Skip to content
SkillModel-led661 tokens in use

li-carousel

Builds a LinkedIn document post: slide-by-slide copy, a cover that earns the swipe, a caption, and an optional PDF ready to upload.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-carousel
/plugin marketplace add Jakeschincariol/linkedin-agent-skill /plugin install linkedin-agent
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing li-carousel costs

68tokens idle
661tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure11/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity28
  • Maintenance4
  • Community52
  • Maturity16
  • Momentum40

li-carousel turns an idea that has a sequence into a LinkedIn carousel. It lays out 8 to 12 slides: a cover of six words or fewer, a stake slide, one idea per slide, a recap slide and a single call to action.

It writes the short post text that sits above the document, runs the copy through the humanizer skill, and builds the PDF as HTML printed to 1080x1350 pages only after you approve the copy. If your idea is one claim, it tells you to write a text post.

What You Get

  • Slide-by-slide copy for 8 to 12 slides with headlines of 3 to 7 words and at most 25 words per slide
  • A cover line of six words or fewer with one line of promise
  • The 2 to 3 line post text that sits above the document
  • An optional PDF at 1080x1350 built from HTML, made after you approve the copy

Common Use Cases

  • Turning a five-step framework into a swipeable document post
  • Making a before and after progression into slides
  • Checking whether a list-shaped idea would work better as a text post
  • Producing a PDF with your handle on every slide for upload

What Makes It Unique

It starts by testing whether the idea has sequence, and sends single-claim ideas to the text-post skill. It gives hard structure rules: numbered slides, a cover that carries most of the result, a standalone recap and your handle on each slide. The PDF step is gated on your approval of the copy.

Under The Hood

The skill is instructions plus a described build step. Once you approve the copy, it has the agent write an HTML file with one section per slide and print it to PDF with headless Chrome or another HTML-to-PDF tool you already use, so it can write files and run a command on your machine. It calls the humanizer skill on the copy. It does not fetch web pages, call APIs or upload anything to LinkedIn.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers