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.mdto 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 · Explainers
- 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: 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