What-If Science Explainer — trending format for explainers
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
A flat-vector space explainer drawn entirely in code: narration-timed camera moves, counters and a tiny mascot.
- Slug:
want-what-if-science-explainer - Status: wanted
- Publisher: Finn (community)
- Source: https://x.com/finnardley/status/2114305886420086817
- Cost: ~10 credits / 30 s video (estimate) — ~450 characters of ElevenLabs v4 narration (~4 credits; v4 Turbo costs half) + render ~6 (catalog of 2026-10-23).
What it does
A 30-second "what if" explainer in flat-vector style (a navy starfield, a shader-lit Earth with city lights, a small astronaut mascot, and countdowns and labels that fire on the narrator's words, such as "8:20 until Earth notices") drawn entirely in code, with no AI images or video. Finn rebuilt the look of a famous science channel with Opus 5.5 and gave away the whole prompt: one HTML file where every frame is a pure function of time, ElevenLabs narration with word timestamps, and Playwright seeking every frame. An agent writes the narration with one visual event per key word, gets timestamps from ElevenLabs v4 (or Whisper), builds canvas and WebGL scenes as a HyperFrames composition, and mixes a music bed and per-event SFX.
Status
A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.
Example: https://x.com/finnardley/status/2114305886420086817
How an agent would make it: Topic → narration with one visual event per key word → ElevenLabs v4 voice with timestamps → code-drawn 2D canvas + WebGL globe scenes, every frame a pure function of time → HyperFrames render → music bed + SFX, mastered to -14 LUFS
Models it drives: eleven_v4, whisper, render
Example output
https://skills.varg.ai/previews/want-what-if-science-explainer.mp4 — 'What if the Sun vanished?' drawn in code: a flat-vector Earth with city lights, an astronaut mascot and an '8:20 until Earth notices' countdown, then a dive to a YOU pin and 'This light left the Sun 8 min 20 sec ago' (2.6–10.6 s of 30 s) (credit: Finn (@finnardley), https://x.com/finnardley/status/2114305886420086817)
More explainers skills
- HyperFrames: Turn HTML, CSS and seekable animation into deterministic MP4s: launch films, explainers, captions, title cards.
- HyperFrames Slideshow: Build a live, navigable deck with fragment reveals, branching hotspots and presenter notes instead of an MP4.
- Plain-Sight Explainer: 60–90 s collage explainers about everyday things, or mined from your documents and links, with numeric seam checks.
- Remotion Create: Scaffold a new Remotion project and lay the video out as clips or scenes before writing any frames.
- Remotion Maps: Animate maps in Remotion: static maps, Mapbox, MapLibre, MapTiler and CesiumJS 3D flyovers.
- Higgsfield Video Explainer: Turn a topic or document into a narrated, stylized explainer assembled from 10-second voiced blocks.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt