Mindket

X posts written by AI on a schedule from a niche and style

Newversion 1 · updated

Overview

An n8n workflow that has OpenAI write a post for an X account from a niche, a style and some inspiration, checks its length and posts it every six hours or on demand.

X posts written by AI on a schedule from a niche and style is an n8n workflow in the Marketing & SEO category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud: import the file there and activate it
  • Your own n8n server: the same file and steps
  • OpenAI: where the posts are written
  • X: where the posts appear

Platform

Connects 2 apps

How it works

Trigger

Every six hours, or by hand

It starts on a timer, every six hours at a minute drawn when you activate it, or when you click Test workflow in n8n:

  • The niche, the style and the inspiration, set in Configure your influencer profile
  • The prompt lines, set in Generate tweet content
  • The interval, set in Schedule posting every 6 hours

Actions

  1. The niche, the style and the inspiration are set
  2. OpenAI writes a post as a JSON object with one key, tweet
  3. The post’s length is checked, and a post over 280 characters is written again
  4. The post is published to X

Result

A new post on your X account every six hours

Integrations

What you need before you start.

OpenAI

Post writer

Writes each post from the niche, the style and the inspiration.

NeedsAn OpenAI API key

X

Publishing

Receives and publishes each post.

NeedsA developer app with an OAuth2 credential that may post

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
6 steps, starting on a schedule or by hand
AI
1 step calls an AI model: Generate tweet content
Sign-ins
Signs in to: X
API keys
No API key is left in the file
Step types
Mindket’s checker reads all 6 of its step types

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow writes posts for an X account on a timer. You set a niche, a writing style and some inspiration. OpenAI writes a post, the workflow checks it fits in 280 characters, and the post goes to X. It runs every six hours or by hand. Six nodes run it, beside six sticky notes.

Who it suits

Creators and small brands who want a steady stream of posts in one voice. Skip it if no person will look at the account, since the workflow posts with no check.

Who uses it, and how
IndustryWho uses itHow they use itExample
CreatorsNiche writersKeep an account active between longer piecesA writer sets a theme and gets four posts a day.
BrandsSmall businessesShare tips in one voiceA shop posts care tips for its products on a rhythm.
EducationTutorsShare a daily thoughtA tutor posts short ideas from the books they teach.
ExperimentsBuildersTest an automated accountA builder watches how a posting bot performs on a test account.

You need some n8n, an OpenAI key and an X developer app: import a file, add two credentials and edit three settings.

Where to use it

Any n8n that can reach OpenAI and X will run it. Activate it to post on the timer, or run it by hand.

  • n8n Cloud: import the file there and activate it
  • Your own n8n server: the same file and steps
  • OpenAI: where the posts are written
  • X: where the posts appear

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Setup takes two credentials and three edited settings.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
OpenAIAn API key
XA developer app with an OAuth2 credential that may post, and credits for the posts
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add an OpenAI credential and select it in Generate tweet content.
  3. Add an X credential and select it in Post tweet.
  4. In Configure your influencer profile, replace the niche, the style and the inspiration with your own.
  5. Click Test workflow, ideally on a test account, since it posts for real.
  6. Activate the workflow to run it every six hours.

How to use it

Run it by hand to see a post, then activate it for the timer. Read the first posts before you leave it alone, and check what they cost on X.

What to change for a different result
To changeWhere
The voiceConfigure your influencer profile
The promptThe system lines in Generate tweet content
How oftenSchedule posting every 6 hours
The modelGenerate tweet content

Example

A writer sets the niche to modern Stoicism and a personal style, with a short list of books as inspiration. The workflow runs at midday.

OpenAI returns a short post with a hashtag and an emoji, such as a Stoic line tied to a morning routine. The length check passes, and the post appears on the account.

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. Here one box sets the profile, one writes, one checks the length and one posts. Run it first by hand on a test account.

For experts. The OpenAI node uses JSON output, and Post tweet reads message.content.tweet. The length check loops back to the profile node when the post is too long.

Where to look closer
NodeWhat it doesWhat to know
Schedule posting every 6 hoursStarts the timerIts minute is drawn once, when you activate the workflow
Generate tweet contentWrites the post as a JSON objectIt names gpt-6-luna and asks for one key, tweet
Verify tweet constraintsCompares the length with 280A post that is too long goes back and is written again
Post tweetPosts the text to XIt needs an X credential that may write

Good to know

The workflow posts to a real account with no person checking first, and X’s automation rules ask automated accounts to carry the automated label.

