Antonio Trento This workflow corresponds to n8n.io template #5598 — we link there as the canonical source.
This workflow follows the Agent → LinkedIn 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": "G2rpmq6qJiMyA708",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "jekyll-autopost",
"tags": [],
"nodes": [
{
"id": "5efad78c-f4ea-490e-83c9-9c8c34eaeb21",
"name": "Start",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-1740,
420
],
"parameters": {},
"typeVersion": 1
},
{
"id": "884e4291-6483-4865-a1c4-35e0d466cfab",
"name": "Read CSV",
"type": "n8n-nodes-base.readBinaryFile",
"position": [
-1480,
460
],
"parameters": {
"filePath": "/data/recipes.csv",
"dataPropertyName": "=data"
},
"typeVersion": 1
},
{
"id": "bfddf1ce-7d31-4cca-b249-be0ffbc2978c",
"name": "Split In Batches",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-1080,
440
],
"parameters": {
"options": {},
"batchSize": 1
},
"typeVersion": 1
},
{
"id": "53a35d7c-b210-4b27-82e4-61fe7eba9bf4",
"name": "Wait Until Publish",
"type": "n8n-nodes-base.wait",
"disabled": true,
"position": [
-220,
-180
],
"parameters": {
"unit": "=",
"amount": "={{ $json.data_pubblicazione }}"
},
"typeVersion": 1
},
{
"id": "d885e9ab-0f9c-46c2-af27-914628718365",
"name": "Commit Markdown",
"type": "n8n-nodes-base.github",
"position": [
-100,
360
],
"parameters": {
"owner": {
"__rl": true,
"mode": "",
"value": "antonio-backend-projects"
},
"filePath": "={{ $json[\"markdownPath\"] }}",
"resource": "file",
"repository": {
"__rl": true,
"mode": "list",
"value": "jekyll-recipe-ai",
"cachedResultUrl": "https://github.com/antonio-backend-projects/jekyll-recipe-ai",
"cachedResultName": "jekyll-recipe-ai"
},
"fileContent": "={{ $('Code').item.json.markdownContent }}",
"commitMessage": "=={{ 'Add recipe: ' + $json.titolo }}"
},
"credentials": {
"githubApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "78d9ca4f-392d-47f6-98c1-b5b2a671c736",
"name": "Post on X",
"type": "n8n-nodes-base.twitter",
"disabled": true,
"position": [
160,
-220
],
"parameters": {
"operation": "createTweet"
},
"typeVersion": 1
},
{
"id": "319bd723-ff2c-40ca-9519-b38107323b49",
"name": "Post on LinkedIn",
"type": "n8n-nodes-base.linkedIn",
"disabled": true,
"position": [
340,
200
],
"parameters": {
"text": "={{$json.titolo}}",
"additionalFields": {}
},
"typeVersion": 1
},
{
"id": "7e6d5cac-befd-4cb6-8564-b4268e9dd04e",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
-1260,
-40
],
"parameters": {
"options": {
"delimiter": ";"
}
},
"typeVersion": 1
},
{
"id": "f72b0e71-92bb-4eb5-ad18-5c5abecd3699",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-980,
-100
],
"parameters": {
"color": 3,
"width": 420,
"height": 440,
"content": "## Write SEO Optimized Blog Post\n\n\n"
},
"typeVersion": 1
},
{
"id": "49cfd514-17d0-467b-b658-7a1cc64fffc2",
"name": "Copywriter AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-900,
0
],
"parameters": {
"text": "=You are a SEO-first food writer for an Italian recipe blog built with Jekyll.\nWrite an article of 800\u20131000 words, with a professional yet warm and accessible tone.\nDO NOT include any front matter.\n\n### POST INPUT\n- Recipe title: {{ $json.titolo }}\n- Description / brief: {{ $json.prompt_descrizione }}\n- Main keyword: {{ $json.keyword_principale }}\n- Secondary keywords (to integrate naturally): {{ $json.keyword_secondarie }}\n\n### GUIDELINES\n1. Start the article with an H2 using the exact title. \n2. Include the **main keyword** in the title, in the first paragraph, and in at least one H3. \n3. Structure the article in Markdown with the following blocks **in order**:\n - Introduction (brief history or fun fact about the recipe)\n - *Ingredients* section (bullet list)\n - *Instructions* section (numbered steps)\n - Chef\u2019s tips / tricks for a perfect result\n - Wine or beverage pairing\n - Possible variations or substitutions\n - FAQ (at least 3 short Q&A entries)\n - Conclusion with **CTA**: invite the reader to try the recipe and explore other recipes on the blog\n4. Highlight keywords using **bold** or *italic* where appropriate (but don\u2019t overdo it). \n5. Keep sentences and paragraphs short, use bullet points and H3s for readability. \n6. Avoid emojis and overly promotional language; tone should be friendly yet authoritative. \n7. The output must be **only the Markdown content** of the article, with no extra explanations.\n\n### SEO GOAL\n- Optimize for the main keyword without keyword stuffing; distribute secondary keywords naturally.\n- Use Italian synonyms where relevant (e.g., \u201cfunghi porcini freschi\u201d, \u201criso Carnaroli\u201d, etc.).",
"options": {},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "16b047d2-0d4d-4fa7-a4f9-9b65025d51f0",
"name": "gpt-4o-mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-900,
