Blog to LinkedIn & X: Claude + Make

A wildlife rehabilitator runs a small blog about the owls and hawks she nurses back to health. Each post could do well on LinkedIn and X, where rescue stories travel. They never get there, because at 9pm after feeding a fledgling she is not opening three more tabs to rewrite the same story twice.

This build does the rewriting. When you publish a post, Claude reads it and writes two versions tuned to each platform, then drops them into your Buffer queue. You skim them in the morning, tweak a line, and approve. The post promotes itself; you stay the editor.

We are using Make as the wiring and Buffer as the one place that posts to LinkedIn and X for you. If you have built our spreadsheet-to-WordPress guide, this is the mirror image: WordPress is the trigger now, not the destination.

What does this workflow actually do?

In one line: a new blog post becomes two social posts. Make watches WordPress. When you publish, it sends the post to Claude with instructions for each platform, Claude writes a LinkedIn version and an X version, and Make queues both in Buffer. Nothing posts automatically; Buffer holds them for your review.

A few real cases, none of them the usual ones:

• The wildlife rehabber above, finally getting her rescue posts onto LinkedIn where donors actually see them.
• A harbor pilot who blogs about ship-handling and wants the highlights on X for the maritime crowd.
• A two-person tabletop game studio turning each devlog into a LinkedIn update for publishers and an X post for players.
• A township historical society volunteer who writes one post a week and wants it shared without learning three apps.

Writing the blog post is the work they already do. Rewriting it for two audiences is the chore they skip. That is the part Claude handles.

Why use Make if Claude can already write?

Worth asking. Claude is good at the rewrite: same story, different shape for LinkedIn versus X. It is not built to watch WordPress, move text between apps, and queue posts on a schedule. That is plumbing, and Make does plumbing.

Make handles the steps that need no judgment: noticing the new post, passing it along, queuing it, running on its own. Claude handles the one step that needs taste, the writing. Make is the conveyor; Claude is the writer at the end of it. I have tried making the AI do the whole pipeline, and it was slower and more brittle. Splitting the work is what keeps it reliable.

What do you need before you start?

• A Make account. The free plan covers 1,000 operations a month, plenty for a blog that posts a few times a week.
• A Claude API key from the Claude console (not the chat app). New to Claude? Start with how to use Claude.
• A WordPress site with an application password (Users, then Profile, then Application Passwords).
• A Buffer account with your LinkedIn and X channels connected.

Two Make words, once. A scenario is one automation, the whole WordPress-to-Buffer chain. A module is one box in it. Three boxes, one scenario.

How does the workflow work, step by step?

Three modules, left to right:

Module	App	What it does
1. Trigger	WordPress	Watches your site and fires when you publish a post
2. Brain	Claude	Writes a LinkedIn version and an X version
3. Output	Buffer	Queues both posts for your approval

Step 1: Watch WordPress for new posts

Create a scenario in Make and add WordPress, Watch posts. Connect your site with the application password and choose to watch published posts. This is the trigger. It hands the next step your post’s title, content, and link.

Step 2: Let Claude write both versions

Add a Claude module (Anthropic), choose Create a Prompt, paste your API key, and pick Claude Sonnet. The prompt is where you set your voice for each platform:

Write two social posts from this blog article.
Title: {{post title from Step 1}}
Article: {{post content from Step 1}}
Link: {{post link from Step 1}}

First, a LinkedIn post: 3 short paragraphs, a clear takeaway, no
hashtag spam. Then a separate X post: under 280 characters, punchy,
one link. Label them LINKEDIN: and X: so they are easy to split.

The {{ }} tokens are mapped in from Step 1, so each post fills them automatically. This is the same prompt craft as any Make AI scenario.

Step 3: Queue both in Buffer

Add Buffer, Create a status update. Connect Buffer, pick your LinkedIn and X channels, and map the matching part of Claude’s reply to each. Set Buffer to add to queue, not post immediately, so nothing goes out until you say so. That review step is the difference between a helper and an embarrassment.

How do you run it and check the result?

Click Run once. Make takes your latest post, sends it to Claude, and queues two drafts in Buffer. Open Buffer and read them. When I tested this, the LinkedIn version was solid out of the gate and the X version needed a tighter first line, which is a ten-second fix. Tune the Step 2 prompt until both come out the way you like, then switch the scenario on so it runs on every new post.

After that, publishing a blog post quietly produces its own promotion. For a blog that posts twice a week, that is roughly eight LinkedIn posts and eight X posts a month you were not going to write by hand.

What does this cost to run?

Piece	Free tier	If you outgrow it
Make	1,000 operations/month free	Core plan from about $9/month
Claude API	Pay per use	Two short posts on Sonnet cost a fraction of a cent
WordPress	Your existing site	No extra cost
Buffer	Free plan covers a few channels	Paid plans from about $6/channel/month

Each post uses three Make operations and a sliver of Claude. The real cost is the twenty-minute setup. For Make’s tiers, see our Make beginner’s guide.

What can go wrong, and how do you avoid it?

• Posts go out before you read them. Only if you set Buffer to post immediately. Use add-to-queue so you approve first.
• The X version is too long. Tell Claude the character limit in the prompt and ask it to count. This is the one I had to nudge in testing.
• It fires on old posts on first run. Normal. Clear the test drafts from Buffer and let it settle.
• Claude mixes the two versions together. Keep the LINKEDIN: and X: labels in the prompt so Make can split them cleanly.

Want more of this pattern? Our Make AI scenarios roundup has the next ideas.

How do you build this in Zapier or n8n instead?

The three jobs do not change, only the names do.

Job	Make	Zapier	n8n
Catch a new post	Watch posts	New Post in WordPress	WordPress Trigger node
Write the versions	Claude module	Claude (Anthropic) action	Anthropic node
Queue to social	Buffer status update	Buffer action	Buffer node

Make and Zapier are the gentlest for a first build. n8n suits self-hosting. We compared all three in Zapier vs Make vs n8n.

Common questions

Do I have to use Buffer?

No. Buffer is the easy choice because it posts to LinkedIn and X from one module. You can swap it for direct LinkedIn or X modules if you prefer, with a little more setup.

Will it post the same text to both?

No, that is the point. Claude writes a separate version for each, because what works on LinkedIn reads wrong on X.

Can I add Threads, Bluesky, or Facebook too?

Yes. Buffer supports more channels, and you add them in the same Buffer step. Start with two so the build stays simple.

Is the Claude chat app the same as the API?

Same models, different door. The app is for you; the API is for software like Make. You need an API key here.

What if I only want a draft, not a queued post?

Buffer’s queue is effectively a draft you approve. Nothing publishes until you click, so you stay in control.

Sources and docs

• Creating a scenario (Make Help)
• Claude API overview (Anthropic)
• Buffer Help Center
• WordPress REST API
• Make — Grokipedia

Last reviewed: May 2026. Make, Claude, Buffer, and WordPress change their interfaces; check the official pages for exact button names.

You may also like

• Turn a YouTube video into a WordPress draft with Claude
• Draft WordPress posts from a spreadsheet with Claude + Make
• Make.com Complete Beginner’s Guide
• Make AI Scenarios: automations that save hours
• How to use Claude AI
• Zapier vs Make vs n8n: which to start with
• The AI Tools Directory