Skip to content

Weekly founder post drafter

Picks a fresh topic each week, writes one LinkedIn post in your voice, and files it as a review task. It never publishes, schedules or sends messages.

MarketingWorks with Claude Code · OpenAI Agents SDK+1Community example
Build your promptSee requirements

What it does

  • Reads past drafts so it does not repeat a topic
  • Pulls public discussion on the topic as optional source material
  • Drafts one post in your voice with source and claim risk notes
  • Flags risky wording like made up client results or savings numbers
  • Creates a review task with the draft

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Publishing or scheduling the post

You decide what happens next.

More about this workflow

This setup is for marketers and solo creators who need steady output without losing their voice. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it reads past drafts so it does not repeat a topic. Next, it pulls public discussion on the topic as optional source material. Then it drafts one post in your voice with source and claim risk notes. After that, it flags risky wording like made up client results or savings numbers. Finally, it creates a review task with the draft. It works with your task tracker, web search and social APIs, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before publishing or scheduling the post, and says plainly if a step cannot be undone.

“The system creates a ClickUp review task.”
kigansolutions kigansolutions on GitHub · Jul 16, 2026
Before you startTask tracker · Web search accessScoped permissionsClaude Code or OpenAI Agents SDK
Explore required tools and model recommendations

Tools and access

  • Linear

    Handles the task tracker part of this job. Grant read plus create in one triage team.

    API required: Yes. Needs a personal API key or an OAuth app.

    Sign up: Linear

  • Web search

    Handles the web search part of this job. Grant public search results only.

    API required: Optional. Built into most agent harnesses. A standalone search API needs its own key.

    No sign-up needed

  • Social APIs

    Handles the social apis part of this job. Grant read-only scopes for comments and mentions.

    API required: Yes. Each network needs its own developer app and keys to read comments and mentions.

    No sign-up needed

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

GPT-6.1 Sol

Strong general writer at a mid price.

$2 per million input tokens, $10 per million output tokens, for prompts up to 272K tokens. Longer prompts cost $4 in and $15 out.

OpenAI docs as of October 11, 2026

Cheaper backup

GPT-6 Luna

Very low cost for first drafts and digests.

$0.10 per million input tokens, $0.50 per million output tokens, for prompts up to 272K tokens.

OpenAI docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

e.g. client results

2Your prompt

4 of 4 still empty
Fill these in before you run it: [YOUR VOICE NOTES] [TOPICS YOU CAN SPEAK TO] [CLAIMS TO NEVER MAKE: e.g. client results] [YOUR REVIEW LIST] You are the Weekly founder post drafter agent. Picks a fresh topic each week, writes one LinkedIn post in your voice, and files it as a review task. It never publishes, schedules or sends messages. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Reads past drafts so it does not repeat a topic - Pulls public discussion on the topic as optional source material - Drafts one post in your voice with source and claim risk notes - Flags risky wording like made up client results or savings numbers - Creates a review task with the draft What you must never do without a yes from a person: - Publishing or scheduling the post Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code, OpenAI Agents SDK, n8n

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Linear with its own login, not yours. Grant read plus create in one triage team.
  2. 2Set up Web search. Keep it to public search results only.
  3. 3Set up Social APIs. Keep it to read-only scopes for comments and mentions.
  4. 4Paste the prompt where your harness takes instructions. See the note under the Copy button.
  5. 5Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  6. 6Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval27 / 30

Waits for a yes on: publishing or scheduling the post.

Undo and logs17 / 20

Leaves drafts you can throw away, with a record of what it made.

Scope16 / 20

Runs on its own login across 3 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Human approval: Add a second named stop next to "publishing or scheduling the post", so every step that leaves your hands waits for a yes, and have the confirm say plainly what cannot be undone +3
  • Scope: Cut it down from 3 connected tools to the 2 it needs most, each with its own limited login instead of your full account +2

Do all of these to reach 89, up from 78.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Weekly founder post drafter](https://trustcase.dev/badge/weekly-founder-post-drafter.svg)](https://trustcase.dev/use-cases/weekly-founder-post-drafter)
HTML
<a href="https://trustcase.dev/use-cases/weekly-founder-post-drafter"><img src="https://trustcase.dev/badge/weekly-founder-post-drafter.svg" alt="Trustcase trust score for Weekly founder post drafter" height="20"></a>

More marketing workflows

  • Daily losing ad cutter

    Checks yesterday's ad results every day and lists the ads that cost too much. You approve which ones to turn off and which winners get more budget.

  • Weekly marketing report digest

    Reads the week's marketing reports, decks and meeting notes, and tells you what actually changed. It keeps a log so slow trends stand out.

  • New page internal link suggester

    Once a week it finds the pages you published and suggests where your older pages should link to them. You approve the links before they go live.

  • One idea to a full post package

    Turns rough notes or a draft into a folder of ready to review posts, a blog draft and images for each platform. Nothing is published for you.