This workflow follows the Form Trigger → Google Drive recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "Data-driven SEO Optimization",
"nodes": [
{
"parameters": {
"formTitle": "Form",
"formFields": {
"values": [
{
"fieldLabel": "Link",
"requiredField": true
}
]
},
"options": {}
},
"type": "n8n-nodes-base.formTrigger",
"typeVersion": 2.2,
"position": [
-500,
280
],
"id": "ba0f4b1f-40be-4c8b-86a8-b880960224d4",
"name": "On form submission"
},
{
"parameters": {
"method": "POST",
"url": "http://crawl4ai:11235/crawl",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "urls",
"value": "={{ $json.Link }}"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-280,
60
],
"id": "1b6e074c-b5f3-4fd2-a6c0-b0d2d1f9275d",
"name": "get_article_content"
},
{
"parameters": {},
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
-80,
60
],
"id": "435d5eb7-f2a2-4b2e-ad27-712e7fd304b7",
"name": "5_sec"
},
{
"parameters": {
"url": "=http://crawl4ai:11235/task/{{ $json.task_id }}",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
60,
60
],
"id": "5f582f3d-616d-433b-9b62-d1c646dea679",
"name": "get_status"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "f42941b7-46c6-44f9-95d6-80065c27c3a9",
"leftValue": "={{ $json.status }}",
"rightValue": "completed",
"operator": {
"type": "string",
"operation": "equals",
"name": "filter.operator.equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
200,
60
],
"id": "5326213d-ffd6-4048-81d2-1c1dd44a3485",
"name": "is_completed"
},
{
"parameters": {
"html": "={{ $json.result.cleaned_html }}",
"destinationKey": "markdown",
"options": {}
},
"type": "n8n-nodes-base.markdown",
"typeVersion": 1,
"position": [
540,
-20
],
"id": "9a5897bb-30f6-4e7c-90e2-4b8995a22aeb",
"name": "Markdown"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "9177b0ac-024c-4088-a1b4-9254a53244e0",
"name": "result.url",
"value": "={{ $json.result.url }}",
"type": "string"
},
{
"id": "bb4b7ad9-dc32-40d5-93d7-51582c64d99f",
"name": "result.metadata.title",
"value": "={{ $json.result.metadata.title }}",
"type": "string"
},
{
"id": "64dfd766-9b2e-4349-8f4f-8771202cb0d4",
"name": "result.cleaned_html",
"value": "={{ $json.result.cleaned_html }}",
"type": "string"
},
{
"id": "a74a89ab-aa6e-4ff5-934a-c6176702c127",
"name": "result.metadata.description",
"value": "={{ $json.result.metadata.description }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
360,
-20
],
"id": "3fc6b9e7-755e-4f0a-bef5-54e3f4f62f21",
"name": "Edit Fields"
},
{
"parameters": {
"resource": "fileFolder",
"searchMethod": "query",
"queryString": "={{ \"name=\" + \"'\"+$json.Link.split('/').filter(Boolean).pop()+\"'\" }}",
"limit": 1,
"filter": {
"includeTrashed": "={{ false }}"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
-280,
500
],
"id": "2bd3d92a-6035-4f9e-b491-5ca18643d93c",
"name": "Google Drive",
"alwaysOutputData": true
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "bf20030a-7234-4e88-bcc9-cb815ac8dcd9",
"leftValue": "={{ $json }}",
"rightValue": "",
"operator": {
"type": "object",
"operation": "notEmpty",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
-100,
500
],
"id": "38e4200b-6e9d-4f4b-b2be-c0156ffc5a54",
"name": "if_sheet_exists"
},
{
"parameters": {
"resource": "spreadsheet",
"title": "={{ $('On form submission').item.json.Link.split('/').filter(Boolean).pop() }}",
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
60,
580
],
"id": "10ab4494-e56d-4854-9557-63702aa92edd",
"name": "create_new_spreadsheet",
"alwaysOutputData": true
},
{
"parameters": {
"projectId": {
"__rl": true,
"value": "automations-451008",
"mode": "list",
"cachedResultName": "automations",
"cachedResultUrl": "https://console.cloud.google.com/bigquery?project=automations-451008"
},
"sqlQuery": "DECLARE target_url STRING DEFAULT '{{ $('On form submission').item.json.Link }}';\nDECLARE current_period_start DATE DEFAULT DATE_SUB(CURRENT_DATE(), INTERVAL 30 DAY);\nDECLARE previous_period_start DATE DEFAULT DATE_SUB(current_period_start, INTERVAL 30 DAY);\n\nWITH \n-- Current period query performance (last 30 days)\ncurrent_period AS (\n SELECT\n query,\n SUM(clicks) AS current_clicks,\n SUM(impressions) AS current_impressions,\n SAFE_DIVIDE(SUM(clicks), SUM(impressions)) AS current_ctr,\n SAFE_DIVIDE(SUM(sum_position), SUM(impressions)) AS current_avg_position\n FROM `your_bigquery_table`\n WHERE \n url = target_url\n AND data_date >= current_period_start\n AND data_date < CURRENT_DATE()\n AND is_anonymized_query = False\n GROUP BY query\n),\n\n-- Previous period query performance (30-60 days ago)\nprevious_period AS (\n SELECT\n query,\n SUM(clicks) AS previous_clicks,\n SUM(impressions) AS previous_impressions,\n SAFE_DIVIDE(SUM(clicks), SUM(impressions)) AS previous_ctr,\n SAFE_DIVIDE(SUM(sum_position), SUM(impressions)) AS previous_avg_position\n FROM `your_bigquery_table`\n WHERE \n url = target_url\n AND data_date >= previous_period_start\n AND data_date < current_period_start\n AND is_anonymized_query = False\n GROUP BY query\n),\n\n-- Combined data with differences\ncombined_data AS (\n SELECT\n COALESCE(c.query, p.query) AS query,\n \n -- Current period metrics\n IFNULL(c.current_clicks, 0) AS current_clicks,\n IFNULL(p.previous_clicks, 0) AS previous_clicks,\n \n IFNULL(c.current_impressions, 0) AS current_impressions,\n IFNULL(p.previous_impressions, 0) AS previous_impressions,\n \n IFNULL(c.current_ctr, 0) AS current_ctr,\n IFNULL(p.previous_ctr, 0) AS previous_ctr,\n \n IFNULL(c.current_avg_position, 0) AS current_avg_position,\n IFNULL(p.previous_avg_position, 0) AS previous_avg_position,\n \n -- Absolute differences\n IFNULL(c.current_clicks, 0) - IFNULL(p.previous_clicks, 0) AS clicks_diff,\n IFNULL(c.current_impressions, 0) - IFNULL(p.previous_impressions, 0) AS impressions_diff,\n IFNULL(c.current_ctr, 0) - IFNULL(p.previous_ctr, 0) AS ctr_diff,\n IFNULL(p.previous_avg_position, 0) - IFNULL(c.current_avg_position, 0) AS position_diff,\n \n -- Percentage differences\n CASE \n WHEN IFNULL(p.previous_clicks, 0) = 0 AND IFNULL(c.current_clicks, 0) > 0 THEN 100\n WHEN IFNULL(p.previous_clicks, 0) = 0 THEN 0\n ELSE ROUND((IFNULL(c.current_clicks, 0) - IFNULL(p.previous_clicks, 0)) / IFNULL(p.previous_clicks, 0) * 100, 2)\n END AS clicks_diff_pct,\n \n CASE \n WHEN IFNULL(p.previous_impressions, 0) = 0 AND IFNULL(c.current_impressions, 0) > 0 THEN 100\n WHEN IFNULL(p.previous_impressions, 0) = 0 THEN 0\n ELSE ROUND((IFNULL(c.current_impressions, 0) - IFNULL(p.previous_impressions, 0)) / IFNULL(p.previous_impressions, 0) * 100, 2)\n END AS impressions_diff_pct,\n \n CASE \n WHEN IFNULL(p.previous_ctr, 0) = 0 AND IFNULL(c.current_ctr, 0) > 0 THEN 100\n WHEN IFNULL(p.previous_ctr, 0) = 0 THEN 0\n ELSE ROUND((IFNULL(c.current_ctr, 0) - IFNULL(p.previous_ctr, 0)) / IFNULL(p.previous_ctr, 0) * 100, 2)\n END AS ctr_diff_pct\n FROM current_period c\n FULL OUTER JOIN previous_period p ON c.query = p.query\n)\n\n-- Main query with categorization\nSELECT\n query,\n \n -- Paired metrics (current next to previous)\n current_clicks,\n previous_clicks,\n clicks_diff,\n clicks_diff_pct,\n \n current_impressions,\n previous_impressions,\n impressions_diff,\n impressions_diff_pct,\n \n current_ctr,\n previous_ctr,\n ctr_diff,\n ctr_diff_pct,\n \n current_avg_position,\n previous_avg_position,\n position_diff,\n \n -- Categorization\n CASE\n WHEN clicks_diff > 0 THEN 'Gaining'\n WHEN clicks_diff < 0 THEN 'Declining'\n ELSE 'Stable'\n END AS trend_category\n\nFROM combined_data\nWHERE \n -- Filter to include only keywords with meaningful data\n (current_clicks > 0 OR previous_clicks > 0 OR current_impressions > 10 OR previous_impressions > 10)\nORDER BY \n -- Default ordering by absolute click difference (biggest gains/losses first)\n ABS(clicks_diff) DESC,\n current_impressions DESC",
