Repurpose
Skill lumizone/social-content-os-claude-skill/skills/repurpose
Claude Code skill pack that plans and produces social media content that performs: a tagged content calendar, scroll stopping hooks, rendered carousels, captions, and repurposing. Interest Graph playbook, zero AI artifacts.
npx -y skills add lumizone/social-content-os-claude-skill --skill repurposeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Break one long-form asset into a batch of social posts across formats and channels (the Content Flywheel). Use when the user has a YouTube script, podcast transcript, newsletter, blog post, or webinar and wants to turn it into social content, or says "repurpose ten artykul", "z tego long-forma zrob posty", "rozbij na content", "turn this into posts", "make social content from this", "atomize this", "content flywheel". Deconstructs the source into N carousels, N text/ caption posts, N short-video hooks+scripts, and a thread, each mapped to a channel and funnel stage, following Best of Nine and multi-channel architecture. Hands pieces off to hook-lab, carousel-builder, and caption-writer.
SKILL.md
2.7 KB, as published. Nobody here has run it
repurpose
One deep asset becomes a week of content. This is the Content Flywheel: long-form
is the foundation, you deconstruct it into many short forms, distribute per channel.
Default output: English.
Reference: multi-channel / flywheel §13, Best of Nine §6, funnel §7–8 in
../social-content-os/reference/frameworks.md. Load ../social-content-os/brand.json.
Inputs
- The source asset: paste the text, give a file path, or a URL/transcript.
- Target channels (default from brand.json).
- How many pieces to extract (default: a 1-week batch — see below).
Method
- Mine the asset for its distinct ideas, claims, stories, data points, and contrarian takes. Each becomes a potential atomic post. Aim for the strongest 8–12 nuggets, not every sentence.
- Assign a format to each nugget by what it is:
- A story or transformation → Reel/Short hook + script, or a carousel.
- A framework or list → carousel (high dwell time).
- A sharp opinion or data point → LinkedIn/X text post.
- A how-to → carousel or thread.
- Map funnel stage for each (Unaware → Conversion) and channel, so the batch nurtures across the funnel, not just ToF.
- Apply Best of Nine: pick the 3 strongest formats and note how to recreate each 3x (different hook/angle) to find a repeatable winner.
- Route, don't write everything inline. Output is the plan + the seed for each piece; offer to run hook-lab on the Reel/short ideas, carousel-builder on the carousel ideas, and caption-writer on the text posts.
Output
A repurpose sheet (table): piece # | source nugget | format | channel | funnel stage | working hook | which skill builds it. Default batch = roughly:
- 2 carousels, 3 short-video hooks+scripts, 3 text posts (IG/LinkedIn/X), 1 thread.
Then a short "build order" recommending which 3 to produce first and why, and the one-click handoffs to the production skills.