Autonomous Shortform Facecam Editing banner
gquthier gquthier

Autonomous Shortform Facecam Editing

Development community

Description

CREATIVE · VIDEO — One raw facecam take → a finished short-form motion-graphics ad. Claude Code skill + playbook, rendered with HyperFrames.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

CREATIVE · VIDEO

Autonomous Short-Form Facecam Editing

One raw facecam take in. A finished motion-graphics ad out.

Paid-social editors charge you per video for a job that is 90 % rules.
This skill hands the rules to your agent — one designed card per sentence, word-synced captions,
sound design, brand B-roll — and renders the whole thing deterministically. You keep the taste.


BizOS — build autonomous companies



X YouTube


Claude Code skill + playbook · silence pre-cut · face-centred square & 9:16 crops (mirror) · word-level transcript · brand steal (palette, screenshots, site B-roll) · one motion-graphics card per sentence · karaoke captions · SFX + music bed · pencil-border windows · cutout variant · HyperFrames render · QA loop


This is a **Claude Code skill** + a complete playbook (with runnable scripts) that turns **one raw talking-head take + one brand URL** into a finished **1080×1920 motion-graphics ad** — the way a paid-social editor would, but scripted for an AI coding agent and rendered deterministically with [HyperFrames](https://hyperframes.heygen.com) (HTML + GSAP → MP4).

The take plays untouched underneath, in a tight face-centred **square window** (or full-bleed). On top: **one designed card per sentence** — count-ups on every number, lists that pop and get struck through, stamps on real scre