agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/linkedin-post-writer/SKILL.md

linkedin-post-writer

Skill13 starsChanged 22 days agoMITView on GitHub

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.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use linkedin-comment-drafter, linkedin-content-planner and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • sergebulaevSkill

    linkedin-comment-drafter

    Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via Publora on approval. Not for replying to existing comments (use linkedin-reply-handler).

    Also in 7 projects that use this

  • sergebulaevSkill

    linkedin-content-planner

    Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post (use linkedin-post-writer).

    Also in 7 projects that use this

  • +9 more from sergebulaev

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 7

    Distinctive

    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:

    Use this to turn an idea, a customer story or an opinion into a post the right buyers read and respond to.

    line 16
  2. Distinctive:

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

    line 36
  3. Distinctive:

    Use the author's words, sentence length and level of formality.

    line 48
  4. Distinctive:

    MUST keep stories and numbers true.

    line 58
  5. Distinctive:

    MUST match the author's voice and approve before posting.

    line 59
  6. Distinctive:

    NEVER name customers or share their results without approval.

    line 60
  7. Distinctive:

    NEVER engagement-bait ("comment YES to get the guide") unless the user explicitly chooses that tactic.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “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

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

FormatShapeBest for
StorySituation → tension → turn → lessonFounders, customer moments
Lesson listHook → 3-7 numbered lessons → takeawayExperience-based expertise
Contrarian takeCommon belief → why it's wrong → what worksStanding out in a crowded topic
How-toProblem → steps → resultPractical, saveable content
Data postSurprising number → what it means → what to doCredibility with analytical buyers
Behind the scenesWhat we tried → what happened → what we learnedTrust, transparency

Read 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."

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.

Check your setup, free