linkedin-repurposer Checked

Name: linkedin-repurposer
Author: sergebulaev

Repurpose existing content into a native LinkedIn post. Take a tweet, thread, YouTube video, blog…

✍️ Writing skills By sergebulaev Version v1.0.0 Updated 2026-09-15

9.1Overall rating

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "linkedin-repurposer" skill by following the instructions at https://skill123.me/install/linkedin-repurposer.

⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/linkedin-repurposer.sh | bash

📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 3 KB

About this skill

Overview

Repurpose existing content into a native LinkedIn post. Take a tweet, thread, YouTube video, blog, or newsletter and rebuild it for LinkedIn: re-hook before the fold, expand to the 900 to 1300 char sweet spot, add whitespace and a CTA, move links to the first comment, run the humanizer, publish via Publora on approval. Not for writing from scratch (use linkedin-post-writer), not for auditing a draft (use linkedin-humanizer --mode audit).

Source

Repo: https://github.com/sergebulaev/linkedin-skills
Path: skills/linkedin-repurposer

Score breakdown

Trigger

9.5

Clear transform purpose with two explicit Not-For routings (post-writer, humanizer audit).

Structure

8.7

Single 75-line SKILL.md, appropriately minimal; depends on bundle-root references.

Workflow

8.4

Nine-step pipeline with per-source mapping rules, never-inject rule, approval card; source-URL fetching path undefined.

Content

10.0

Sharp writing with concrete per-platform rules and refusal anti-patterns.

Engineering

9.0

Correct frontmatter; bundle-root path references only; no scripts.

Security

9.5

Publish gated on approval; no scraping, credentials, or external endpoints of its own.

Clean single-file transform skill: extract spine, re-hook with 20 formulas, expand to 900-1300 chars, strip platform artifacts, humanize, approval card, routed publish. Per-source-type native-fit rules are concrete; no own references and no defined fetch path for source URLs.