Content repurposer

Skill Ootto-AI/claude-content-skills/skills/content-repurposer

Turn one long-form source (blog post, podcast, YouTube video, webinar, transcript) into a batch of short-form reel ideas and scripts. Use when the user says "repurpose", "turn this into reels", "atomize", "clip this", "content from my blog/podcast", or "make videos from this".From its SKILL.md

Install

npx -y skills add Ootto-AI/claude-content-skills --skill content-repurposer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

19 stars19 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 file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, 389 tokens by cl100k_base, as published. Nobody here has run it

Content Repurposer

Turn one long source into a week of short-form videos — the heart of a content factory.

When to use

You have a blog post, podcast episode, YouTube video, or webinar and want 5+ reels out of it instead of one.

What you'll need

The source text or transcript (paste it, or a detailed summary), your audience, and the platform. Optional: brand voice.

Instructions

Give Claude the source, then run this prompt:

You are my content repurposing engine. From the source below, extract the short-form video gold.

Source:
"""
[paste blog post / transcript / detailed summary]
"""

Audience: [who it's for]   Platform: [Reels/TikTok/Shorts]

Do this:
1. Pull the 5 most reel-worthy ideas (a surprising claim, a how-to, a myth, a story, a result). One line each.
2. For each idea: write 1 scroll-stopping hook + a 3-beat outline (hook → value → CTA).
3. Flag which 2 have the highest viral potential and why (emotion, specificity, or contrarian angle).

Keep it concrete and lifted from the source — no generic filler.

Obsidian memory tip: Keep your long-form library in your Obsidian vault (Filesystem MCP), and Claude can repurpose across sources — "find the 5 best reel ideas across everything I published this quarter," not just one post.

Tip: One good podcast can become 8-10 reels. Batch the scripts, then film in one sitting.

Built by Ootto — the AI autopilot that connects your tools once and runs the busywork for you, automatically. Book a demo →

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most video audio skills give in 389 tokens

Counted across 619 of the 725 authors here whose files we hold, read 2026-09-06

Read product marketing context firstin 13 of 619, across 7 files
Define the core visual thesis in one sentencein 11 of 619, across 3 files
Break the concept into 3 to 6 scenesin 11 of 619, across 3 files
Render the smallest working version firstin 11 of 619, across 3 files
Start with a low-quality smoke test renderin 11 of 619, across 3 files
Add captions for accessibility and engagementin 11 of 619, across 5 files
Write the scene outline before writing codein 11 of 619, across 3 files
Specify subject, action, camera, style, and moodin 11 of 619, across 5 files
Decide what each scene provesin 10 of 619, across 2 files
Export one clean thumbnail framein 10 of 619, across 2 files
Pick the right tool for the jobin 10 of 619, across 4 files
Run the test suite before proposing a fixin 8 of 619, across 7 files

Said here and by no other author read

Give Claude the source text
Run the repurposing prompt
Extract five reel-worthy ideas
Write hooks and outlines
Flag highest viral potential

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.