All templates
FeaturedAI#LLM#Content#Social Media#Marketing#OpenAI

AI Content Repurposer

Paste a blog URL — fetch the article and get a ready-to-post LinkedIn update and Twitter/X thread in one run.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#LLM#Content#Social Media#Marketing#OpenAI

Click a node to select it — same as the Heym editor; the panel shows its settings.

9 nodes · Free & source-available

AI Content Repurposer

Turn any blog post into platform-ready social content in seconds. Heym fetches the article, passes it to two LLM nodes tuned for each platform, and delivers a LinkedIn post and a Twitter/X thread ready to copy-paste.

What this workflow does

  1. Input accepts a blog post URL
  2. Crawler fetches and cleans the article body
  3. LLM (LinkedIn) rewrites the key insights as an engaging LinkedIn post (≤1,300 characters, 3–5 hashtags)
  4. LLM (Twitter) distills the article into a numbered Twitter/X thread of 8–10 tweets
  5. Set bundles both outputs into a single result object
  6. Output returns the ready-to-post content

Use cases

  • Scale content distribution from a single article to multiple channels
  • Repurpose evergreen blog posts on a weekly schedule
  • Give marketing teams first drafts to edit rather than create from scratch

Setup

No API keys are embedded. Connect an OpenAI credential in Heym. You can swap in Claude or Mistral via the LLM node model dropdown after importing.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3Press Cmd+V / Ctrl+V — nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym