
		Schema: il.ExtractionSchema{
			Fields: []any{
				il.TextFieldConfig{
					Name: "employee_name",
					Type: "TEXT",
					Description: "Employee full name",
				},
				il.TextFieldConfig{
					Name: "social_security_number",
					Type: "TEXT",
					Description: "Employee Social Security number",
				},
				il.AddressFieldConfig{
					Name: "address",
					Type: "ADDRESS",
					Description: "Employee address",
				},
				il.TextFieldConfig{
					Name: "filing_status",
					Type: "TEXT",
					Description: "Selected filing status",
				},
				il.CurrencyAmountFieldConfig{
					Name: "dependents_amount",
					Type: "CURRENCY_AMOUNT",
					Description: "Step 3 dependent and other credits amount",
				},
				il.CurrencyAmountFieldConfig{
					Name: "other_income",
					Type: "CURRENCY_AMOUNT",
					Description: "Step 4(a) other income",
				},
				il.CurrencyAmountFieldConfig{
					Name: "deductions",
					Type: "CURRENCY_AMOUNT",
					Description: "Step 4(b) deductions",
				},
				il.CurrencyAmountFieldConfig{
					Name: "extra_withholding",
					Type: "CURRENCY_AMOUNT",
					Description: "Step 4(c) extra withholding",
				},
				il.BooleanFieldConfig{
					Name: "is_signed",
					Type: "BOOLEAN",
					Description: "Whether the employee signature is present",
				},
				il.DateFieldConfig{
					Name: "signature_date",
					Type: "DATE",
					Description: "Date signed",
				},
			},
		},
	})
	if err != nil {
		panic(err)
	}

	_ = result
}

{
  "name": "Extract W-4 Data",
  "nodes": [
    {
      "parameters": {
        "content": "## Extract W-4 Data\n\nTax and finance teams use this recipe to extract W-4 fields from official forms into structured JSON for review, routing, and downstream filing preparation.\n\n**Note:** This workflow uses the Iteration Layer community node (`n8n-nodes-iterationlayer`). Install it via Settings > Community Nodes on self-hosted n8n, or add it directly on n8n Cloud with Verified Community Nodes enabled.",
        "height": 280,
        "width": 500,
        "color": 2
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        200,
        40
      ],
      "id": "extract-w-4-data-overview",
      "name": "Overview"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        250,
        300
      ],
      "id": "extract-w-4-data-trigger",
      "name": "Manual Trigger"
    },
    {
      "parameters": {
        "resource": "documentExtraction",
        "schemaInputMode": "rawJson",
        "schemaJson": "{\n  \"fields\": [\n    {\n      \"name\": \"employee_name\",\n      \"type\": \"TEXT\",\n      \"description\": \"Employee full name\"\n    },\n    {\n      \"name\": \"social_security_number\",\n      \"type\": \"TEXT\",\n      \"description\": \"Employee Social Security number\"\n    },\n    {\n      \"name\": \"address\",\n      \"type\": \"ADDRESS\",\n      \"description\": \"Employee address\"\n    },\n    {\n      \"name\": \"filing_status\",\n      \"type\": \"TEXT\",\n      \"description\": \"Selected filing status\"\n    },\n    {\n      \"name\": \"dependents_amount\",\n      \"type\": \"CURRENCY_AMOUNT\",\n      \"description\": \"Step 3 dependent and other credits amount\"\n    },\n    {\n      \"name\": \"other_income\",\n      \"type\": \"CURRENCY_AMOUNT\",\n      \"description\": \"Step 4(a) other income\"\n    },\n    {\n      \"name\": \"deductions\",\n      \"type\": \"CURRENCY_AMOUNT\",\n      \"description\": \"Step 4(b) deductions\"\n    },\n    {\n      \"name\": \"extra_withholding\",\n      \"type\": \"CURRENCY_AMOUNT\",\n      \"description\": \"Step 4(c) extra withholding\"\n    },\n    {\n      \"name\": \"is_signed\",\n      \"type\": \"BOOLEAN\",\n      \"description\": \"Whether the employee signature is present\"\n    },\n    {\n      \"name\": \"signature_date\",\n      \"type\": \"DATE\",\n      \"description\": \"Date signed\"\n    }\n  ]\n}",
        "files": {
          "fileValues": [
            {
              "fileInputMode": "url",
              "fileName": "w-4.pdf",
              "fileUrl": "https://example.com/documents/w-4-sample.pdf"
            }
          ]
        }
      },
      "type": "n8n-nodes-iterationlayer.iterationLayer",
      "typeVersion": 1,
      "position": [
        500,
        300
      ],
      "id": "extract-w-4-data-extract",
      "name": "Extract Data",
      "credentials": {
        "iterationLayerApi": {
          "id": "1",
          "name": "Iteration Layer API"
        }
      }
    }
  ],
  "connections": {
    "Manual Trigger": {
      "main": [
        [
          {
            "node": "Extract Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  }
}

Extract w-4 data from the file at [file URL]. Use the extract_document tool with these fields:

