--- title: "LinkedIn post drafts from a Google Sheets topic queue" kind: "Kit" category: "Marketing & SEO" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/84870ab2-d5cd-4985-ae8b-dec52869c8fb" updated: "2026-11-09" --- # LinkedIn post drafts from a Google Sheets topic queue > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that turns a list of topics in Google Sheets into LinkedIn post drafts. Each run searches the next To Do topic with Tavily, an AI agent on OpenRouter writes a short post from three results, and the draft goes back into the row. LinkedIn post drafts from a Google Sheets topic queue is an n8n workflow in the Marketing \& SEO category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-09. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow drafts LinkedIn posts from a list of topics in a Google Sheet. Each run takes the first row marked To Do and searches the web for that topic with Tavily. An AI agent on OpenRouter reads the top three results and writes one short post for entrepreneurs, with a few hashtags and emojis. The draft lands in the row’s `Content` cell, and the status turns to Created. Nothing is posted for you. ### Who it suits Founders, consultants and small marketing teams who post on LinkedIn about their field and want a first draft, built from fresh sources, to edit. Skip it if your posts rest on your own stories or a voice other than upbeat. The prompt asks for a motivating post aimed at entrepreneurs, so you would rewrite most of each draft. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Consulting | Independent consultants | Queue a week of topics from their field on Monday | A consultant lists five topics and drafts one post each morning before client calls. | | Startups | Founders | Turn industry news into a post about what it means for them | A founder adds a funding trend as a topic and edits the draft into a post about the team. | | Marketing agencies | Social media managers | Keep one sheet per client with its own topics | A manager drafts posts for a client’s page and sends the sheet for approval. | | Recruiting | Recruiters | Post about hiring trends to stay visible to candidates | A recruiter adds remote hiring as a topic and posts the edited draft on Friday. | | Coaching | Business coaches | Keep posting between programs | A coach keeps a list of topics on habits and drafts two posts a week. | ### Where to use it Any n8n that can reach Google Sheets, Tavily and OpenRouter will run it. You start each run. The drafts stay in your sheet until you post them. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Google Sheets: the topic queue and the drafts, side by side in one row - LinkedIn: you copy each draft you like from the sheet and post it - A Schedule Trigger: put it in place of the manual one to draft a post every morning ### How to set it up Get it saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Its author puts setup at about 13 minutes. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | Tavily | An API key for its search endpoint | | OpenRouter | An API key for the chat model the agent runs on | | A spreadsheet | A tab named \`Sheet1\` with \`Topic\`, \`Status\` and \`Content\` in row 1 | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. Put one topic per row in `Topic`, with `To Do` in `Status`. 3. Add a Google Sheets OAuth2 credential. Select it in `Get Topic` and `Send Content`, and replace `YOUR_SHEET_ID` in both with the sheet’s ID. 4. In `Tavily`, replace `` in the Authorization header with your key. 5. Add an OpenRouter credential, select it in `OpenRouter Chat Model` and pick a current model there. 6. Save and press Execute workflow. The model in the file, `anthropic/claude-3.5-sonnet`, was missing from OpenRouter’s model list on 2 November 2026, which is why step 5 asks you to pick another one in that node. ### How to use it Mark a topic To Do and press Execute workflow. When the run ends, the row shows Created and the post sits in `Content`. Read it first. Change what does not sound like you, then post it on LinkedIn yourself. Each press drafts one topic. What to change for a different result | To change | Where | | --- | --- | | Audience and tone | The system message in \`Content Creator\`, written for entrepreneurs | | Length | The same message, at most 700 characters | | Hashtags and emojis | The same message: 2 to 4 hashtags and 1 to 3 emojis | | Search | \`search\_depth\`, \`max\_results\` and \`topic\` in the body of \`Tavily\` | | Recent results only | \`time\_range\` in that body, null in the file. Set it to week | | Status words | \`To Do\` in the filter of \`Get Topic\`, \`Created\` in \`Send Content\` | ### Example A row with the topic remote work tools for small teams and the status To Do. Tavily returns three results, and the agent receives their text in this shape: ```text Article 1: Article 2: Article 3: ``` It answers with the post alone, and `Send Content` writes it into the row: ```text Topic: remote work tools for small teams Status: Created Content: ``` ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. A credential is a key n8n keeps for you and hands to the node you pick it in. The Tavily key is the exception. It sits in a header field. Run one topic first, then open `Tavily` in the run to see what the agent was given. **For experts.