explainer-big-thinklisted
Install: claude install-skill Safiullah-Rahu/claude-video-skills
# Big Think — expert interview + graphic packaging
> `ENGINE` = `~/.claude/skills/explainer-engine/engine` (the **explainer-engine** skill: renderer, voice, score, QA). Rendered sample of this skill: `the sample film (the render is not included in this repository)` (source in `assets/sample/`).
An expert, seated on a wooden chair in front of a white paper sweep set up inside a big warm room, explains one idea
in their own voice. The edit never rests: wide "set reveal" ↔ chest-up medium ↔ ×1.25 punch-in, b-roll on every concrete
noun, and a calm, bookish graphics layer — black-on-off-white speckled paper cards that roll down like blinds, white serif
words that land on syllables, label tapes, archival plates in physical frames. The graphics barely move; the cutting and
the footage carry the energy. Code-only rebuild: the expert is an ORIGINAL flat-vector person (`BT.expert`) in a drawn loft
(`BT.studio`), stock CGI becomes canvas neurons / spheres / synapses (`BT.cgi`). Built from frame analysis of 3 source
videos (references/sources.md). Original work only: own expert, own monogram bug, own series name, own end card.
## 1. Signature traits
- **Interview set within a set**: white seamless backdrop + roll tube in a warm loft (brick, arched factory windows, bookshelves, wood floor, softbox). Wide shows the room; medium is all grey-white paper with a blurred room sliver at one edge.
- **Cut every 2–3 s** on the stressed word: framing changes inside interview runs, hard cuts to