"options": {}
},
"type": "n8n-nodes-base.googleBigQuery",
"typeVersion": 2.1,
"position": [
540,
500
],
"id": "d8864e24-c4b0-4848-8abd-6fddac21bf8f",
"name": "get_article_performance"
},
{
"parameters": {
"operation": "create",
"documentId": {
"__rl": true,
"value": "={{ $json.id }}",
"mode": "id"
},
"title": "={{$now.format('yyyy-MM-dd')}}",
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
60,
420
],
"id": "ef356758-0b7f-4984-a11f-44a39ec86fc7",
"name": "add_sheet_0",
"alwaysOutputData": true
},
{
"parameters": {
"operation": "create",
"documentId": {
"__rl": true,
"value": "={{ $json.spreadsheetId }}",
"mode": "id"
},
"title": "={{ $now.format('yyyy-MM-dd')}}",
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
240,
580
],
"id": "46a01b97-6576-4c7d-8198-d21a5cedbcd7",
"name": "add_sheet_1",
"alwaysOutputData": true
},
{
"parameters": {},
"type": "n8n-nodes-base.merge",
"typeVersion": 3,
"position": [
400,
500
],
"id": "18066faf-8a89-4ed7-b612-b9fe6a3b85a7",
"name": "Merge",
"alwaysOutputData": true
},
{
"parameters": {
"operation": "append",
"documentId": {
"__rl": true,
"value": "={{ $('Merge').item.json.spreadsheetId }}",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "={{ $now.format('yyyy-MM-dd') }}",
"mode": "name"
},
"columns": {
"mappingMode": "autoMapInputData",
"value": {},
"matchingColumns": [],
"schema": [
{
"id": "query",
"displayName": "query",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "current_clicks",
"displayName": "current_clicks",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "previous_clicks",
"displayName": "previous_clicks",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "clicks_diff",
"displayName": "clicks_diff",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "clicks_diff_pct",
"displayName": "clicks_diff_pct",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "current_impressions",
"displayName": "current_impressions",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "previous_impressions",
"displayName": "previous_impressions",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "impressions_diff",
"displayName": "impressions_diff",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "impressions_diff_pct",
"displayName": "impressions_diff_pct",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "current_ctr",
"displayName": "current_ctr",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "previous_ctr",
"displayName": "previous_ctr",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "ctr_diff",
"displayName": "ctr_diff",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "ctr_diff_pct",
"displayName": "ctr_diff_pct",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "current_avg_position",
"displayName": "current_avg_position",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "previous_avg_position",
"displayName": "previous_avg_position",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "position_diff",
"displayName": "position_diff",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "trend_category",
"displayName": "trend_category",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
700,
500
],
"id": "17a2c863-c55f-458a-8a7c-ffc016c7acf6",
"name": "insert_performance"
},
{
"parameters": {},
"type": "n8n-nodes-base.merge",
"typeVersion": 3,
"position": [
900,
60
],
"id": "3a5d7bf9-8fb4-4d1c-8770-c39f57afd39c",
"name": "Merge1",
"executeOnce": false
},
{
"parameters": {
