agentleFS
Sign inStart free
Vishwajeetkumbhar379Vishwajeetkumbhar379/claude-skills/skills/linkedin-carousel/SKILL.md

linkedin-carousel

Skill0 starsChanged 41 days agoMITView on GitHub

Plan and produce a high-signal LinkedIn carousel in one locked visual style, rendered to PNG slides and a PDF. Use when asked for a LinkedIn post, carousel, or content ideas on AI, marketing, creators or growth.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    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:

    If no topic is given, offer 5 options across: AI tools for marketers, creator-marketing truths, career and growth, brand strategy, and one …

    line 11
  2. Very specific:

    Run the application-humanizer tells list on all copy: no not-X-but-Y, no dramatic one-liners, no stock AI words.

    line 23
  3. Very specific:

    Write the deck JSON and run carousel render deck.json.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 4 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

LinkedIn carousel

Rendering is handled by linkedin-carousel-studio. This skill covers the thinking: topic, structure, words.

1 · Topic

If no topic is given, offer 5 options across: AI tools for marketers, creator-marketing truths, career and growth, brand strategy, and one opinion. Prefer rare, high-signal knowledge from the person's own experience over generic advice. Check topic-history.md to avoid repeats.

2 · Structure (6-9 slides)

  1. Cover: a hook under 10 words with one accent word.
  2. Setup: why it matters, two or three lines.
  3. One idea per slide: a label, a title and at most 45 words.
  4. Optionally a compare slide (red flag vs fair, before vs after) or a stat slide using a real number.
  5. CTA: save and follow.

3 · Words

  • Real numbers only, from the person's notes. Never invent statistics.
  • Small emojis as visual anchors, used sparingly (two per deck at most).
  • Run the application-humanizer tells list on all copy: no not-X-but-Y, no dramatic one-liners, no stock AI words.

4 · Caption

A punchy first line, a short arrow list (→), a save CTA and one open question.

5 · Render

Write the deck JSON and run carousel render deck.json. The renderer enforces the style rules and fails loudly if a deck breaks them. Upload the PDF to LinkedIn as a document post.

Visual system (locked)

Light Claude-style UI · tinted cards (purple #F5F4FF, teal #F0FBF6, coral #FEF6F3) · accent #7F77DD · 0.5px borders · badge labels · pill counter · name and handle top-left · 1080×1350.

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