200
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "27288133-400d-4957-b7d2-b1ee2260c12a",
"name": "Code",
"type": "n8n-nodes-base.code",
"position": [
-400,
20
],
"parameters": {
"jsCode": "// Item proveniente da \"Split In Batches\" (indice 0)\nconst base = $items(\"Split In Batches\")[0].json;\n\n// 1. Slug SEO-friendly\nconst slug = base.titolo\n .toLowerCase()\n .replace(/[^a-z0-9]+/g, '-')\n .replace(/(^-|-$)/g, '');\n\n// 2. Front-matter Jekyll\nconst frontMatter = `---\\ntitle: \"${base.titolo}\"\\ndate: ${base.data_pubblicazione} +0200\\nlayout: post\\n---`;\n\n// 3. Contenuto AI\nconst aiContent = $json.output.trim();\n\n// 4. Markdown completo\nconst markdown = `${frontMatter}\\n\\n${aiContent}`;\n\nreturn [\n {\n json: {\n ...base, // mantiene titolo, keyword\u2026\n slug,\n markdownPath: `_posts/${base.data_pubblicazione.slice(0,10)}-${slug}.md`,\n markdownContent: markdown\n }\n }\n];\n"
},
"typeVersion": 2
},
{
"id": "a7816b95-b5a0-44b6-af54-a90177524f7e",
"name": "Remove the processed csv line",
"type": "n8n-nodes-base.code",
"position": [
-840,
500
],
"parameters": {
"jsCode": "const fs = require('fs');\nconst CSV_PATH = '/data/recipes.csv';\n\n// 1. Leggi il CSV attuale\nconst rawCsv = fs.readFileSync(CSV_PATH, 'utf8').trim();\nconst rows = rawCsv.split('\\n');\n\n// 2. Filtra via la riga pubblicata\nconst filtered = rows.filter((row, idx) => {\n\tif (idx === 0) return true; // header\n\treturn row.split(';')[0] !== $json.titolo;\n});\n\n// 3. Se \u00e8 cambiato, riscrivi il file\nif (filtered.length !== rows.length) {\n\tconst newCsv = filtered.join('\\n') + '\\n';\n\tfs.writeFileSync(CSV_PATH, newCsv, 'utf8');\n}\n\n// 4. Restituisci l\u2019item JSON senza binari inutili\n// 4. Restituisci l\u2019item originale (senza binari aggiuntivi)\nreturn [\n\t{\n\t\tjson: $json\n\t}\n];\n"
},
"typeVersion": 2
},
{
"id": "39814681-6340-4b30-a4b9-14bc8298243f",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-1660,
-180
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 8
}
]
}
},
"typeVersion": 1.2
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "9ce77bdb-3568-43ea-8e92-c5a282b870e4",
"connections": {
"Code": {
"main": [
[
{
"node": "Wait Until Publish",
"type": "main",
"index": 0
}
]
]
},
"Start": {
"main": [
[
{
"node": "Read CSV",
"type": "main",
"index": 0
}
]
]
},
"Read CSV": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
},
{
"node": "Remove the processed csv line",
"type": "main",
"index": 0
}
]
]
},
"Post on X": {
"main": [
[
{
"node": "Post on LinkedIn",
"type": "main",
"index": 0
}
]
]
},
"gpt-4o-mini": {
"ai_languageModel": [
[
{
"node": "Copywriter AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Commit Markdown": {
"main": [
[
{
"node": "Post on X",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Read CSV",
"type": "main",
"index": 0
}
]
]
},
"Split In Batches": {
"main": [
[
{
"node": "Copywriter AI Agent",
"type": "main",
"index": 0
},
{
"node": "Remove the processed csv line",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Split In Batches",
"type": "main",
"index": 0
}
]
]
},
"Wait Until Publish": {
"main": [
[
{
"node": "Commit Markdown",
"type": "main",
"index": 0
}
]
]
},
"Copywriter AI Agent": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Remove the processed csv line": {
"main": [
[]
]
}
}
}
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.
githubApiopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow automates the entire process of publishing SEO-optimized blog posts (e.g., recipes) to a Jekyll site hosted on GitHub. It uses LangChain + OpenAI to write long-form Markdown articles, and commits them directly to your repository. Optional steps include posting to X…
Source: https://n8n.io/workflows/5598/ — 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.
This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents.
Tool Http Request, Agent, HTTP Request +27
Hacker News to Video Template - AlexK1919. Uses manualTrigger, hackerNews, splitInBatches, lmChatOpenAi. Event-driven trigger; 48 nodes.
Hacker News, OpenAI Chat, Tool Http Request +11
Instead of staring at a blank page, this workflow scrapes top-performing content, breaks down the psychological hooks, rewrites it for your specific audience, and drafts a custom text graphic. Once yo
Twitter, Facebook Graph Api, LinkedIn +8
Awesome N8N Templates. Uses stickyNote, gmail, executeWorkflowTrigger, httpRequest. Event-driven trigger; 35 nodes.
Gmail, Execute Workflow Trigger, HTTP Request +7
Whether you’re a product manager, developer, or simply curious about workflow automation, you’re in the right place. This n8n workflow is designed to help you streamline and automate your social media
Output Parser Structured, OpenAI Chat, LinkedIn +8