Skip to content

On a schedule

Share new blog posts on LinkedIn after a quick review

Each new article on your blog becomes a LinkedIn post draft in your inbox, published when you click approve.

Runs
On a schedule
Apps
Gmail, LinkedIn
AI
Yes, uses the built-in AI allowance
Access
gmail.send; w_member_social

Send this to your assistant

Create a ClickRuntime automation: every hour, check our blog feed for new articles. For each one, write a LinkedIn post that makes people want to read it, email it to me, and publish it only when I approve.

Paste it into your assistant. It tells you what it will send or change before it runs live.

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A small marketing team publishes good articles, then forgets to promote them. Someone is meant to write a LinkedIn post for each one, but it slips, and the article gets a fraction of the readers it could have had.

Drafting the LinkedIn post the moment an article appears, and putting it in front of the right person for a one-click review, means every article gets promoted without anyone remembering to do it.

What you get out of it

  • Every article gets promoted

    No post is forgotten, so each article gets the extra readers that LinkedIn brings, not only the ones someone remembered.

  • A human still signs off

    The draft waits for your approval, so the wording that represents your company is always checked.

  • Promotion happens on publish day

    The draft is ready within the hour, when the article is newest and most worth sharing.

  • Writers keep writing

    The person who wrote the article does not also have to write the social post, which keeps them on the work they do best.

How it works

What happens, step by step

  1. Every hour ClickRuntime checks your blog's feed for articles it has not seen before.

  2. For each new article, AI writes a short LinkedIn post with the article link.

  3. The draft is emailed to you from your Gmail with an approve link.

  4. Clicking approve publishes the post on LinkedIn, and each draft can only be published once.

Before it runs live

  • Connect Google through your own Google app (a one-time, 10-minute setup), so it works with your own Gmail
  • Connect LinkedIn

What you get

RunsOn a schedule
Share new blog posts on LinkedIn after a quick reviewtoday, 9:00Succeeded
Email · LinkedIn draftLinkedIn draft: Five onboarding emails that cut churn "We rewrote our first-week emails at Northwind and churn dropped. Here's what changed…" Approve and publish →

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.
  • Your own rules

    Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.

  • Any number of apps

    One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.

  • AI where it helps

    Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.

  • On a schedule or on each event

    Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

  • Act only on the items that match your own rules, and skip the rest
  • Change what the AI looks for, or how it writes the result
  • Add another app, for example also send it to Slack
  • Combine it with other Gmail and LinkedIn steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.
blog_rss_articles_shared_to_linkedin_after_email_review.pyexample
import base64, uuid
import feedparser
from email.message import EmailMessage
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_trigger, on_event, report_fetched, credentials, http, state, ai

FEED, ME, APPROVE_URL = "https://blog.example.com/feed", "me@example.com", "https://your-trigger-link"

@on_trigger
def check(event):
    seen = state.get("seen")
    entries = feedparser.parse(FEED).entries[:20]
    new = [e for e in entries if seen is not None and e.link not in seen]
    report_fetched(len(new))
    if seen is None:
        state.set("seen", [e.link for e in entries])
    if not new:
        return {"drafts": 0}
    gmail = build("gmail", "v1", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False)
    for e in new:
        text = ai.generate(f"Write a 100-word LinkedIn post promoting this article, ending with the link.\n{e.title}\n{e.get('summary', '')[:1500]}\n{e.link}",
                           max_output_tokens=300).text.strip()
        key = uuid.uuid4().hex
        state.set(f"draft:{key}", text)
        msg = EmailMessage()
        msg["To"], msg["Subject"] = ME, f"LinkedIn draft: {e.title}"
        msg.set_content(f"{text}\n\nApprove and publish: {APPROVE_URL}?draft={key}")
        gmail.users().messages().send(userId="me", body={"raw": base64.urlsafe_b64encode(msg.as_bytes()).decode()}).execute()
    state.set("seen", (seen + [e.link for e in new])[-300:])
    return {"drafts": len(new)}

@on_event
def approve(event):
    key = (event.json or {}).get("draft", "")
    text = state.get(f"draft:{key}")
    if not text:
        return {"published": False}
    headers = {"Authorization": "Bearer " + credentials.connection("linkedin", "main"), "LinkedIn-Version": "202405"}
    me = http.get("https://api.linkedin.com/v2/userinfo", headers=headers).json()["sub"]
    http.post("https://api.linkedin.com/rest/posts", headers=headers, json={
        "author": f"urn:li:person:{me}", "commentary": text, "visibility": "PUBLIC", "lifecycleState": "PUBLISHED",
        "distribution": {"feedDistribution": "MAIN_FEED", "targetEntities": [], "thirdPartyDistributionChannels": []}}).raise_for_status()
    state.delete(f"draft:{key}")
    return {"published": True}

FAQ

Common questions

Which feeds can it watch?
Any RSS or Atom feed, which most blogs and site builders publish automatically. You can list several, for example your blog and your podcast.
Will older articles be posted when I first turn it on?
No. The first run notes what is already in the feed and only drafts posts for articles published after that.
What if I don't approve a draft?
Nothing is posted. Drafts you ignore stay unpublished.
What permissions does it need?
gmail.send; w_member_social. Nothing else in your accounts is used.
Does it need AI?
Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.
How many runs does it use?
One run each time it checks. Checks that find nothing new and stop right away aren't counted.
Can I change how it works?
Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

Set up “Share new blog posts on LinkedIn after a quick review” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.