jakeschincariol/linkedin-agent-skill

li-carousel

- Build a LinkedIn document post (carousel) - slide-by-slide copy, the cover that earns the swipe, and the PDF to upload.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/jakeschincariol/linkedin-agent-skill --skill li-carousel

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

li-carousel

Document posts are the highest-dwell format on LinkedIn, because a swipe is counted and a scroll is not. The format rewards one idea broken into steps. It punishes a text post cut into pieces.

When to use it instead of a text post

Use a carousel when the idea has sequence - steps, a countdown, a before/after progression, a framework with parts. Use a text post when the idea is one claim. Splitting one claim across eight slides is the most common way carousels fail, and if that is what the user has, say so and hand them to /li-post.

Structure

8-12 slides. Under 8 is a text post. Over 12 and the completion rate falls off a cliff.

1        COVER      the hook, 6 words or fewer, plus one line of promise
2        THE STAKE  why this matters, in one sentence
3-N      ONE IDEA PER SLIDE. A headline of 3-7 words, and at most 25 words
                    under it. If a slide needs a paragraph, it is two slides.
N+1      RECAP      the whole thing as a list, so the screenshot is useful
LAST     CTA        one action. Follow, comment a keyword, or the link. One.

Slide copy rules

  • Slide 1 is 80% of the result. Six words. Big. The rest of the deck

cannot save a cover nobody swipes.

  • Number every slide (3/10). Completion goes up when people can see the

end.

  • No slide is a paragraph. If you cannot say it in 25 words, split it.
  • The recap slide is the one people screenshot. Make it standalone.
  • The user's handle on every slide, small, bottom corner. Screenshots

travel without you.

Making the PDF

LinkedIn wants a PDF, 1080x1350 (4:5) for maximum feed real estate, under 100MB, under 300 pages. Build it as HTML and print to PDF:

bash
# one page per slide, 1080x1350, no margins
# then: Chrome headless --print-to-pdf, or any HTML-to-PDF you already use

Write the HTML with one <section> per slide, width:1080px; height:1350px; page-break-after:always, a single accent colour, and type no smaller than 28px - people read these on a phone at thumbnail size. If the user has a brand skill or design system in this project, use it and do not invent a palette.

Output

The slide-by-slide copy first, as a numbered list the user can read in ten seconds. Then the accompanying post text - a carousel still needs 2-3 lines above it, which is the actual hook in the feed. Run both through /li-human. Then build the PDF only if the user approves the copy.

Nothing is uploaded to LinkedIn. The user posts the PDF themselves.

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
jakeschincariol
コミュニティ

li-audit

- Post-mortem on what the user has already published - which posts actually worked, why, and what to stop doing. Use when the user pastes their LinkedIn analytics or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to double down on.

導入数
1
GitHub Stars
2393
更新日
9月17日
jakeschincariol
コミュニティ

li-comment

- Write comments on other people's LinkedIn posts that read as a person with an opinion, not a bot. Use when the user pastes a post and wants a comment, says "comment on this", "engage with this", "what do I say here", or wants a batch of comments for their engagement round.

導入数
1
GitHub Stars
2393
更新日
9月17日
jakeschincariol
コミュニティ

li-dm

- Write connection notes and DM follow-ups that get replies - the 200-character invite, the first message, and the two follow-ups. Use when the user says "write a connection request", "DM this person", "outreach message", "how do I follow up", or is reaching out to someone specific on LinkedIn.

導入数
1
GitHub Stars
2393
更新日
9月17日
jakeschincariol
コミュニティ

li-human

- Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out. Use whenever text needs to sound human, when the user says humanize, "does this sound like AI", "remove the em dashes", "de-slop this", "will this get flagged", or before any LinkedIn post, comment, reply or DM is shown to the user.

導入数
1
GitHub Stars
2393
更新日
9月17日