What this agent does
One good long-form video usually has five short clips hiding inside it, but cutting them by hand means re-watching the whole thing with a stopwatch. This agent finds the strongest moments in a long-form video and turns each one into a short, captioned clip ready to post.
highlight-finder— analyzes the video's transcript and pacing to identify 5 standalone moments that work without the surrounding context (a strong hook, a complete thought, a punchline).clip-captioner— cuts each identified segment, generates burned-in captions synced to the audio, and writes a short platform-native caption + hashtag set for each clip.
Every run saves the 5 clips plus their captions into a dated output folder, ready to review and post.
Requirements
- A video file (local, or a URL Claude AI can fetch) with clear spoken audio — this agent relies on the transcript for highlight detection, so heavily music-only content won't work well.
- Works on Claude AI (Claude Code, with a local video-processing tool like
ffmpegavailable on the machine) for the cutting/captioning step. ffmpeginstalled locally for video cutting and caption burn-in — this is the only external dependency.
Setup
- Unzip the package into your workspace, keeping the folder structure intact.
- Confirm
ffmpegis installed and on yourPATH(ffmpeg -versionto check). - Edit
config/repurpose-preferences.mdwith your preferred clip length range and caption style. - Run the starter prompt in
starter-prompts.mdagainst a sample video to see the full pipeline end to end. - For a recurring workflow (e.g. every new upload in a watched folder), adapt
automation-prompt.mdto your folder-watching setup.
What's included
Skills/highlight-finder/SKILL.mdandSkills/clip-captioner/SKILL.mdconfig/repurpose-preferences.md— clip length, caption style, hashtag setinstallation-prompt.md—ffmpeginstall check and Claude Code setupautomation-prompt.md— notes on adapting this to a watched-folder workflowstarter-prompts.md— example prompt for a first test runassets/— pipeline diagram
