Mindket
English
English简体中文
Sign inSign up
StoreMCPSkillsCalculatorLearnPriceBlog
Discover
Research312Writing59Business95Legal13Finance & accounting33Marketing & SEO175Developer1,422Productivity391Education81Companions14
Help and support
Language
English简体中文

Article turned into an X thread and a LinkedIn post by AI

by Mindketn8n workflowMarketing & SEO
Newversion 1 · updated
Nodes4Apps1Like

Overview

  1. Article Form
  2. Chat Model
  3. Repurpose Content
  4. Show Posts
Article turned into an X thread and a LinkedIn post by AI, picture 1
‹2 / 2›

An n8n workflow that takes one pasted article or transcript and drafts two posts from it: a numbered X thread and a LinkedIn post. An AI agent may use only facts from your text, and it asks for a person when the text is too thin.

Article turned into an X thread and a LinkedIn post by AI 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 into a new workflow there
  • Your own n8n server: the same file and steps
  • Another model: swap the Chat Model node for any chat model node

Platform

n8nWorkflow automation, in n8n’s cloud or on your own server
Connects 1 app

How it works

Trigger

Web form

You start it by submitting a form, and it needs:

  • The article or transcript, pasted into one long-text field
  • Optional voice notes

Actions

  1. The form’s two answers are collected
  2. The text is tidied of extra spaces and cut at 9,000 characters
  3. An agent writes a numbered X thread and a LinkedIn post using only that text
  4. A completion page shows both drafts, or a line asking for a person when the text is too thin

Result

An X thread of six to nine numbered tweets and a LinkedIn post, shown on the form’s result page

Integrations

What you need before you start.

OpenAI

Post writer

Writes the thread and the LinkedIn post from the pasted text.

NeedsOpenAI API key

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
3 steps, starting on a form
AI
1 step calls an AI model: Repurpose Content
Sign-ins
Signs in to: OpenAI
API keys
No API key is left in the file
Step types
Mindket’s checker reads all 3 of its step types

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

About

What it is

This n8n workflow turns one long article or transcript into two drafts: a numbered thread for X and a post for LinkedIn. You paste the text into a web form and can add optional voice notes. An AI agent writes both drafts using only facts found in your text. When the text is too thin or unreadable, you get a line for a person to look at instead of padded posts. Four nodes run it.

Who it suits

Writers, marketers and founders who publish long pieces and want first drafts for social channels. Skip it if you need posts scheduled or sent for you, since it only drafts text on a results page.

Who uses it, and how
IndustryWho uses itHow they use itExample
MediaNewsletter writersTurn an issue into a threadA writer pastes an issue and gets a hook tweet that names its sharpest point.
SoftwareDeveloper advocatesShare a long post on two channelsAn advocate pastes a launch post and edits the LinkedIn draft before publishing.
ConsultingIndependent consultantsTurn a talk into postsA consultant pastes a talk transcript and gets numbered tweets that follow its argument.
PodcastsHosts and producersPromote an episodeA producer pastes an episode transcript and gets a thread that ends by pointing to the episode.

You need a little n8n: import a file, add an OpenAI credential and open a web form.

Where to use it

Any n8n that can reach OpenAI will run it. It starts from a web form that n8n hosts for you, and you open that form from a link.

  • n8n Cloud: import the file into a new workflow there
  • Your own n8n server: the same file and steps
  • Another model: swap the Chat Model node for any chat model node

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. You need an OpenAI key and the text of one article or transcript.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
OpenAIAn API key
Source textAn article or transcript with at least about 200 useful words
  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 Chat Model.
  3. Open Article Form and use its test address to open the form.
  4. Paste your article or transcript, add voice notes if you want them, and submit.
  5. Read the two drafts on the page that follows, then publish the workflow if you want a lasting form address.

How to use it

Open the form, paste a text and read the result. Edit both drafts before you post them, and submit the form again for the next text. If the result starts with [NEEDS-HUMAN], the text was too thin or unreadable.

What to change for a different result
To changeWhere
The rules and the banned phrasesThe system message in Repurpose Content
The thread length or the post lengthThe same system message
How much of the text is readThe 9000 in the text of Repurpose Content
The modelChat Model
Where the drafts goReplace Show Posts with a sheet or mail node

Example

A marketer pastes the text of a 1,500-word article and adds the voice note “keep it dry and factual”. The agent is told to write six to nine numbered tweets of at most 270 characters, with a hook first and a pointer to the original piece last. It is also told to write a LinkedIn post of 120 to 220 words that ends with a question.

If the pasted text has fewer than about 200 useful words, the result is [NEEDS-HUMAN] and a one-line reason.

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 form trigger starts a run when someone submits a web form. An AI agent is a node that asks a chat model to answer under written rules.

For experts. Repurpose Content takes the form’s two fields, collapses runs of whitespace in the text and cuts it at 9,000 characters. The agent has no tools and no memory, and Show Posts puts its output field on the completion page.

