Gooseworks Video (Apple Notes Ads) — workflow skill for phone & app screens
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.
Video ads in chat from a reference ad or a ready style, including the viral HTML-only Apple Notes typing ad.
- Type: Workflow · Phone & app screens
- Slug:
gooseworks-apple-notes-ads - Status: live
- Publisher: Gooseworks (community)
- License: MIT
- Source: https://github.com/gooseworks-ai/goose-skills/tree/main/skills/entry/goose-video
- Works in: Claude Code, Codex, Cursor, Any MCP client
- Requires: Gooseworks account, Node.js (npx)
- Cost: Billed in Gooseworks credits; each video is priced and needs your approval first
- Adoption: 1,270 GitHub stars (GitHub (gooseworks-ai/goose-skills), 2026-10-26)
What it does
The Gooseworks entry skill behind the July 2026 "Apple Notes ads in Claude" launch (about 200K views on X): Claude builds a native-looking Notes typing ad in HTML with no video model in the loop, and the same kit renders iMessage and ChatGPT screen mockups. Today goose-video is a thin router: it asks for the brand and product, finds a real reference ad to remake (or offers ready-made styles) and drives the work through the Gooseworks MCP server, which holds the provider keys and bills in Gooseworks credits after you approve a priced plan. The deterministic Notes renderer (create-apple-notes-mockup, HTML + Playwright) is still in the repo but marked superseded by the kit's phone-chat part.
Use when
- Make a vertical Apple Notes, iMessage or ChatGPT-screen ad for Meta or TikTok
- Remake a reference ad you like for your own brand and product
- Test many cheap ad variants without a video model
Not for
- Offline or self-hosted rendering (generation runs on the Gooseworks service)
- Cinematic footage or talking-head video
Install
- Claude Code:
npx gooseworks@latest install --claude --mcp - Codex:
npx gooseworks@latest install --codex --mcp - Cursor:
npx gooseworks@latest install --cursor --mcp
Example output
https://skills.varg.ai/previews/gooseworks-apple-notes-ads.mp4 — The 'Introducing Apple Notes ads in Claude' launch video for /goose-video: a native-looking Notes typing ad built in HTML. First 8 s of the typing. (credit: Shiv Sakhuja / Gooseworks, https://x.com/shivsakhuja/status/2075128457030472110)
Used for
- Apple Notes style ad: A note types itself in a phone notes app, reads like a confession, and turns into an ad.
- Trending AI video formats: What's going viral now — formats you can make for your brand today, with the skill for each.
More phone & app screens skills
- iPhone Duo Fold: Your screens on Apple's foldable iPhone Duo, unfolding in 3D with its progressive blur. Local, free.
- iMessage Video: Pixel-perfect iMessage conversation videos from a JSON script: iOS 26 chrome, typing, tapbacks, group chats.
- Duo Foldable Phone: Two HTML screens composited into a photo of hands holding an open foldable phone, for side-by-side meme videos.
- X Posting License: A 10-second animated 'posting license' card for an X profile, filled with real profile data into a locked template.
- App Store Screenshots: Make App Store and Google Play screenshots to exact specs: sizes, gallery order, mockups and previews.
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