render-flat-vector-explainer

Assembles a flat-vector product-routine explainer: one illustrated creator-character walks through a countable N-step routine (e.g. collagen -> serum -> eye cream -> hair), one step per beat, each beat carrying a large corner numeral, a labelled chip + one-line tagline, and the step's real product photo, closing on an "N products" grid + brand CTA. It reads as a premium DTC explainer (Spotify/Anchor flat-vector lineage), not UGC.

This capability is documentation-grade. The content-goose molecule is a documented recipe, not a runnable end-to-end app, so this capability ships the config schema (scripts/config.example.json), the field-to-script map (scripts/PIPELINE.md), and a README (scripts/README.md) describing the FREE assembly steps the agent runs by hand with ffmpeg + Remotion + PIL. The paid generative steps are separate capabilities the recipe orchestrates and gates.

The two non-negotiable separations

Motion layer != text layer. Animate a text-stripped clean plate with Kling i2v (subtle motion, style-preserving negative, cfg 0.5), then composite every chip / numeral / tagline / slate / CTA as an animated Remotion DOM overlay on top. Baking text into the keyframe before i2v warps the type and forfeits the ability to retime/restyle it — this separation is the format's whole credibility.
Real assets != AI assets. The per-step product photo and the closing "N products" grid are real product webps composited with PIL (AI duplicates SKUs in a grid). Only the character vignettes and stylized backgrounds are generative.

Free assembly steps (this capability)

The agent runs these deterministic, $0 steps by hand — see scripts/README.md for the ffmpeg/Remotion/PIL detail: