Clipify

Clipify

A [Claude Code](https://claude.com/claude-code) skill that turns long videos into social-ready clips.


Point it at any video file and it will:

1. Find clip-worthy segments — transcribes the video with Whisper and scans the transcript for punchlines, reversals, awkward pauses, and audio peaks to propose 3–5 candidates.
2. Create a 9:16 clip — cuts your chosen moment, then reframes 16:9 → 9:16 with hard-cut pans that follow whoever is speaking (or split-screen if you'd rather see both faces).
3. Add subtitles — burns opus-style word-by-word captions (big bold white, yellow active-word highlight).

No cloud APIs. Runs entirely on your machine. No OpenCV. ~20s of work for a 20s clip on Apple Silicon.

Why this exists

Most "auto-clip" tools are either expensive SaaS, slow, or produce slop. This skill is what I actually use to clip my long-form videos for LinkedIn and TikTok. Built for talking-head dialogue (interviews, podcasts, two-person setups).

Requirements

• macOS (uses VideoToolbox for hardware-accelerated decode — works on Linux/Windows if you remove -hwaccel videotoolbox flags)
• Claude Code
• ffmpeg with libx264 (brew install ffmpeg)
• `whisper` (pip install openai-whisper)
• Python 3 with numpy (pip install numpy)

Install

git clone https://github.com/louisedesadeleer/clipify.git ~/.claude/skills/clipify

That's it. Restart Claude Code and `/clipify` is available as a slash command.

Usage

In Claude Code:

/clipify

Then paste a video file path when asked. The skill will:

1. Transcribe → propose 3–5 funny candidate clips with timestamps and titles
2. Ask which to cut
3. Ask 9:16 / 16:9 / 1:1
4. If 9:16 from 16:9 with two faces: ask pan vs split-screen
5. Ask subtitle style (opus / karaoke / minimal — or paste