# Sourced Data-Story 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 `.md` to its path. Before generating anything, show the person the options on the use-case page.

One point, one hero number, three beats: every figure sourced, every frame compiled in code.

- **Slug:** `want-data-story-explainer`
- **Status:** wanted
- **Publisher:** Francesco (community)
- **Source:** https://x.com/francescoinweb3/status/2111393917899808880
- **Cost:** ~6 credits / run (estimate) — Render only (catalog of 2026-10-23); an ElevenLabs v4 Turbo voiceover adds ~0.0042 credits per character.

## What it does

A short data video with one point, one hero number and three beats, where every figure on screen carries its source and every frame is code. Francesco's "6 small jobs" method splits the work into files an agent can check: a spec of a reference video, a data.json with sources, a story.md, a Remotion scene, plain-language timing notes, then rendered stills checked against the spec and the data before final.mp4. An agent follows the same contract with HyperFrames or Remotion, adds an optional ElevenLabs voiceover, and re-renders only the line that changed when the user gives a note.

## 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/francescoinweb3/status/2111393917899808880

How an agent would make it: Reference spec → sourced data.json → story.md (one point, one hero number, three beats) → code scene (Remotion / HyperFrames) → plain-language timing notes → stills checked against spec and data → final.mp4

**Models it drives:** render, eleven_v4_turbo

## Example output

https://skills.varg.ai/previews/want-data-story-explainer.mp4 — His code-drawn 'Claude / Agent Lab' data visual: counters (references, rooms, skills, scenes, re-rolls), a radial chart and labeled panels step through DATA and STORY ('one point, one hero number'). It shows the six-job method, not a finished data story (4.5–12.5 s of 24 s) (credit: Francesco (@francescoinweb3), https://x.com/francescoinweb3/status/2111393917899808880)

## Used for

- [Animated chart or data video](https://skills.varg.ai/use-cases/data-video.md): Numbers from a CSV or a report as an animated chart: bar race, line, hero number.

## More explainers skills

- [HyperFrames](https://skills.varg.ai/skills/hyperframes.md): Turn HTML, CSS and seekable animation into deterministic MP4s: launch films, explainers, captions, title cards.
- [HyperFrames Slideshow](https://skills.varg.ai/skills/hyperframes-slideshow.md): Build a live, navigable deck with fragment reveals, branching hotspots and presenter notes instead of an MP4.
- [Plain-Sight Explainer](https://skills.varg.ai/skills/hyperframes-vox-explainer.md): 60–90 s collage explainers about everyday things, or mined from your documents and links, with numeric seam checks.
- [Remotion Create](https://skills.varg.ai/skills/remotion-create.md): Scaffold a new Remotion project and lay the video out as clips or scenes before writing any frames.
- [Remotion Maps](https://skills.varg.ai/skills/remotion-maps.md): Animate maps in Remotion: static maps, Mapbox, MapLibre, MapTiler and CesiumJS 3D flyovers.
- [Higgsfield Video Explainer](https://skills.varg.ai/skills/higgsfield-video-explainer.md): 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