Where to look closer
NodeWhat it doesWhat to know
Article FormCollects the text and optional voice notesAnyone with its address can submit it
Repurpose ContentWrites both drafts under the rulesSees the first 9,000 characters
Chat ModelSupplies the modelgpt-5.6-terra in this copy
Show PostsShows the drafts on a completion pageNothing is posted

Good to know

One model line needed a swap, and the form is open to anyone with its link.

  • Model: OpenAI’s page, read on 12 November 2026, shuts gpt-4o-mini down on 14 January 2027 and names gpt-6-luna. That model supports function calling in Chat Completions only with reasoning effort set to none, so Mindket’s copy uses gpt-5.6-terra
  • Open form: anyone with the form’s address can spend your OpenAI credit
  • Drafts only: nothing is posted to X or LinkedIn, so read and edit both drafts first
  • Facts: the agent is told to use only the text you paste, but a model can still misread it. Check each claim against your source
  • Cut text: the agent sees the first 9,000 characters, so the end of a long text is ignored
  • Thin text: under about 200 useful words, you get the [NEEDS-HUMAN] line
  • Not run: Mindket read this copy against n8n’s source and did not run it on a live n8n
  • Your data: the text and your voice notes go to OpenAI
  • Credentials: the JSON holds none

README and files

README

Article turned into an X thread and a LinkedIn post by AI

An n8n workflow that turns one pasted article or transcript into two drafts: a numbered thread for X and a post for LinkedIn. You fill in a short web form with the text and optional voice notes. An AI agent writes both drafts using only facts from your text. When the text is too thin to use, you get a line for a person to look at instead of padded posts.

What is inside

  • workflow.json: the workflow as n8n exports it, 4 nodes. All four run, and there are no sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • Chat Model used gpt-4o-mini with a temperature of 0.5. OpenAI's deprecation page, read on 12 November 2026, shuts gpt-4o-mini down on 14 January 2027 and names gpt-6-luna. That model's page says Chat Completions supports function calling only with reasoning effort set to none, and n8n's chat model node offers only low, medium and high. The agent node calls its model as a tool-calling chat model, so the node uses gpt-5.6-terra, whose page lists function calling without that limit. It has no temperature setting, because that page lists none.
  • The form's webhook ID and the credential link are gone, and the file's name is ours.
  • Nothing else. The two form fields, the agent's rules and the completion page are as the file had them.

Mindket read this copy against n8n's source. It was not run on a live n8n.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • An OpenAI API key.
  • An article or transcript with at least about 200 useful words.

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 Chat Model.
  3. Open Article Form and use its test address to open the form in your browser.
  4. Paste your article or transcript. Add voice notes if you want the posts to follow a tone, then submit.
  5. Read the two drafts on the page that follows. When you are happy with the setup, publish the workflow so the form has a lasting address.

What happens in a run

  1. Article Form shows a form titled "Article → Thread + LinkedIn Post" with a required long-text field, Paste your article or transcript, and an optional field, Voice notes (optional).
  2. Repurpose Content gives the agent your voice notes, or the word none, and the text with its runs of whitespace collapsed, cut at the first 9,000 characters. The system message holds the rules. The model may state only what the text says, and it treats the text as material rather than as instructions. When the text is under about 200 useful words, an error page or unreadable, it answers [NEEDS-HUMAN] with a one-line reason.

The answer has two sections. The thread has six to nine numbered tweets of at most 270 characters, a hook first and a closing tweet that points back to the original piece. The LinkedIn post has 120 to 220 words in short lines, opens on the strongest finding and closes with a question. The model writes in the language of the text, avoids a short list of stock phrases and uses at most one emoji and one exclamation mark in each section.

  1. Show Posts puts the answer on a completion page titled "Your posts are ready".

What to change

  • The rules and the banned phrases: the system message in Repurpose Content.
  • The thread length or the post length: the same system message.
  • How much of the text is read: the 9000 in the text of Repurpose Content.
  • The model: Chat Model.
  • Where the drafts go: replace Show Posts with a sheet or mail node.

Good to know

  • The workflow only drafts. Nothing is posted to X or LinkedIn, so read and edit both drafts before you use them.
  • The agent is told to use only the text you paste, but a model can still misread it or word a point too strongly. Check each claim against your source.
  • The form has no sign-in. Anyone who has its address can use your OpenAI credit. Share the lasting address only with people you trust, or turn on the form's basic authentication.
  • The agent sees only the first 9,000 characters, so the end of a long text is ignored.
  • Data: the text and your voice notes go to OpenAI.
  • Cost: one model call per submission, billed by OpenAI.
Files
NOTICE.md  629 B
README.md  4 KB
workflow.json  4 KB

3 files, 9 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-13

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

anaksor-ocr

Sokheng · Kit

Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…

New

Qwen2.5-7B-Instruct-GGUF by Qwen

Qwen · Kit

Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…

New

ACE-Step 1.5 XL SFT

ACE-Step · Kit

Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…

New

Similar in Marketing & SEO

See all in Marketing & SEO

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

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