agentleFS
Sign inStart free
shyamw-cloudshyamw-cloud/Claude-skill/.claude/skills/write-linkedin-post/SKILL.md

write-linkedin-post

Skill0 starsChanged 7 months agoMITView on GitHub

Use when the user wants to draft a LinkedIn post — launch, lesson learned, hot take, or hiring announcement. Produces a feed-stoppable hook, a tight body, a real CTA, and 2 alternate hooks. Never posts; always returns a draft for approval.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. magnusrodseth/dotfiles★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user hasn't given any of these, ask before drafting (one consolidated question).

    line 24
  2. Distinctive:

    No emojis unless the user explicitly requests them.

    line 52
  3. Very specific:

    Never invent a number. Use [INSERT METRIC] if the user hasn't supplied one.

    line 56

≈ “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

write-linkedin-post

A LinkedIn post that performs has three properties:

  1. The first line stops the scroll before "see more" is clicked.
  2. The body tells a story the reader recognizes (or shows the work behind a result).
  3. The post earns its CTA — a real, specific ask, not "thoughts?".

Inputs to gather

Before drafting, confirm:

  • Topic — what is this post about in one sentence?
  • Voice — founder-operator, technical-builder, analyst-commentator, or community-host. Default founder-operator.
  • Goal — awareness, recruiting, demand-gen, recruiting feedback, community building?
  • CTA — what should a reader do? (Reply, click, DM, share their answer.) If no CTA, ask whether to skip it.
  • Numbers / specifics — any metric, timeline, or named example to anchor the post. If none, ask before inventing.

If the user hasn't given any of these, ask before drafting (one consolidated question).

Structure

<HOOK — ≤ 12 words, ends with a period.>

<context — 1 short sentence>

<the story / data / before-and-after — 3-6 single-sentence paragraphs>

<the takeaway — 1 line, in plain English>

<CTA — optional, single specific ask>

Total length: 80-180 words. White space is a feature.

Hooks that work (templates, not formulas)

  • Counterintuitive claim: "Hiring senior engineers slowed us down."
  • Specific number: "We replied to 412 cold emails this quarter. 11 became customers."
  • Before/after: "Two years ago I couldn't read a P&L. Last week I closed our seed round."
  • Confession: "I shipped a bug to production at 4pm on Friday. Here's what we changed."
  • Sharp observation: "Most 'AI strategies' I read are 90% AI and 0% strategy."

Hard rules

  • No emojis unless the user explicitly requests them.
  • Max 3 hashtags, lowercase, end of post.
  • No "agree?", "thoughts?", "what do you think?" as the closer.
  • No "I'm thrilled to announce" / "humbled and honored" / "incredibly excited."
  • Never invent a number. Use [INSERT METRIC] if the user hasn't supplied one.

Output format

## Draft (voice: <preset>)
<the post>

## Why this hook
<one line on the angle and why it should stop the scroll>

## Variants
1. <alternate first line — different angle>
2. <alternate first line — different angle>

## Posting checklist
- [ ] Numbers verified
- [ ] Tagged people consented
- [ ] Image / carousel attached (if applicable)
- [ ] Posted to personal vs company page (chosen)

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