- Home
- Skills
- Social Media
- Beat-Sync Edit Studio
Beat-Sync Edit Studio
Turn photos and a song into an original, beat-synced video edit (birthday, anniversary, friendship, fan reels and more), with a new design every time.
$10
Works with the AI Agents you already use
Beat-Sync Edit Studio
Example session with this skill installed
Here are 12 photos of my best friend and this song. It's her birthday, keep it funny but sweet, 30 s for Instagram, use the chorus.
- Read your context and instructions
- Compiled the beat-sync edit studio
A short questionnaire (occasion, tone, duration, song part, photo placement, then look, energy and signature elements), a beat-by-beat plan, preview stills, then a 1080×1920 MP4 with every cut on the beat, loudness-normalised audio and a section-by-section breakdown of the captions.
Connects securely to your tools. The creator never sees your data.
About this skill
Give your AI agent a few photos and a song, and get back an original music-video edit where every cut, transition, text reveal and effect lands on the beat.
How it works
- It asks first: the occasion (birthday, anniversary, crush, friendship, farewell, wedding, fan edit…), how friendly or romantic it should feel, the duration and format (9:16 reel, 16:9, 1:1), which part of the song to use, and where you want specific photos.
- It maps the song: tempo, downbeats, builds, drops and breakdowns, then designs the video's flow around them. A soft intro gets an intimate opening, the drop gets the boldest element, the breakdown gets the emotional photo.
- It builds and checks: preview stills of every section before the full 1080p render, then a final check of the finished video.
Never the same video twice. The look, elements, captions and ending come from your song, mood and occasion each time. The four preview videos (shown with placeholder figures and original music) are examples of the craft, not templates.
What's inside
- Beat analysis script (tempo, beat grid, best song windows, kick envelope)
- Effects toolkit: 8 colour looks, bass hits, liquid/whip/iris/slice transitions, stickers, halftone, kinetic text, render harness
- Royalty-free beat layer: add afro, house, techno or rock drums to a soft song, at speaker-safe loudness (−14 LUFS)
- 40+ elements: social-card carousel, story mode, notification storm, magazine cover, polaroids, stat card, parallax cutouts, compliment-word portrait, trading-card pack, tarot reveal and more
- Bonus formats: holographic card pack, tarot deck, walk-through photo museum, playable mini-game, "the sky the night they were born" poster
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Social Media.
It doesn't download music (you supply the song file). Renders take a few minutes per 15 s at 1080p. Face positions are estimated by eye and checked on preview stills. Song excerpts are for personal sharing; the bundled beatlayer.py makes royalty-free tracks if you need one.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Accounts
GitHub
- Software
Python 3.10+FFmpeg~4 GB RAM for 1080p
- Optional
- rembg (photo cutouts)pillow-heif (iPhone photos)rubberband (tempo change)
Permissions
Allowed Hosts
File Scopes
Installs rembg and pillow-heif with pip; rembg downloads its segmentation model from GitHub on first use; fonts come from Google Fonts on GitHub. Everything renders locally.