vox-collage

vox-collage is a Video production & editing skill for AI agents, published by alecs5am in the ralphy repository on GitHub. Skillspace rates vox-collage D (62/100) and it passed the safety scan; the rating is based on static analysis only.

How to turn ONE topic into a Vox-style paper-collage explainer / ad video — a punchy narrated short where each beat is a torn-paper collage POSTER that comes alive, with VO, music and captions. A craft overlay on the standard pipeline: the look is BORN in the image (a rich layered collage poster per beat — text-to-image, 5-part prompt structure, headline baked in), then a FLAT-SAFE "living poster" motion pass animates it, then hard-cut assembly. Supplies the one mandatory beat-map approval gate, the density rule (6+ separate cut-out pieces filling the frame, NOT one sticker on a plain bg), the flat-safe i2v constraint set (ONE smooth 2D camera move, ~5% amplitude, stability anchors on text/layout, banned warp moves) that is WHY seedance works for flat art, and anti-monotony hard cuts (adjacent beats never share a camera move; static reserved for the payoff). Works for ANY topic / product / person + ANY era-matched aesthetic. Ported from vox-director by Alisa Qian. USE WHEN the user…

Grade

D

Quality

62 / 100

Safety

Passed

GitHub stars

108

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.