Download for MacApple silicon, macOS 14+
Skill

repurpose-video

@upload-post Updated 2026-10-17

Turn a long video (talking head, podcast, livestream, webinar) into multiple viral short clips and schedule them to TikTok, Instagram Reels, and YouTube Shorts. Transcribe, find viral moments with AI, cut with FFmpeg, optionally add hook overlays, then schedule. Use when the user mentions repurposing, autoshorts, viral clips, making shorts, or cutting a long video into clips.

autodmautoshortsclaude-codeclaude-code-marketplaceclaude-code-plugincomment-funnelcontent-creatorcursor-plugin

Install

With your agent

Install OMGSkills skill "upload-post/upload-post-plugin:skills/repurpose-video" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.

Manual command

git clone https://github.com/Upload-Post/upload-post-plugin /tmp/upload-post-plugin && ln -s /tmp/upload-post-plugin/skills/repurpose-video ~/.claude/skills/repurpose-video

From README

Repurpose a long video into viral shorts This is the autoshorts pipeline. It chains: transcribe → identify clips → cut → optional overlay → upload to short-form platforms. Locate the source video The FFmpeg tools need a public, directly downloadable HTTPS URL (or an Upload-Post media URL from a previous upload). A YouTube/Vimeo watch page is not a file URL. If the user only has a local file, ask them to share a direct download link first. Transcribe The Upload-Post MCP does not ship a transcription tool today. Two options: The user already has a transcript (YouTube captions, a Whisper export, an existing autoshorts run). Ask for it and skip to step 3. No transcript yet. Submit a submitffmpegjob with inputurl and a fullcommand that extracts the audio (e.g. ffmpeg -y -i {input} -vn -ac 1 -b:a 64k {output} with outputfilename: "audio.mp3"), then run Whisper locally (or any transcription tool the user has).