Communitygithub.com

video-explainer

Video and animation skill. Build an editorial, documentary or technical explainer from an approved brief and shotbook. Covers narration, word-anchored timeline, Remotion scene code (world-space camera, maps, charts, diagrams, Manim inserts), sound, render, QA and an independent critic revision. Use after /video-direct for explainers (Vox-inspired editorial, 3Blue1Brown-style technical, data journalism, maps).

Qu'est-ce que video-explainer ?

video-explainer is a Gemini CLI agent skill that video and animation skill. Build an editorial, documentary or technical explainer from an approved brief and shotbook. Covers narration, word-anchored timeline, Remotion scene code (world-space camera, maps, charts, diagrams, Manim inserts), sound, render, QA and an independent critic revision. Use after /video-direct for explainers (Vox-inspired editorial, 3Blue1Brown-style technical, data journalism, maps).

Compatible avec~Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/Blaise-Muhune/video-studio-starter/tree/HEAD/claude-skills/video-explainer

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

/video-explainer

Inputs: projects/$0/ with an approved BRIEF.md, SHOTBOOK.md, narration.json and timeline.json cues. Outputs: renders/<slug>_vN.mp4 (≥ v2), stems, review/<render>/qa_report.md + critic.md, an updated manifest/costs.

Load only

  • docs/motion-design.md (tokens, choreography, determinism, engine choice)
  • docs/editing-and-compositing.md § One timeline, § Audio
  • The project's chosen style file(s) in styles/
  • Editorial or factual: docs/editorial-documentary.md. Technical: styles/technical-math.md
  • docs/quality-assurance.md before reviewing

Procedure

  1. Voice. Scratch first (free): python tools/narrate.py $0 --provider kokoro. For production, audition Gemini (--audition --provider gemini): print the estimate, get the user's approval, then add --yes. If the user supplied their own recording, put it at audio/narration.wav and write segments with narrate.py --align instead.
  2. python tools/timeline.py $0: resolve every cue against the actual audio.
  3. Scene code. Create engine/src/projects/<slug>/Scene.tsx (copy the structure of question-to-product/Scene.tsx) and register it in engine/src/projects/registry.ts. Rules:
    • World space plus one camera container; every state is a pure function of t and cue()
    • Easing only from EASE; randomness only via rnd(seed); fonts from lib/fonts.ts
    • Maps: d3-geo + topojson-client + world-atlas (bundled, never fetched at render), with a source line
    • Charts: SVG with honest axes, direct labels and a source line; numbers come from BRIEF §4
    • Math: Manim CE renders to assets/manim/*.mp4, composited with <OffthreadVideo>
    • Images: code-drawn first. Generated (tools/image_gen.py, paid, --yes) only for illustration/cutouts, recorded in the manifest
  4. Style-frame check. python tools/render.py $0 --stills <cue times> → look at them, fix layout or safe areas.
  5. Sound. Add sfx and music to timeline.json (peaks on cues, one riser→impact max), then python tools/sound_synth.py $0 and python tools/audio_mix.py $0.
  6. Render v1: python tools/render.py $0 --out <slug>_v1.mp4.
  7. QA + critic: run /video-review $0 renders/<slug>_v1.mp4.
  8. Revise: fix all P0s and the P1s you agree with, re-render v2, and run review round 2. At most 3 rounds.
  9. Deliver: see /video-render for platform cuts and the delivery note.

Quality gates

  • No hard-coded seconds in scenes: only cues
  • Every factual graphic carries a source line; the numbers match BRIEF §4
  • qa_report shows no automatic issues; loudness −14 ±1 LUFS, TP ≤ −1 dBTP
  • Critic P0 = 0; at least one revision round performed
  • Report says what was measured vs what still needs a human listen

Shared parts (2026-11-06)

Build on engine/src/lib/parts.tsx (Svg, PartsDefs, Finish, Push, PartLabel, BigWord, Counter, Dust, Caption, ChatBubble, SAFE). Import them instead of re-writing captions, counters, labels, vignette or safe-area maths; a scene should be 200-400 lines. Add a new reusable piece to parts.tsx when a second project needs it.

Individual skills in this repo

This repo contains 1 individual skill — each has its own dedicated page.

Skills associés