- employee_name (TEXT): Employee full name
- social_security_number (TEXT): Employee Social Security number
- address (ADDRESS): Employee address
- filing_status (TEXT): Selected filing status
- dependents_amount (CURRENCY_AMOUNT): Step 3 dependent and other credits amount
- other_income (CURRENCY_AMOUNT): Step 4(a) other income
- deductions (CURRENCY_AMOUNT): Step 4(b) deductions
- extra_withholding (CURRENCY_AMOUNT): Step 4(c) extra withholding
- is_signed (BOOLEAN): Whether the employee signature is present
- signature_date (DATE): Date signed

Response

{
  "success": true,
  "data": {
    "employee_name": {
      "value": "Employee Name",
      "confidence": 0.97,
      "citations": [
        "EMPLOYEE NAME"
      ]
    },
    "social_security_number": {
      "value": "Social Security Number",
      "confidence": 0.97,
      "citations": [
        "SOCIAL SECURITY NUMBER"
      ]
    },
    "address": {
      "value": {
        "street": "100 Market Street",
        "city": "Berlin",
        "postal_code": "10115",
        "country": "DE"
      },
      "confidence": 0.97,
      "citations": [
        "ADDRESS"
      ]
    },
    "filing_status": {
      "value": "Filing Status",
      "confidence": 0.97,
      "citations": [
        "FILING STATUS"
      ]
    },
    "dependents_amount": {
      "value": {
        "amount": "1234.56",
        "currency": "USD"
      },
      "confidence": 0.97,
      "citations": [
        "$1,234.56"
      ]
    },
    "other_income": {
      "value": {
        "amount": "1234.56",
        "currency": "USD"
      },
      "confidence": 0.97,
      "citations": [
        "$1,234.56"
      ]
    },
    "deductions": {
      "value": {
        "amount": "1234.56",
        "currency": "USD"
      },
      "confidence": 0.97,
      "citations": [
        "$1,234.56"
      ]
    },
    "extra_withholding": {
      "value": {
        "amount": "1234.56",
        "currency": "USD"
      },
      "confidence": 0.97,
      "citations": [
        "$1,234.56"
      ]
    },
    "is_signed": {
      "value": true,
      "confidence": 0.97,
      "citations": [
        "IS SIGNED"
      ]
    },
    "signature_date": {
      "value": "2026-04-15",
      "confidence": 0.97,
      "citations": [
        "15 Apr 2026"
      ]
    }
  }
}

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

More skills from this repository

compress-image-for-email

Free

Resize, sharpen, and compress an image to fit email platform size limits in a single pipeline.

The English summary is being prepared. Showing the original description.

iterationlayer/skills4Updated Jun 9, 2026

compress-image-to-target-size

Free

Compress an image to fit within a specific file size in bytes using quality-first compression.

The English summary is being prepared. Showing the original description.

iterationlayer/skills4Updated Jun 9, 2026

convert-contract-to-markdown

Free

Convert a contract PDF to clean markdown for clause extraction or LLM analysis.

The English summary is being prepared. Showing the original description.

iterationlayer/skills4Updated Jun 9, 2026

convert-document-for-knowledge-base

Free

Convert external documents — specs, contracts, reports — to markdown for knowledge base ingestion.

The English summary is being prepared. Showing the original description.

iterationlayer/skills4Updated Jun 9, 2026

convert-document-for-rag-ingestion

Free

Convert a document to clean markdown suitable for chunking and embedding in a RAG pipeline.

The English summary is being prepared. Showing the original description.

iterationlayer/skills4Updated Jun 9, 2026

convert-image-format

Free

Convert an image between PNG, JPEG, and WebP formats with quality control for web optimization.

The English summary is being prepared. Showing the original description.

iterationlayer/skills4Updated Jun 9, 2026

See all skills by iterationlayer

Report a problem with this skill

Install

Install with a command

npx skills add https://github.com/iterationlayer/skills --skill extract-w-4-data

Paste it into your terminal and run it (requires Node.js). You can choose which agents to install it for, such as Claude Code or Codex.

Ask your agent

Please install the following Agent Skill.
https://github.com/iterationlayer/skills/tree/main/skills/extract-w-4-data

First review SKILL.md and the bundled files and confirm there is nothing suspicious (such as sending data externally or reading credentials). Then place it in ~/.claude/skills/extract-w-4-data/ for Claude Code, or ~/.agents/skills/extract-w-4-data/ for Codex.

Send this text to Claude Code or Codex as is. It checks the contents before installing.

View source on GitHub

Repository: iterationlayer/skills
Stars: 4
Forks: 0
Category: Data & AI
License: MIT
Original language: English
Last updated: Jun 9, 2026

A skill is a set of instructions and scripts for an agent. cccskills does not guarantee that skills are safe. Review the contents before you install.

Files included (1)

SKILL.md (original)

Extract W-4 Data

APIs Used

Prerequisites

Implementation

Response

Links

Reviews

Comments

More skills from this repository

compress-image-for-email

compress-image-to-target-size

convert-contract-to-markdown

convert-document-for-knowledge-base

convert-document-for-rag-ingestion

convert-image-format