Workflow 04 / Marketing
Content Repurposing Engine
One new blog post becomes LinkedIn, X, newsletter and quote-card copy waiting for approval.
- Trigger
- New post in an RSS feed
- Size
- 8 nodes, 3 credentials
- Typical build
- 4 working days
- Tools
- n8n, RSS, OpenAI API, Google Sheets, Slack
Example scenario: B2B fintech, two long-form articles a week, two-person marketing team
The problem
The marketing team had no time to turn articles into social posts. Distribution was inconsistent and most articles were shared once, by the founder, on a Friday evening.
What the workflow does
The solution
n8n watches the blog RSS feed, fetches each new article and extracts the body. An LLM with a written brand-voice guide produces a LinkedIn post, a five-post X thread, a newsletter blurb and three quote cards. Everything lands in the content calendar sheet scheduled for 9:00 the next day with Status "Awaiting approval". Slack announces the row and the team approves by setting Status to Approved in the sheet. Invalid AI output is reported to Slack instead of being queued.
The flow
Drawn from the real JSON
Node names, order and branches are read from the exported file at build time, so this diagram can never drift from what n8n will show you. Dashed lines are connections; amber ones leave an IF, a Switch or an error output.
Download n8n JSONScroll sideways to see all branches
Node by node
| # | Node | Type | What it does |
|---|---|---|---|
| 01 | RSS: New Blog Post | Trigger | Polls blog.example-fintech.example/rss.xml every hour |
| 02 | HTTP: Fetch Article | App action | GET article URL |
| 03 | HTML: Extract Body | Transform | Extracts the article title and body text |
| 04 | LLM: Repurpose | AI step | Chat completion (gpt-4o-mini), JSON-only output |
| 05 | Parse Assets | Transform | Validates the LLM answer and builds the calendar row. Invalid output leaves through the error output. |
| 06 | Sheets: Content Calendar | App action | Appends a row to the "Queue" tab |
| 07 | Slack: Parse Failure | App action | Posts a message to #content |
| 08 | Slack: #content Approval | App action | Posts a message to #content |
How a run goes
RSS trigger checks the blog feed every hour.
HTTP Request fetches the article page; the HTML node extracts title and body.
The LLM repurposes the text into four formats using the brand-voice rules.
A Code node validates all four formats and schedules the publish slot; invalid output goes to a Slack warning instead.
Google Sheets appends the row to the content calendar with status "Awaiting approval".
Slack posts a preview to the content channel; the team approves by setting Status to Approved in the sheet.
Tools and credentials
Credentials are referenced by name inside the JSON. Create each one in n8n under Credentials, using these names, and the nodes connect automatically.
| Credential name | What you need |
|---|---|
| OpenAI – Flowforge | API key from platform.openai.com |
| Slack – Flowforge Bot | Bot token with the chat:write scope |
| Google Sheets – Ops | Google OAuth client with the Sheets API enabled |
Setup in about 30 minutes
Import the file. In n8n open Workflows, then Import from file, and pick
content-repurposing.json. The workflow arrives inactive.Create the 3 credentials listed above with exactly those names.
Replace the placeholders with your own IDs:
REPLACE_WITH_CALENDAR_SHEET_IDin “Sheets: Content Calendar”
Adapt it to your business.
- Set the feed URL in the RSS trigger to your blog.
- Paste your brand-voice guide (tone, banned phrases, three example posts) into the system prompt of "LLM: Repurpose".
- Create the calendar sheet with a "Queue" tab and these columns: Publish on, Source, URL, LinkedIn, X thread, Newsletter, Quotes, Status.
- Publishing stays manual by design: approval is the Status column in the sheet. To auto-post, add a Buffer or LinkedIn step that runs when Status changes to Approved.
Connect error reporting. Import
error-reporter.jsononce, then open this workflow’s Settings and choose it as the Error workflow. Failed runs are posted to Slack and logged, with a link to retry.Test, then activate. Run the first node with sample data, check each output in the execution view, then switch the workflow to active. Keep the test run for your records.
Example figures for the scenario above, not guarantees
What this kind of build changes
Use it, or have it built for you
The JSON is free to import and adapt. If you would rather have it wired to your own stack and tested on your data, a single flow like this is a fixed-price project.