webreel — effect skill for UI walkthroughs
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page. From a terminal:curl -fsSL https://varg.ai/install | shinstalls the vargai CLI (https://varg.ai/how-to/cli.md):vargai searchandvargai install <slug>with no key, every varg model aftervargai login.
Scripted browser demo videos from a JSON config: clicks, typing, drags and scrolls with cursor and keystroke overlays.
- Type: Effect · UI walkthroughs
- Slug:
webreel - Status: live
- Publisher: Vercel Labs (vendor, verified)
- License: Apache-2.0
- Source: https://github.com/vercel-labs/webreel
- Works in: Claude Code, Codex, Cursor, Gemini CLI
- Requires: Node.js, webreel npm package (npm install webreel), Chrome headless shell and ffmpeg (downloaded to ~/.webreel on first run)
- Cost: Free, Apache-2.0: records locally
- Adoption: 283 installs, 966 GitHub stars (skills.sh, 2026-11-10)
What it does
webreel records scripted browser demos as MP4, GIF or WebM. You describe steps in a JSON config (navigate, click, type, key combos, drag, scroll, pause, screenshot), and it drives headless Chrome, captures frames at about 60 fps and encodes with ffmpeg, adding an animated cursor, a keystroke overlay and click and key sound effects. One config can hold several videos and shared setup steps, and npx webreel preview shows a run before recording. The skill teaches the agent to write and debug those configs, so a demo can be re-recorded whenever the UI changes. It is a Vercel Labs experiment.
Use when
- record a scripted product or feature demo of a web app
- a browser walkthrough with cursor motion, keystroke HUD and click sounds
- re-record a demo after the UI changes, from the same JSON config
- MP4, GIF or WebM demo clips at desktop or mobile viewport sizes
Not for
- Recording a real screen or desktop app: it drives headless Chrome only
- Editing existing footage
Install
- Claude Code:
npx skills add vercel-labs/webreel --skill webreel -a claude-code - Codex:
npx skills add vercel-labs/webreel --skill webreel -a codex - Cursor:
npx skills add vercel-labs/webreel --skill webreel -a cursor - Gemini CLI:
npx skills add vercel-labs/webreel --skill webreel -a gemini-cli - Any agent, with the vargai CLI:
vargai install webreel
Example output
https://s3.varg.ai/files/4325c578-378d-4c43-ae53-3cc3218df1ea/file_2a0980076a13.mp4 — The drag-and-drop example from the webreel docs: a card dragged across a kanban board with the animated cursor, recorded by webreel (credit: Vercel Labs (webreel examples), https://webreel.dev/examples)
More UI walkthroughs skills
- Zoom to the Action: The full app establishes, then the camera pushes 1.5–2× into the part being used and eases back out.
- 3D Tilted Dashboard Reveal: The dashboard rises from a steep 3D tilt to flat, like a screen lifting toward the viewer.
- Floating UI Panels in Depth: The interface splits into its panels, which float apart in depth with parallax, then snap back.
- UI Builds Itself Piece by Piece: Grey skeleton blocks pulse once, then real cards, charts and text fill in with a stagger.
- Before/After UI Wipe: A divider sweeps across one screen, turning the old version into the new one underneath.
- Card Expands Into Detail: A small card grows into a full detail panel in one continuous shape change.
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.
- Any agent with a terminal:
curl -fsSL https://varg.ai/install | sh(Windows:irm https://varg.ai/install.ps1 | iex), thenvargai loginand every model is a command —vargai generate_video …,vargai estimate_cost …(https://varg.ai/how-to/cli/) - 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 - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - 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