Davide Boizza This workflow corresponds to n8n.io template #16761 — we link there as the canonical source.
This workflow follows the Chainllm → 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 →
{
"id": "F5Vc6P90dSHIJ9Iv",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Robots.txt Generator for SEO & GEO",
"tags": [],
"nodes": [
{
"id": "685f802b-b2a7-458f-8b86-ea556152fd60",
"name": "If",
"type": "n8n-nodes-base.if",
"position": [
-96,
-48
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 3,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "f1c8ee1a-b701-4dd2-98a1-3e2fe20e4a5a",
"operator": {
"type": "number",
"operation": "equals"
},
"leftValue": "={{ $json.statusCode }}",
"rightValue": 200
}
]
}
},
"typeVersion": 2.3
},
{
"id": "931808e9-16fc-41f4-9808-252896157b00",
"name": "robots.txt",
"type": "n8n-nodes-base.httpRequest",
"position": [
-336,
-48
],
"parameters": {
"url": "={{ $json.website_url }}/robots.txt",
"options": {
"response": {
"response": {
"fullResponse": true
}
}
},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "User-Agent",
"value": "Mozilla/5.0"
},
{
"name": "Accept",
"value": "text/plain,text/html"
}
]
}
},
"typeVersion": 4.4
},
{
"id": "6c020f9c-f263-4acc-ba95-1272f188ebbb",
"name": "No Operation, do nothing",
"type": "n8n-nodes-base.noOp",
"position": [
192,
224
],
"parameters": {},
"typeVersion": 1
},
{
"id": "76ed553f-7571-49f5-bd98-fb36ca5a066d",
"name": "When clicking \u2018Execute workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-880,
-48
],
"parameters": {},
"typeVersion": 1
},
{
"id": "9bd4cbe7-9575-4339-84b1-eeaab4776c18",
"name": "Set Website Url",
"type": "n8n-nodes-base.set",
"position": [
-624,
-48
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "a03c93f9-4a91-4535-9e25-d2ec5bc61a73",
"name": "website_url",
"type": "string",
"value": "https://n3w.it"
},
{
"id": "40c3d988-9e79-478c-a390-585e30c69820",
"name": "sitemap",
"type": "string",
"value": "https://n3w.it/sitemap.xml"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "40f14918-1263-4ec6-85da-2ecd25d7dab2",
"name": "Get HTML",
"type": "n8n-nodes-base.httpRequest",
"position": [
192,
-256
],
"parameters": {
"url": "={{ $('Set Website Url').item.json.website_url }}",
"options": {}
},
"typeVersion": 4.4
},
{
"id": "556f1ba4-1b90-4e0d-80b9-b7630d37f38a",
"name": "Discover CMS",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
464,
-256
],
"parameters": {
"text": "={{ $json.data }}",
"batching": {},
"messages": {
"messageValues": [
{
"message": "=You are a CMS detection assistant.\n\nYou will receive the HTML source code of a website homepage.\n\nYour task is to detect the CMS used by the website (e.g. WordPress, Joomla, Drupal, Shopify, Magento, Wix, Squarespace, PrestaShop, Webflow, Ghost, Blogger, etc.).\n\nReturn ONLY a valid JSON object in this format:\n\n{\n \"cms\": \"WordPress\"\n}\n\nIf no common CMS can be confidently identified, return:\n\n{\n \"cms\": \"not detected\"\n}\n\nDo not include explanations, markdown, or any additional text. Output only the JSON."
}
]
},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "70908f48-5bbe-4b1e-be56-65a89422208a",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
848,
-16
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5.4-mini",
"cachedResultName": "gpt-5.4-mini"
},
"options": {},
"builtInTools": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "9b780136-785f-4f04-9e5f-e2cad9a445d4",
"name": "Parser",
"type": "n8n-nodes-base.code",
"position": [
832,
-256
],
"parameters": {
"jsCode": "return items.map(item => {\n return {\n json: JSON.parse(item.json.text)\n };\n});"
},
"typeVersion": 2
},
{
"id": "8b9e95e3-722d-4195-ba54-6e0e2944ab98",
"name": "Robots.txt Generator",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1120,
-256
],
"parameters": {
"text": "=robots.txt: {{ $('robots.txt').item.json.data }}\nSitemap url: {{ $('Set Website Url').item.json.sitemap }}\nCMS: {{ $json.cms }}",
"batching": {},
"messages": {
"messageValues": [
{
"message": "=You are an expert Technical SEO and GEO specialist.\n\nYou will receive:\n- The current robots.txt content\n- The sitemap URL\n- The detected CMS\n\nInput:\n- current robots.txt\n- Sitemap url\n- CMS\n\nYour task is to generate an optimized robots.txt file for SEO and GEO.\n\nRules:\n- Adapt the robots.txt to the detected CMS when possible.\n- If CMS is \"not detected\", generate a safe generic robots.txt.\n- Do not block important public pages, assets, CSS, JS, images, or sitemap access.\n- Block only useless, duplicate, private, admin, internal search, cart, checkout, account, login, filter, and tracking URLs when appropriate for the CMS.\n- Allow major search engines and AI/LLM crawlers when useful for GEO visibility.\n- Include the Sitemap directive using the provided sitemap URL.\n- Keep the file clean, valid, and production-ready.\n- Use only standard robots.txt syntax: User-agent, Allow, Disallow, Sitemap.\n- Return ONLY the final robots.txt content.\n- Do not include explanations, markdown, JSON, comments outside the robots.txt file, or extra text."
}
]
},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "720940e0-0c37-4106-9132-978e122a266b",
"name": "Convert to File",
"type": "n8n-nodes-base.convertToFile",
"position": [
1536,
-256
],
"parameters": {
"options": {
"fileName": "robots.txt"
},
"operation": "toText",
"sourceProperty": "text"
},
"typeVersion": 1.1
},
{
"id": "36fa0c43-f820-4563-b684-21f8058a8ba7",
"name": "Upload file",
"type": "n8n-nodes-base.googleDrive",
"position": [
1760,
-256
],
"parameters": {
"name": "={{$binary.data.fileName}}",
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive"
},
"options": {},
"folderId": {
"__rl": true,
"mode": "list",
"value": "root",
"cachedResultName": "/ (Root folder)"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "dbee1971-0c32-4549-86c0-a5ca33758739",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
1056,
-1216
],
"parameters": {
"color": 7,
"width": 736,
"height": 784,
"content": "## MY NEW YOUTUBE CHANNEL\n\ud83d\udc49 [Subscribe to my new **YouTube channel**](https://youtube.com/@n3witalia). Here I\u2019ll share videos and Shorts with practical tutorials and **FREE templates for n8n**.\n\n[](https://youtube.com/@n3witalia)"
},
"typeVersion": 1
},
{
"id": "16cbf623-aa2d-4569-b460-599e06051519",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
160,
-1072
],
"parameters": {
"width": 864,
"height": 640,
"content": "# Robots.txt Generator for SEO & GEO\n\n### How it works\n\n1. The workflow starts manually and sets the target website URL and sitemap values.\n2. It checks whether the site already has a robots.txt file and branches accordingly.\n3. If needed, it fetches the site HTML, uses an LLM to identify the CMS, and parses the result.\\n4. It generates a robots.txt file with another LLM chain, converts it to a file, and uploads it to Google Drive.\n\n### Setup steps\n- [ ] Configure the manual trigger or replace it with your preferred input trigger.\n- [ ] Set the target website URL and any sitemap value in the Set Website Url node.\n- [ ] Ensure the HTTP Request nodes can access the target site without blocking or authentication issues.\n- [ ] Connect and authorize the OpenAI credentials used by the LLM chain nodes.\n- [ ] Review the robot generation prompt and parser logic so the output matches your SEO/GEO rules\n- [ ] Configure Google Drive credentials and choose the destination folder for the generated file.\n\n### Customization\nYou can customize the website URL input, the CMS detection logic, the robots.txt rules generated by the LLM, and the Google Drive upload destination."