** One search and one model call make each post. What each step sends | Step | Service | What to know | | --- | --- | --- | | \`Tavily\` | Tavily search, basic depth | Sends the topic with Search the web for in front of it and asks for 3 results plus a short answer, which nothing reads | | \`Content Creator\` | The model set in \`OpenRouter Chat Model\` | An agent with no tools. Its prompt reads \`results\[0\]\` to \`results\[2\]\` | | \`Send Content\` | Google Sheets update | Finds the row by \`Topic\`, so keep topics unique | ### Good to know Each run costs a Tavily search and one model call at OpenRouter. - One row a run: the manual trigger drafts the first To Do topic only. A Schedule Trigger in its place drafts one per interval - Recent news: the body sends \`days: 7\` with \`time\_range\` null. Tavily’s search reference, read on 2 November 2026, lists \`time\_range\` and no \`days\`, so results are not held to the last week until you set \`time\_range\` - Three results: the prompt reads three. With fewer, an article comes through empty or the agent stops with an error - No posting: the drafts stay in the sheet, so nothing reaches LinkedIn until you post it - One voice: every draft aims at entrepreneurs in an upbeat tone, whatever the topic - Your key: the Tavily key sits in a header as plain text and travels with any export of the workflow - Credentials: the JSON holds none, and nothing from its author’s account ## README ```markdown # LinkedIn post drafts from a Google Sheets topic queue An n8n workflow. Keep a list of topics in a Google Sheet. Each run takes the next one marked To Do, searches the web for it with Tavily, has an AI agent on OpenRouter write a short LinkedIn post, and puts the draft back in the row. Nothing is posted to LinkedIn. ## What is inside - `workflow.json`: the workflow as n8n exports it, 7 nodes, one of them a sticky note. It holds no credential. The spreadsheet and the Tavily key are left as placeholders. - `README.md`: these notes. ## Before you start - An n8n instance, on n8n Cloud or your own server. - A Tavily API key. - An OpenRouter API key. - A Google account, and a spreadsheet with a tab named `Sheet1` and these column names in row 1: `Topic`, `Status` and `Content`. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Fill the sheet with one topic per row in `Topic` and `To Do` in `Status`. Leave `Content` empty. Keep each topic unique, because the draft finds its row again by the topic. 3. Copy the spreadsheet's ID, the long part of its address between `/d/` and `/edit`. Add a Google Sheets OAuth2 credential, select it in `Get Topic` and `Send Content`, and replace `YOUR_SHEET_ID` with the ID in both. 4. In `Tavily`, replace `` in the Authorization header with your key. The brackets go too. 5. Add an OpenRouter credential and select it in `OpenRouter Chat Model`. Then pick a current model in the same node. The file names `anthropic/claude-3.5-sonnet`, which was not in OpenRouter's model list on 2 November 2026. 6. Save and press Execute workflow. The trigger node is named `When clicking ‘Test workflow’`. ## How a run goes - `Get Topic` returns the first row whose `Status` is `To Do`. - `Tavily` sends the topic with the words "Search the web for" in front of it. It asks for a basic search, three results and a short answer, which nothing reads. - `Content Creator` is an AI agent with no tools. It gets the content of the three results as Article 1, 2 and 3. Its system message asks for an upbeat post for entrepreneurs, at most 700 characters long, with 2 to 4 hashtags and 1 to 3 emojis. It must not quote the articles or name their sources. - `Send Content` finds the row by its `Topic` and writes the post in `Content` and `Created` in `Status`. ## Change the look - Audience and tone: the system message in `Content Creator`, written for entrepreneurs. - Length, hashtags and emojis: the same message. - Search: `search_depth`, `max_results` and `topic` in the body of `Tavily`. The agent reads exactly three results, so keep `max_results` at three or more. - Recent results only: `time_range` in the same body (below). - Status words: the `To Do` filter in `Get Topic` and the `Created` value in `Send Content`. ## Good to know - Each run drafts one topic. Press Execute workflow once per topic, or swap in a Schedule Trigger for the manual one to draft a post every morning. A run that finds no row marked To Do stops after `Get Topic`. - Nothing reaches LinkedIn. Read each draft in the sheet, make it yours and post it, or add a LinkedIn node after `Send Content`. - The search is not held to recent pages. The body sends `"days": 7` and `"time_range": null`, and Tavily's search reference, read on 2 November 2026, lists `time_range` (day, week, month or year) and no `days` field. Set `"time_range": "week"` to keep results to the last week. - If Tavily returns fewer than three results, the prompt asks for an article that is not there. That article comes through empty, or the agent stops with an error, depending on your n8n version. - Every draft aims at entrepreneurs in an upbeat tone, whatever the topic, so change the system message if your readers are someone else. - Tavily and OpenRouter each bill their own part of a run. - The Tavily key sits in the request header as plain text, so it travels with any export of the workflow. Take it out before you share the file. ``` ## What is in it 2 files, 12 KB, downloaded as a zip. ```text README.md 4 KB workflow.json 8 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 5 steps, starting by hand - AI: 1 step calls an AI model: Content Creator - Sign-ins: Signs in to: Google Sheets, OpenRouter and Tavily - API keys: No API key is left in the file; 1 blank in it for your own key - Step types: Mindket’s checker reads all 4 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/84870ab2-d5cd-4985-ae8b-dec52869c8fb) - [Its page on Mindket](https://mindket.com/p/84870ab2-d5cd-4985-ae8b-dec52869c8fb)