agentleFS
zrosenfieldzrosenfield/sharepoint-ai-skills/Skills/linkedin-post-writing/SKILL.md

linkedin-post-writing

Skill96 starsChanged 3 months agoMITView on GitHub

Crafts high-performing LinkedIn posts from any topic, story, announcement, or idea. Use this skill when a user needs to write, draft, improve, or optimize a LinkedIn post — including personal stories, product announcements, thought leadership, professional milestones, or content repurposing. Triggers include requests to "write a LinkedIn post about", "help me announce this on LinkedIn", "make this sound better for LinkedIn", or when a user provides a transcript, article, achievement, or idea they want to share professionally.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every strong LinkedIn post follows this arc:

    line 22
  2. Distinctive:

    If the user has not provided a clear angle or audience, ask before writing.

    line 92
  3. Distinctive:

    Before finalizing any post, verify:

    line 98
  4. Distinctive:

    No paragraph runs longer than two sentences

    line 101
  5. Distinctive:

    If there is an external link, it appears at the very end or is moved to the first comment

    line 105

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LinkedIn Post Writing Guide

This skill transforms any topic, story, or announcement into a compelling LinkedIn post that earns engagement. The goal is always a post that stops the scroll, delivers real value, and invites a response.


What Makes a LinkedIn Post Perform

LinkedIn truncates posts after roughly 140 characters — everything after that is hidden behind a "see more" link. This makes the opening line the single most important element. Readers decide in under two seconds whether to keep reading.

Beyond the hook, high-performing posts share three traits: they are easy to scan, they offer a clear point of view, and they end with a reason to respond.


The Five-Part Structure

Every strong LinkedIn post follows this arc:

1. Hook — The opening line that earns the click. Make it specific, surprising, or immediately relevant. Never bury the lead with context-setting. The best hooks make a bold claim, ask a provocative question, or open a story mid-action.

2. Context — One or two sentences that explain why this matters. Set up the problem, tension, or opportunity. Keep it brief — readers want the payoff, not the backstory.

3. Core value — The insight, lesson, announcement, or story. This is the substance. Use short paragraphs (one to two sentences each) with a blank line between them. Bullet points work well for lists of three or more items.

4. Implication — Why should the reader care? Zoom out to the broader lesson, trend, or takeaway. This is what makes the post shareable beyond your immediate network.

5. Call to action — Close with a question, invitation, or next step. Posts that end with a direct question get 20–40% higher engagement. Options include: asking for the reader's experience, directing them to a link, or prompting them to share the post with someone who needs it.


Hook Formulas

Choose the hook type that fits the content:

The result first — Lead with the outcome, then explain how you got there. ("We tripled response rates. Here's what changed.")

The counterintuitive claim — State something that challenges a common assumption. ("Most onboarding checklists make new hires worse at their job.")

The specific story — Drop the reader into a scene. Use a number, a name, or a concrete detail. ("Last Tuesday, a five-minute conversation saved us three months of rework.")

The direct question — Ask something your audience is already wondering. ("Why do so many good ideas die in the first meeting?")

The bold announcement — State the news clearly and immediately. ("We just launched [X]. Here's what it does and why it matters.")


Format Rules

Length — 150 to 300 words is the sweet spot for most posts. Text-only posts in the 1,300–1,800 character range tend to see peak reach. Going under 1,000 characters can lose up to 25% of potential engagement.

Paragraphs — Maximum two sentences per paragraph. Always add a blank line between paragraphs. Dense text blocks lose readers immediately.

Bullets — Use them for lists of three or more. Do not use bullets for single items or as a substitute for proper sentences.

Emojis — Use sparingly (one to three per post maximum) and only where they add meaning or visual separation. Never use them as decoration.

Hashtags — Three to five relevant hashtags at the end of the post. Do not embed hashtags in the body text.

Links — LinkedIn's algorithm deprioritizes posts with external links in the body. Either place the link in the first comment and reference it in the post ("link in comments"), or include it at the end after all substantive content.


Content Types and When to Use Each

Personal story — Best for building trust and relatability. Leads with a specific moment, challenge, or realization. The most shareable format when the story has a transferable lesson.

Announcement — Best for launches, milestones, or news. State the news in the first sentence, then explain what it means and why it matters. End with a clear next step.

Thought leadership — Best for establishing expertise. Takes a clear position on a topic, backs it up with evidence or experience, and invites disagreement. Avoid hedging — a strong opinion performs better than a balanced both-sides take.

How-to or list — Best for educational content. Use a numbered list or bullets. Front-load the most valuable item, not the most obvious one.

Repurposed content — Best for extending the reach of existing work (an article, talk, or project). Extract the single most interesting insight and build the post around that, rather than summarizing the whole piece.


Inputs to Gather

Before writing, identify:

  • The core message — In one sentence, what is this post saying?
  • The audience — Who is this for? What do they already know, and what do they care about?
  • The goal — Awareness, engagement, driving traffic, building credibility, or recruiting?
  • The angle — Is this a story, an opinion, a lesson, or an announcement?
  • Any supporting material — Transcripts, articles, data, or talking points to draw from

If the user has not provided a clear angle or audience, ask before writing. A post written for the wrong audience or with the wrong angle will need to be scrapped, not revised.


Optimization Checklist

Before finalizing any post, verify:

  • The first line works as a standalone hook — would it make someone pause while scrolling?
  • No paragraph runs longer than two sentences
  • The post has a single, clear point of view — it is not trying to say three things at once
  • The call to action is specific, not generic ("What's your experience with this?" is better than "Let me know what you think")
  • Hashtags are at the end and limited to three to five
  • If there is an external link, it appears at the very end or is moved to the first comment
  • The post reads naturally out loud — if it sounds stiff, it will read stiff

Output Format

For every post, deliver:

  1. Draft post — Ready to copy and paste, formatted with proper line breaks
  2. Hook alternatives — Two or three opening line variations for the user to choose from
  3. One-line rationale — Why this structure and angle was chosen for this content
  4. Optional: A suggested hashtag set and a note on where to place any links

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.