},
"typeVersion": 1
},
{
"id": "5393cbbf-50ec-4fe8-868c-e867c5249237",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-688,
-240
],
"parameters": {
"color": 7,
"width": 256,
"height": 368,
"content": "## Manual site input\nStarts the workflow and initializes the website URL and sitemap values used downstream."
},
"typeVersion": 1
},
{
"id": "0907927c-0e1d-4cf5-962b-60c650734f77",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-400,
-240
],
"parameters": {
"color": 7,
"height": 368,
"content": "## Check existing robots\nFetches the site's robots.txt file and branches based on whether it should continue with generation or stop."
},
"typeVersion": 1
},
{
"id": "8286cf0c-7167-4c3b-8978-c5c0a2789b19",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
160,
-400
],
"parameters": {
"color": 7,
"width": 864,
"height": 336,
"content": "## Detect CMS and parse\nRetrieves the homepage HTML, infers the site CMS with an LLM chain, and normalizes the output with custom code."
},
"typeVersion": 1
},
{
"id": "582dae63-52bc-4a93-b6b8-e3a60dffc903",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1056,
-400
],
"parameters": {
"color": 7,
"width": 880,
"height": 336,
"content": "## Generate and upload file\nCreates the final robots.txt content, converts it into a file, and uploads it to Google Drive."
},
"typeVersion": 1
},
{
"id": "ba1006e8-ab51-4175-8b4d-62954682a919",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
160,
96
],
"parameters": {
"color": 7,
"width": 880,
"height": 272,
"content": "## Existing file exit\n\nStops the workflow on the branch where no further action is required, leaving the existing robots.txt untouched."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"executionOrder": "v1"
},
"versionId": "70e83d62-c50b-4a1d-bef0-5eb9c0acd83c",
"nodeGroups": [],
"connections": {
"If": {
"main": [
[
{
"node": "Get HTML",
"type": "main",
"index": 0
}
],
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
]
]
},
"Parser": {
"main": [
[
{
"node": "Robots.txt Generator",
"type": "main",
"index": 0
}
]
]
},
"Get HTML": {
"main": [
[
{
"node": "Discover CMS",
"type": "main",
"index": 0
}
]
]
},
"robots.txt": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"Discover CMS": {
"main": [
[
{
"node": "Parser",
"type": "main",
"index": 0
}
]
]
},
"Convert to File": {
"main": [
[
{
"node": "Upload file",
"type": "main",
"index": 0
}
]
]
},
"Set Website Url": {
"main": [
[
{
"node": "robots.txt",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Discover CMS",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Robots.txt Generator",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Robots.txt Generator": {
"main": [
[
{
"node": "Convert to File",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Set Website Url",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleDriveOAuth2ApiopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow runs manually to check a website’s existing robots.txt, detect the site’s CMS from the homepage HTML using OpenAI, and generate an optimized robots.txt (including the provided sitemap URL) that is saved as a file and uploaded to Google Drive. Starts when you click…
Source: https://n8n.io/workflows/16761/ — 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.
The best content automation template in the market is now even better—with “deep research” on time-sensitive topics\! Unlike most n8n content automation templates that are mainly for “demo purposes,”
OpenAI, HTTP Request, XML +11
🤖🧑💻 AI Agent for Top n8n Creators Leaderboard Reporting. Uses httpRequest, lmChatOpenAi, executeWorkflowTrigger, toolWorkflow. Event-driven trigger; 49 nodes.
HTTP Request, OpenAI Chat, Execute Workflow Trigger +8
🤖🧑💻 AI Agent for Top n8n Creators Leaderboard Reporting. Uses httpRequest, lmChatOpenAi, executeWorkflowTrigger, toolWorkflow. Event-driven trigger; 49 nodes.
HTTP Request, OpenAI Chat, Execute Workflow Trigger +8
This n8n workflow is designed to automate the aggregation, processing, and reporting of community statistics related to n8n creators and workflows. Its primary purpose is to generate insightful report
HTTP Request, OpenAI Chat, Execute Workflow Trigger +8
Use cases are many: This tool is perfect for YouTube and Shorts creators who want to publish daily content without showing their face, TikTok and Reels marketers automating voice-over-driven videos, a
Google Drive, Output Parser Structured, Chain Llm +4