"aggregate": "aggregateAllItemData",
"destinationFieldName": "performance",
"options": {}
},
"type": "n8n-nodes-base.aggregate",
"typeVersion": 1,
"position": [
720,
160
],
"id": "0716f221-9819-4533-98fe-34bec5e9ac83",
"name": "set_key"
},
{
"parameters": {
"modelId": {
"__rl": true,
"value": "gpt-4o-mini",
"mode": "list",
"cachedResultName": "GPT-4O-MINI"
},
"messages": {
"values": [
{
"content": "Du bist Copywriter mit einem vielseitigen Skillset an SEO-F\u00e4higkeiten. Du bist auf die datengetriebene Optimierung spezialisiert und verbesserst bestehende Artikel auf Basis von realen Traffic-Daten. Deine Daten stammen aus der Google Search Console und zeigen, wie gut Keywords performen. Du st\u00fctzt dich ausschlie\u00dflich auf die zugrundeliegenden Daten und erfindest keine falschen Informationen. Dein Ziel ist es immer, den Artikel datengetrieben zu verbessern. Des Weiteren bist du HTML-Experte und gibst deine Antworten ausschlie\u00dflich als HTML-formatiert zur\u00fcck. Wir ben\u00f6tigen kein DOCTYPE, meta oder title tag. Ausschlie\u00dflich HTML der den Inhalt strukturiert darstellt.",
"role": "system"
},
{
"content": "=Analysiere den vorhandenen Artikel: <{{ $json.content }}> im Detail und verstehe den Inhalt sowie die Suchintention, die dieser Artikel befriedigen soll. Anschlie\u00dfend analysierst du ALLE Keywords aus der Google Search Console. Diese Keywords zeigen dir, wie gut der Artikel f\u00fcr bestimmte Suchanfragen performt.\nDie Performance-Daten sind wie folgt:\n\"\"\n{{ JSON.stringify($('Merge1').all()[1].json.performance) }}\n\"\"\nF\u00fchre folgende Optimierungen durch:\n 1. Analysiere den bestehenden Artikelinhalt auf Struktur, Lesbarkeit und SEO-Relevanz.\n 2. Identifiziere Optimierungspotenziale im Artikel basierend auf den analysierten Daten.\n 3. Entwickle neue Vorschl\u00e4ge f\u00fcr den Titel und die Meta-Beschreibung. \n\t- Die Titel d\u00fcrften nicht mehr wie 60 Zeichen lang sein.\n\t- Die Meta-Beschreibung muss relevante Keywords aus den Performance-Daten enthalten.\n 4. Erstelle optimierte Textpassagen, die die relevanten Keywords aus der Google Search Console nat\u00fcrlich integrieren.\n \t- Gib an, aus welchem Kapitel die Textpassage stammen, so dass man diese schnell erkennen und optimieren kann.\n \t- Erstelle mindestens f\u00fcr jeden Paragraphen eine optimierte Textpassage.\n\t- Gib an, aus welchem Kapitel die Textpassage stammen, so dass man diese schnell erkennen und optimieren kann.\n\t- (Die Textpassagen m\u00fcssen so aufgebaut sein, dass ich diese schnell finden und ersetzen kann)\n 5. Erstelle neue Textpassagen mit Keywords aus den Google Search Console Daten, die man nicht im vorherigen Schritt einf\u00fcgen konnte.\n - Verwende hier als \u00dcberschrift \"Neue Textpassagen\".\n 6. Erstelle eine HTML Tabelle die deine Auswahl der selektieren Keywords aus der Google Search Console darstellt.\n\nFormatiere deine Ausgabe wie folgt und vermeide Fehler:\n - Ein kurzer Analysebericht des aktuellen Artikelinhalts.\n - Pro Verbesserungsvorschlag einmal die originale Passage und direkt daruntere die SEO-freundliche Erg\u00e4nzung.\n - 5 Vorschl\u00e4ge f\u00fcr optimierte Titel.\n - 5 Vorschl\u00e4ge f\u00fcr optimierte Meta-Beschreibungen.\n - Eine Liste von \u00fcberarbeiteten Textpassagen, die die identifizierten Keywords und Phrasen nat\u00fcrlich integrieren. Bearbeite mindestens\n 5 Textpassagen. Wenn m\u00f6glich, dann auch mehr, so dass der Text die Keywords aus der Google Search Console beinhaltet.\n - HTML Tabelle mit selektieren Keywords aus der Google Search Console.\n Alles in HTML formatiert.\nWir ben\u00f6tigen kein DOCTYPE, meta oder title tag. Ausschlie\u00dflich HTML der den Inhalt strukturiert darstellt."
