agentleFS
HemanthMChakravarthyHemanthMChakravarthy/linkedin-agent-skills/skills/li-carousel/SKILL.md

li-carousel

Skill2 starsChanged 43 days agoMITView on GitHub

Write a LinkedIn document post (carousel) slide by slide: the cover that earns the swipe and the copy for every slide. Use when the user wants a carousel, a slide deck post, "turn this into slides", or a document post. Produces slide copy and a build-ready outline; the user assembles and uploads the PDF themselves.

7 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, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    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:

    Document posts earn the swipe and the dwell time.

    line 13
  2. Distinctive:

    Every slide's headline must work as a standalone tweet.

    line 46
  3. Distinctive:

    No walls of text: if a slide needs a paragraph, it needs to be two slides.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 7 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

li-carousel

Document posts earn the swipe and the dwell time. This skill writes the slide-by-slide copy and the cover that earns the first tap. The user builds the PDF in their own design tool and uploads it. This skill produces words, not files.

Before you write

  1. Load the voice profile (li-voice if missing).
  2. Get the raw material: the idea, the framework, the list, the before/after. A carousel needs a spine: one promise the slides deliver in order. If the user has five unrelated points, that is five posts or one carousel with a real spine. Find the spine first.
  3. Decide the length: 7-10 slides is the working range. Under 5 is a post; over 12 is a webinar.

The structure

Slide 1  COVER: the promise, 8 words or fewer. Must survive at thumbnail size.
         Subtitle line optional, 12 words max. No "swipe to learn".
Slide 2  The problem, stated the way the reader would say it.
Slides 3-N  One idea per slide. Headline + 2-4 short lines. Each slide must
         make sense if it is the only one screenshotted.
Slide N  The turn: what changes now that the reader knows this.
Slide N+1  CTA: one action. Follow, comment with a word, DM a keyword.
         Never two.

Slide copy rules

  • Headlines under 10 words. Body lines under 15 words each.
  • Numbers on slides, adjectives in posts. "Cut reporting time 73%" belongs on a slide.
  • Every slide's headline must work as a standalone tweet. Test each one.
  • No walls of text: if a slide needs a paragraph, it needs to be two slides.
  • The cover gets three options, not one. Covers are the whole game.

The loop

1. Spine check. State the one promise in one sentence. Get a yes before writing slides.

2. Three covers. Numbered, with a one-line note on which you would ship.

3. All slides. Slide number, headline, body lines, in order.

4. Humanize. Invoke the li-human skill on all slide copy. Carousel copy read as AI is worse than no carousel; the format already signals effort.

5. The handoff block.

CAROUSEL READY
slides:     9 (cover + 7 content + CTA)
cover pick: #2
humanizer:  3 artefacts stripped, human score 82 PASS
post text:  [the 2-3 line caption for the post itself, written by li-post rules]

Build the PDF in your design tool, upload as a document post, paste the caption.

6. Never upload. The user assembles and publishes. On "yes", log to ~/.agents/linkedin/log.md.

Caption

The post caption is 2-4 lines: the promise, who it is for, one question. The carousel is the content; the caption is the invitation. Write it to li-post standards but keep it short.

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.