  • The repair: the model was gpt-4-turbo-preview, which OpenAI’s deprecations page, read on 12 November 2026, lists as shut down on 26 March 2026. This copy names gpt-6-luna, and its last system line now asks for an object with the key tweet
  • Invented stories: the example style asks for personal stories, so the model makes them up. Edit the style if you do not want that
  • Loops: a post that stays too long is written again, with no limit on the tries
  • Cost: X’s pricing page lists $0.015 for a post and $0.20 for a post with a link
  • Not run: this copy was not run against OpenAI or X
  • Your data: the settings go to OpenAI, and the post goes to X
  • Credentials: the JSON holds none

README and files

README

X posts written by AI on a schedule from a niche and style

An n8n workflow that writes a post for an X account from a niche, a writing style and some inspiration that you set. It runs every six hours or by hand, writes the post again when it is over 280 characters and posts the rest.

What is inside

  • workflow.json: the workflow as n8n exports it, twelve nodes: six that do the work and six sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • The credential links are gone. Select your own for OpenAI and X.
  • The model was gpt-4-turbo-preview. OpenAI's deprecations page, read on 12 November 2026, lists gpt-4-0125-preview, which includes gpt-4-turbo-preview, as shut down on 26 March 2026, and points to gpt-5 or gpt-4.1. The same page lists the gpt-4.1 family for shutdown on 14 January 2027 with gpt-6-luna as its replacement. The step has no tools, so this copy names gpt-6-luna.
  • The last system message asked for the post alone, but the node's JSON mode returns an object, and Post tweet reads message.content.tweet. The message now asks for an object whose one key, tweet, holds the post.
  • The note on scheduling said the minute is randomized to seem natural. n8n's source reads the schedule once, when you activate the workflow, so the minute is drawn once then. The note now says so.
  • Nothing else.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • An OpenAI API key.
  • An X developer app with an OAuth2 credential that may post for the account. X sells pay-per-use credits in advance, at $0.015 for a post and $0.20 for a post that holds a link.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add an OpenAI credential and select it in Generate tweet content.
  3. Add an X credential and select it in Post tweet.
  4. Open Configure your influencer profile and replace the three example settings with your own.
  5. Click Test workflow. This posts to the account for real, so use a test account first.
  6. Activate the workflow to run it every six hours.

How a run goes

  1. Schedule posting every 6 hours starts a run, at a minute that was drawn when the workflow was activated. Trigger posting manually starts one by hand.
  2. Configure your influencer profile sets niche, style and inspiration.
  3. Generate tweet content sends the model a series of system lines. They give the influencer role, the style, the inspiration and the niche. A last line asks for the post under the key tweet, within the limit, with hashtags and emojis, and states the current date and time. A user line asks for a post that will go viral.
  4. Verify tweet constraints checks the length. A post over 280 characters goes back to Configure your influencer profile and is written again.
  5. Post tweet posts the text.

Change the look

  • The voice: Configure your influencer profile.
  • The prompt: the system lines in Generate tweet content.
  • How often: the interval in Schedule posting every 6 hours.
  • The model: Generate tweet content.

Good to know

  • The workflow posts to a real account with no person checking it first. X's automation rules and its page on automated account labels, read on 12 November 2026, say an automated account carries the automated label and stays connected to a human-run account. Set the label if the account is automated.
  • The example style says the posts are personal and share personal stories, so the model will invent them. Edit the style if you do not want invented stories presented as real.
  • A post that stays too long is written again, with no limit on the tries.
  • With X's pay-per-use prices, four posts a day add up. A post with a link costs far more than one without.
  • This copy was not run against OpenAI or X.
  • Your profile settings go to OpenAI, and the post goes to X.
  • The JSON holds no credential.
Files
NOTICE.md  597 B
README.md  4 KB
workflow.json  9 KB

3 files, 13 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Huashu Design

alchaincyf · Skill

Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…

New29.4k

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Claude Code Skills & Plugins

alirezarezvani · Skill

Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…

New29.8k

Similar in Marketing & SEO

See all in Marketing & SEO

Pixel Art XL

nerijs · Kit

A pixel art style add-on for Stable Diffusion XL that turns text prompts into pixel-style images, with an optional LCM LoRA for faster runs. For game makers, d…

New

Licon MSR for LTX-2.5

LiconStudio · Kit

Keeps characters, clothing, objects and backgrounds consistent in generated video by feeding the model up to five reference images. A LoRA for LTX-2.5 in Comfy…

New

Flux.2-Klein-9B-MatchingPose

nhathoangfoto · Kit

A LoRA for FLUX.2 Klein 9B that puts a character into the pose shown by a mannequin reference while keeping the character's face and style. For artists and des…

New