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.