Linkedin Post Writer logo

Linkedin Post Writer

Community
aakashg
linkedin-post-writer

Use when the user asks to write, draft, or rewrite a LinkedIn post, turn notes or an article into a LinkedIn post, or fix a hook that is not landing. Do NOT use for X/Twitter threads, newsletters, or blog posts — those need different length and hook rules.

Overview

Publisheraakashg
Repositorypm-claude-skills
Skill namelinkedin-post-writer
Stars
116
Forks
35
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aakashg on GitHub. Read the source before you install it.

Installation

Install the Linkedin Post Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aakashg/pm-claude-skills/tree/main/skills/linkedin-post-writer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aakashg/pm-claude-skills.git /tmp/pm-claude-skills
mkdir -p .claude/skills
cp -r /tmp/pm-claude-skills/skills/linkedin-post-writer .claude/skills/linkedin-post-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linkedin Post Writer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Linkedin Post Writer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Linkedin Post Writer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

LinkedIn Post Writer

Turn a rough idea into one publishable LinkedIn post: one hook, one format, one CTA.

Step 0 — Read first

Read these before writing a single line. Do not write from memory of "how LinkedIn posts go."

SourcePathWhat to extract
Project contextCLAUDE.mdWho the user is, their product, banned words, audience
Post patternsreferences/post-patterns.md5 full worked posts + why each works
User's raw inputwhatever they pastedThe one insight, the specific numbers, the personal detail
Prior postsany file/link the user namesTheir actual voice — match it, do not invent one

If references/post-patterns.md is missing, say so and proceed with the worked example below only.

Constraints

These are mandatory. Violating any one means the draft is not done.

  • Hook is ONE line. Two-line hooks lose reach. No exceptions.
  • Total body 800–1,300 characters. Under 800 reads thin; over 1,300 truncates in feed.
  • Exactly ONE call to action. Not two, not "and follow me."
  • Zero or one emoji. Zero is the default.
  • No paragraph longer than 3 lines.
  • The post must contain at least one specific number, name, or timeframe.
  • Never use: delve, landscape, synergy, leverage, robust, streamline, cutting-edge.
  • Never open with "I'm excited to announce" or "Thrilled to share."
  • No hashtags in the body. If requested, 3–5 after a line break at the end.
  • Lead with the insight, never the product. Product appears in context or not at all.

Existence check

Before drafting, verify three things:

  1. The insight — one sentence the reader did not already know.
  2. The evidence — a number, a named result, a specific story the user actually lived.
  3. The audience — a specific person or role, not "professionals."

If two of three are missing, do not draft. Say which are missing and ask for exactly those. A post with no insight and no evidence is engagement bait, and publishing it costs the user credibility.

Step 1 — Gather

Ask, in one message:

  1. What is the one insight or takeaway?
  2. Who is the target reader?
  3. Any hook or angle you want?
  4. Format preference — listicle, story, hot take, before/after, framework, observation — or should I pick?

If the user pasted raw notes, a thread, or an article, extract the insight yourself and confirm it in one line. Never ask the user to organize their notes first.

Step 2 — Pick the format

FormatBest forOptimizes for
ListicleTips, lessons, frameworksSaves
Story arcPersonal turning pointsComments
Hot takeChallenging conventional wisdomShares
Before/afterTransformations, resultsSaves
FrameworkTeaching a conceptSaves
ObservationIndustry trendsSpeed

Output template

Produce exactly this, in this order. No preamble, no "here's your post!"

[HOOK — one line, no context needed to understand it]
[RE-HOOK — one line: adds heft, creates contrast, or preempts the objection]

[BODY — 8–16 lines. Chosen format. 1-3 line paragraphs, alternating single
lines with short clusters. At least one signpost line showing how the author
knows this. Specific numbers throughout.]

[CLOSER — the reusable line. The part someone screenshots.]

[CTA — one question, low friction, easy to answer. "P.S." form works well.]

Then, below the post, output:

  • Character count: [number]
  • Format used: [name]
  • Hook alternatives: two more one-line hooks the user can swap in.

Example

Input: "I want to write about how I only got clients once I stopped posting about myself. Got my first 10 clients in 2024 with under 1,000 followers."

Output:

How to get your first 10 clients on LinkedIn:
(even if you have less than 1,000 followers)

Most people overcomplicate this.

They build funnels, run ads, and buy courses.

But the people I've watched go from 0 to 6 figures did 4 things:

1. Picked ONE problem they solve
→ Not 5. Not "I help businesses grow." One specific pain.

2. Posted 3x/week about that problem
→ Not about themselves. About the reader's pain.

3. Commented on 20 posts a day from their ideal clients
→ Not "Great post!" — they added a missing insight or tip #8.

4. Ended every conversation with "How can I help?"
→ Not "Buy my thing." Just helped. For free. Consistently.

That's it. No funnel. No ads. No viral post needed.

The boring stuff works. Most people just won't do it long enough.

P.S. What's the one thing that got YOU your first client?

Character count: 1,043 Format used: Listicle Why this works: the parenthetical re-hook removes the reader's excuse before they raise it. Each point carries a DO and a DON'T, which forces specificity. The P.S. is low friction.

Four more worked posts — story arc, framework, contrarian, observation — are in references/post-patterns.md. Read them before choosing a format.

Shortcuts Claude takes

What Claude might thinkWhy it's wrong
"The hook works, the checklist is a formality"The checklist catches character count and double-CTA every time. Run it.
"Two lines make a stronger hook"Two-line hooks measurably lose reach. Cut to one.
"I'll add a second CTA so they can also follow"Two CTAs halve the response rate on both.
"The user has no numbers, I'll write it generically"A post with no specifics is indistinguishable from every other post. Ask for the number.
"This is a product launch, so lead with the product"Product-first posts get scrolled. Insight first, always.
"I'll show the draft, then run the checklist"Run it silently first and fix the issues. Show only the clean version.

Exit checklist

Run this silently. Fix every failure, then present the clean draft. Not complete until every box is checked. Any placeholder left in the draft — [name], [number], [company] — is an automatic unchecked box.

  • Hook is one line and works with zero context
  • Re-hook adds contrast, heft, or handles an objection
  • Body is 800–1,300 characters
  • At least one specific number, name, or timeframe appears
  • A signpost line establishes why the author knows this
  • No paragraph exceeds 3 lines
  • Exactly one CTA, phrased as an easy question
  • Zero or one emoji
  • No banned words
  • Read aloud: sounds like a coffee chat, not a keynote
  • Remove any sentence starting with "I'm excited to," "I believe that," "It's important to"
  • No placeholders remain
  • Two alternative hooks are included below the post

Next

  • If the user liked the post and wants more from the same insight → offer to spin it into a 3-post sequence.
  • If the insight turns out to be about a product idea they have not validated → recommend /idea-validator before they post a claim they cannot back.
  • If they want to reuse this post as a prompt for future drafts → recommend /prompt-engineer.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Linkedin Post Writer AI skill do?

Use when the user asks to write, draft, or rewrite a LinkedIn post, turn notes or an article into a LinkedIn post, or fix a hook that is not landing. Do NOT use for X/Twitter threads, newsletters, or blog posts — those need different length and hook rules.

Why use Linkedin Post Writer on TypingMind?

Because you install it once and use it with any model. Linkedin Post Writer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Linkedin Post Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aakashg/pm-claude-skills/tree/main/skills/linkedin-post-writer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Linkedin Post Writer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Linkedin Post Writer?

As many as you like. As long as a model supports skills, you can use Linkedin Post Writer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Linkedin Post Writer AI skill free?

Yes. It is published on GitHub by aakashg under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