# Explainroo — workflow skill 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.

Narrated explainer MP4s with a local voice (Kokoro), word timing (Whisper) and a canvas renderer; no API key needed.

- **Type:** [Workflow](https://skills.varg.ai/workflows.md) · [Explainers](https://skills.varg.ai/browse/skills/explainers.md)
- **Slug:** `explainroo`
- **Status:** live
- **Publisher:** Vincent Schmalbach (community)
- **License:** MIT
- **Source:** https://github.com/vincentsch/explainroo/tree/main/skills/explainroo
- **Works in:** Claude Code, Codex
- **Requires:** Node.js 20.11+, ffmpeg, Chrome or Chromium, espeak-ng for some narration languages
- **Cost:** Free — local voice and render; ElevenLabs optional with your key
- **Runtime:** ~2 min for a 15 s promo (Agent Skills Hub test)
- **Adoption:** 46 installs, 654 GitHub stars (GitHub + skills.sh, 2026-10-26)

## What it does

Makes an explainer, how-to, walkthrough, launch or tutorial video (or a vertical short) from two files: the script the voice reads and a small JavaScript scene file that draws the pictures. A voice model runs on your machine, word timings come from Whisper, Chrome renders the frames, explainroo adds music and sound effects, and `explainroo verify` checks the result. In the Agent Skills Hub end-to-end test (2026-10-11) it was the fastest of 16 skills, 2.0 minutes for a 15-second promo, with a look of its own.

## Use when

- Make a narrated explainer or tutorial video without API keys
- Animate a diagram with a voice-over
- Make a quick YouTube, Reels or TikTok explainer

## Not for

- Talking-head or AI-generated footage

## Install

- Claude Code: `git clone https://github.com/vincentsch/explainroo.git && cd explainroo && npm install`

**Models it drives:** kokoro, whisper

## Example output

https://skills.varg.ai/previews/explainroo.webp — Poster frame of the repo's DNS example explainer in the chalk look: hand-drawn browser → resolver → root/.com/name servers. Still image; the README's demo video attachment is not publicly downloadable and explainroo.com is blocked by this network's safe-browsing filter. (credit: Vincent Schmalbach (explainroo), https://github.com/vincentsch/explainroo/tree/main/docs/media)

## 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