agentleFS
matteotittamatteotitta/claude-marketing-linkedin/skills/linkedin-personal-posts/SKILL.md

linkedin-personal-posts

Skill0 starsChanged 31 days agoMITView on GitHub

Writes personal LinkedIn posts in the author''s own voice: full story posts built from real experiences, plus short formats (behind the work, a quick thought, a life-outside-work post). Each story maps to one buyer pain so it builds trust with the right audience. Never invents stories or numbers. Triggers: "personal post", "story post", "founder story", "credibility post", "personal LinkedIn series", "behind the scenes post". Not for educational or framework posts (use linkedin-expert-posts).

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write personal posts from the author's real experiences.

    line 10
  2. Very specific:

    Not for frameworks, how-tos or opinion pieces (/linkedin-expert-posts) or for comments (/linkedin-comment).

    line 18
  3. Distinctive:

    If the voice file is missing, ask for 3 posts or messages the author wrote, and match those.

    line 33
  4. Distinctive:

    Collect seeds: Read the story seeds, ICP and voice.

    line 57
  5. Very specific:

    Write the hook: Use a hook from /linkedin-hooks or write one that opens on the shared pain.

    line 59
  6. Distinctive:

    Every detail happened and came from the user.

    line 78

≈ “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 personal posts

Write personal posts from the author's real experiences. Personal stories earn the longest reads and the most trust on LinkedIn because they are hard to fake. That is also why every detail must be true.

When to use it

  • A series of 3 to 5 story posts that build credibility with the buyer.
  • A single story post for the week's plan.
  • Short posts: something mid-build, a quick thought after a call, a post about life outside work.

Not for frameworks, how-tos or opinion pieces (/linkedin-expert-posts) or for comments (/linkedin-comment).

Inputs

InputRequired?Where it comes from
Real story seedsRequiredThe user: turning points, failures, a client moment, a lesson
Buyer pains and goalsRequiredcontext/icp/
VoiceRequiredthe tone-of-voice file in context/brand/
The offerRecommendedcontext/positioning/
Proof (real numbers, outcomes)RecommendedThe user or context/win-loss/
A hookOptionalFrom /linkedin-hooks

If there are no story seeds, ask for them with questions like: "When did you last change your mind about how to do this work?", "What did a client say that stuck with you?", "What did you get wrong early on?" Do not make stories up.

If the voice file is missing, ask for 3 posts or messages the author wrote, and match those. Say what was missing in the output.

Agency users: swap context/ for clients/<client>/context/.

The story structure

  1. The shared pain. Open with a struggle the reader also has, in their words, with a real detail.
  2. A break. One to three short lines that shift the energy or set up a turn.
  3. What happened. What it cost to leave the problem alone, what was hard, and what the author did. This is where credibility comes from.
  4. The better place. What changed, described as the outcome the reader wants.
  5. The ending. Why the author does this work, or what it means for the reader. Close on a thought, not a neat moral.

Short formats

FormatWhat it isRules
Behind the workA screenshot or photo of work in progress with 1 to 2 lines of contextNo big hook needed. Remove client names unless they agreed
Quick thought2 to 6 lines after a call or something seen this weekStays on the author's topics. No politics, drama or hot takes on news
Life outside workA photo and 1 to 5 lines that add an observationPick themes that make the right buyer more likely to want to work with the author

Short formats get no call to action.

Steps

  1. Collect seeds. Read the story seeds, ICP and voice. Produces: a list of stories, each with the real details the user gave.
  2. Map each story to one buyer pain. Produces: a table of story, pain, and the outcome the reader wants.
  3. Write the hook. Use a hook from /linkedin-hooks or write one that opens on the shared pain. Produces: the first two lines.
  4. Draft the post in the structure above, in the author's voice. Open on "I" where it reads naturally. Produces: the draft.
  5. Scan for AI tells (table below) and rewrite any hits. Produces: the clean draft.
  6. Trim 15 to 20 percent. Produces: the final post, with a note on any [detail needed] placeholders.

AI tells to remove

PatternFix
"It's not X. It's Y."State the point directly
A neat moral at the endEnd mid-thought or on an open question to yourself
"Here's the thing:"Cut it
Same-length paragraphsMix one-line beats with longer passages
"Looking back, I realise..."Stay in the moment
"I failed... then I crushed it"Stay in the failure longer
"Just start. Take the leap."Say exactly what you did

What good looks like

  • Every detail happened and came from the user.
  • A buyer in the ICP sees their own situation in the first lines.
  • It sounds like the author talking, not like a newsletter.
  • One story per post, one point per story.

Mistakes to avoid

  • Inventing or blending stories into a composite.
  • Adding emotional details (family, health, money) the author did not share.
  • Inventing numbers to make a story land. Use [your number here].
  • Ending every post with a lesson in bold.
  • "Link in the comments". Put a link in the post if it is needed at all.

Output

Save to outputs/social/linkedin/MMYY-personal-posts.md: each post ready to paste, with the pain it maps to, the hook type, a suggested image if any, and a list of placeholders the user must fill before posting.

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.