}
]
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
1140,
60
],
"id": "4a96ce2e-ca8b-4bb3-b252-3c0c1ddb5fab",
"name": "create_report",
"executeOnce": true
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "6c07931f-d135-44cb-a9f5-d0e80887a0b4",
"name": "url",
"value": "={{ $json.result.url }}",
"type": "string"
},
{
"id": "d3223ba3-1e08-47b2-9265-f3fb178a49ee",
"name": "title",
"value": "={{ $json.result.metadata.title }}",
"type": "string"
},
{
"id": "13da4adc-a125-4410-b2ca-c0c239b939ab",
"name": "description",
"value": "={{ $json.result.metadata.description }}",
"type": "string"
},
{
"id": "03d09f45-3ece-4da2-953b-fdbe54cd2896",
"name": "content",
"value": "={{ $json.markdown }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
720,
-20
],
"id": "a46ffc94-4651-4481-89e6-ed073735a41f",
"name": "Edit Fields1"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "654e6696-7705-4021-87df-1edf19bbe439",
"name": "message.content",
"value": "={{ $json.message.content}}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1460,
60
],
"id": "878b56fc-b988-412a-90eb-0b2d87b3c1d5",
"name": "get_clean_html",
"notes": ".replace('html', '').replaceAll(\"```\", '').replaceAll(\"\\n\", \"\") "
},
{
"parameters": {
"operation": "toBinary",
"sourceProperty": "base64",
"options": {
"fileName": "test.html",
"mimeType": "={{ $json.mimetype }}"
}
},
"type": "n8n-nodes-base.convertToFile",
"typeVersion": 1.1,
"position": [
1780,
60
],
"id": "203ca372-670e-4db6-a2f6-99f01c5a4841",
"name": "convert_to_html_file"
},
{
"parameters": {
"jsCode": "return [\n {\n json: {\n base64: Buffer.from($input.all()[0].json.message.content).toString('base64'),\n mimetype: \"text/html\"\n }\n }\n];\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1620,
60
],
"id": "74ba8692-7d3d-4f32-bb74-c075b6a58d83",
"name": "convert_to_base64"
},
{
"parameters": {
"name": "test123",
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive"
},
"folderId": {
"__rl": true,
"mode": "list",
"value": "root",
"cachedResultName": "/ (Root folder)"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
1940,
60
],
"id": "ede28035-8a35-40a6-89df-ffa196470765",
"name": "save_report"
},
{
"parameters": {
"content": "# Crawl Article",
"height": 420,
"width": 1420
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-340,
-100
],
"id": "9b518a2a-5b18-4cbb-8afd-0de2fc17a4a0",
"name": "Sticky Note1"
},
{
"parameters": {
"content": "# Generate Optimized Report",
"height": 420,
"width": 1040
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
1100,
-100
],
"id": "caffcc7c-7af1-49ee-b513-1840a6a7ba73",
"name": "Sticky Note2"
},
{
"parameters": {
"content": "# Generate and Save Performance Report",
"height": 420,
"width": 2480
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-340,
340
],
"id": "bb48be15-d76d-4e75-ad17-54ad27cfaf87",
"name": "Sticky Note"
}
],
"connections": {
"On form submission": {
"main": [
[
{
"node": "get_article_content",
"type": "main",
"index": 0
},
{
"node": "Google Drive",
"type": "main",
"index": 0
}
]
]
},
"get_article_content": {
"main": [
[
{
"node": "5_sec",
"type": "main",
"index": 0
}
]
]
},
"5_sec": {
"main": [
[
{
"node": "get_status",
"type": "main",
"index": 0
}
]
]
},
"get_status": {
"main": [
[
{
"node": "is_completed",
"type": "main",
"index": 0
}
]
]
},
"is_completed": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
],
[
{
"node": "5_sec",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
}
]
]
},
"Google Drive": {
"main": [
[
{
"node": "if_sheet_exists",
"type": "main",
"index": 0
}
]
]
},
"if_sheet_exists": {
"main": [
[
{
"node": "add_sheet_0",
"type": "main",
"index": 0
}
],
[
{
"node": "create_new_spreadsheet",
"type": "main",
