<!-- LinkedIn post writer | install: npx skills add prosyo-ai/gtm-skill --skill linkedin-post-writer | source: https://github.com/prosyo-ai/gtm-skill/tree/main/skills/linkedin-post-writer -->

---
name: linkedin-post-writer
description: "Use this skill when you need LinkedIn posts that build pipeline, not just likes: \"write a LinkedIn post\", \"turn this idea into a post\", \"ghostwrite posts for our founder\", \"plan a week of LinkedIn content\". Picks a post format (story, lesson, contrarian take, how-to, data, behind the scenes), writes a hook that earns the click on see more, keeps the body skimmable, ends with a conversation-starting question, and matches the author's voice. Includes a content plan that ties posts to the buyer's problems."
license: MIT
metadata:
  title: LinkedIn post writer
  category: linkedin
  tags: "Founders, Marketing, Sales, Agencies"
  author: prosyo
  version: "1.0.0"
  keywords: "linkedin post writer, linkedin post ideas for b2b, ghostwriting linkedin posts, claude linkedin post skill, linkedin hook examples"
  inputs: "Idea, story or data point, Author voice samples, Target buyer"
  outputs: "Post drafts in two or three formats, Hooks, Content plan"
---

Use this to turn an idea, a customer story or an opinion into a post the right buyers read and respond to. Posts that build pipeline teach buyers something about their own problem; posts that only build reach entertain peers.

## Inputs

- The idea, story, lesson or data point.
- Two or three past posts or messages by the author, for voice.
- The target buyer and the problem space.

## The play

### 1. Pick a format
| Format | Shape | Best for |
| --- | --- | --- |
| Story | Situation → tension → turn → lesson | Founders, customer moments |
| Lesson list | Hook → 3-7 numbered lessons → takeaway | Experience-based expertise |
| Contrarian take | Common belief → why it's wrong → what works | Standing out in a crowded topic |
| How-to | Problem → steps → result | Practical, saveable content |
| Data post | Surprising number → what it means → what to do | Credibility with analytical buyers |
| Behind the scenes | What we tried → what happened → what we learned | Trust, transparency |

Read [references/post-formats.md](references/post-formats.md) for a template and an example of each.

### 2. Write the hook
The first two lines decide whether anyone clicks "see more". Hooks that work: a specific number, a counter-intuitive claim, a vivid moment, or the reader's exact problem. Avoid questions as the very first line and avoid "I'm excited to announce".

### 3. Make the body skimmable
One idea per line or short paragraph. White space. No more than 1,300 characters for most posts; long only when the story earns it. No external links in the post body; put them in a comment if needed.

### 4. End with a conversation
A specific question invites comments from buyers: "How long does month-end take your team?" beats "Thoughts?".

### 5. Match the voice
Use the author's words, sentence length and level of formality. A founder who writes plainly should not suddenly sound like a motivational speaker.

## What good looks like

- A buyer would save it or send it to a colleague.
- The hook is specific; the lesson is earned by the story.
- The common mistake is broetry: one-line dramatic sentences, a fake story, and a lesson nobody needed. Readers spot it and so does the algorithm's audience.

## Rules

- MUST keep stories and numbers true; ask the author for details rather than invent them.
- MUST match the author's voice and approve before posting.
- NEVER name customers or share their results without approval.
- NEVER engagement-bait ("comment YES to get the guide") unless the user explicitly chooses that tactic.

## Example prompts

- "Turn this customer story into a LinkedIn post for our founder."
- "Write a contrarian post about why more SDRs doesn't mean more pipeline."
- "Plan 8 posts for the next month aimed at heads of RevOps."


---

<!-- references/post-formats.md -->

# Post formats with examples

## Story

```
Hook: the moment, specific and vivid
Tension: what was at stake
Turn: what changed
Lesson: one sentence the reader can use
Question: invite their version
```

> Our best customer almost churned in month two.
>
> Their ops lead, Priya, emailed: "We're spending more time on this than on the old spreadsheet."
>
> We had built a beautiful onboarding. She needed one thing: her existing shift codes imported.
>
> We did it by hand that afternoon. She renewed for three years.
>
> Lesson: the fastest onboarding is the one that starts from the customer's mess, not your template.
>
> What's the one thing that made you stick with a tool?

## Lesson list

> I've reviewed 400 cold emails this year. The ones that got replies had five things in common:
>
> 1. Under 90 words
> 2. One problem, not three
> 3. A named peer, not "leading companies"
> 4. No links in the first email
> 5. An ask you can answer with one word
>
> The ones that failed usually started with "I hope this finds you well".
>
> Which of these do you break most often?

## Contrarian take

> Hiring more SDRs won't fix your pipeline.
>
> Most teams that double SDR headcount see meetings per rep drop by a third. Same list, more people fishing in it.
>
> The fix is upstream: better accounts, better timing, better first lines.
>
> Before you open four reqs, check how many accounts in your ICP haven't been touched this quarter.
>
> Agree or disagree?

## How-to

Hook with the result, then numbered steps, then the outcome and a question.

## Data post

> 62% of the "no replies" in our last campaign were never delivered to the inbox.
>
> The copy wasn't the problem. The domain was.
>
> Here's the 10-minute check we now run before every campaign: ...

## Behind the scenes

What we tried, the numbers, what surprised us, what we'd do differently. Honest numbers, including the bad ones, build the most trust.

## Weekly plan template

| Day | Format | Topic tied to buyer problem |
| --- | --- | --- |
| Tue | Lesson list or how-to | A practical fix |
| Thu | Story or contrarian take | A belief to challenge |
| Optional | Data or behind the scenes | Proof and credibility |