"index": 0
}
]
]
},
"create_new_spreadsheet": {
"main": [
[
{
"node": "add_sheet_1",
"type": "main",
"index": 0
}
]
]
},
"get_article_performance": {
"main": [
[
{
"node": "insert_performance",
"type": "main",
"index": 0
},
{
"node": "set_key",
"type": "main",
"index": 0
}
]
]
},
"add_sheet_1": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"add_sheet_0": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "get_article_performance",
"type": "main",
"index": 0
}
]
]
},
"Markdown": {
"main": [
[
{
"node": "Edit Fields1",
"type": "main",
"index": 0
}
]
]
},
"Merge1": {
"main": [
[
{
"node": "create_report",
"type": "main",
"index": 0
}
]
]
},
"set_key": {
"main": [
[
{
"node": "Merge1",
"type": "main",
"index": 1
}
]
]
},
"create_report": {
"main": [
[
{
"node": "get_clean_html",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields1": {
"main": [
[
{
"node": "Merge1",
"type": "main",
"index": 0
}
]
]
},
"get_clean_html": {
"main": [
[
{
"node": "convert_to_base64",
"type": "main",
"index": 0
}
]
]
},
"convert_to_base64": {
"main": [
[
{
"node": "convert_to_html_file",
"type": "main",
"index": 0
}
]
]
},
"convert_to_html_file": {
"main": [
[
{
"node": "save_report",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "35ba3601-2edb-4bfd-8f0a-c41298ab9d21",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "cO3xILd89yLoQPGu",
"tags": [
{
"createdAt": "2025-03-02T12:05:53.836Z",
"updatedAt": "2025-03-02T12:05:53.836Z",
"id": "utwtHTzeqUdktrxJ",
"name": "SEO"
}
]
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow streamlines SEO optimisation by automatically analysing submitted article content and generating tailored recommendations to boost search rankings, saving content creators hours of manual research. It suits digital marketers, bloggers, and SEO specialists who need data-backed insights without deep technical expertise. Upon form submission, the process fetches the article via HTTP request, checks its status, and leverages Google Sheets and Google Drive to store and process data, culminating in AI-powered suggestions from OpenAI for keyword enhancements and structure improvements.
Use this workflow when handling regular content updates where quick, actionable SEO advice can directly inform revisions, such as for a blog publishing schedule. Avoid it for one-off analyses or sites with highly customised SEO needs requiring specialist tools beyond basic integrations. Common variations include swapping OpenAI for another AI service or adding Google BigQuery for aggregating performance data across multiple articles.
About this workflow
Data-driven SEO Optimization. Uses formTrigger, httpRequest, googleDrive, googleSheets. Event-driven trigger; 26 nodes.
Source: https://github.com/Marvomatic/n8n-templates/blob/main/gsc-ai-seo-writer/gsc_ai_seo_writer.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Template - SERP Analysis (Serper). Uses formTrigger, httpRequest, googleSheets, openAi. Event-driven trigger; 36 nodes.
Form Trigger, HTTP Request, Google Sheets +1
SERP Analysis Template. Uses formTrigger, httpRequest, openAi, googleSheets. Event-driven trigger; 35 nodes.
Form Trigger, HTTP Request, OpenAI +1
Converttofile Http. Uses lmChatOpenAi, googleSheets, httpRequest, openAi. Event-driven trigger; 18 nodes.
OpenAI Chat, Google Sheets, HTTP Request +3
Cold Email Live Build. Uses formTrigger, httpRequest, googleSheets, splitInBatches. Event-driven trigger; 9 nodes.
Form Trigger, HTTP Request, Google Sheets +1
HR-focused automation pipeline with AI. Uses formTrigger, extractFromFile, informationExtractor, chainSummarization. Event-driven trigger; 18 nodes.
Form Trigger, Information Extractor, Chain Summarization +5