Launch Films From the Product's Real UI With Click Checks — workflow skill for launch videos
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.
Launch film in Remotion that renders the product's real page or components, with a verify step that checks every click, zoom and frame.
- Type: Workflow · Launch videos
- Slug:
launch-film-real-ui-verified - Status: live
- Publisher: jammaru (community)
- Source: https://github.com/jammaru/launch-video-craft/tree/main/skills/launch-video-craft
- Works in: Claude Code
What it does
Input: a reference clip, a logo and the product's code. The reference gives only story roles and film grammar; every screen comes from the product's own renderer (its built page in ProductFrame, its components, or captured terminal output). Each shot is one argument sentence with a beat sheet: headline alone at least 1 s, window rises and lands, camera zooms to 1.4x+ on the control, cursor presses, result held 50+ frames. npm run verify fails on guessed coordinates, missed clicks, unreadable type or a lookalike window, and render refuses until it passes. Ships a kit with stage, camera, cursor, terminal, agent chat and synthesized sound.
Use when
- Make a launch video or promo in Remotion
- Show the product's real UI, not a mockup
- Borrow tempo and camera from a reference clip
- Make a launch film for a CLI, library or agent skill
- Render a localized second cut
Install
- Claude Code:
npx skills add jammaru/launch-video-craft - Any agent, with the vargai CLI:
vargai install launch-film-real-ui-verified
Example output
https://github.com/jammaru/launch-video-craft/raw/main/assets/samples/emdash-preflight-preview.mp4 — example (credit: jammaru)
More launch videos skills
- Orbit Card: A single feature card orbits a dot sphere on a Blender-made camera move: a 10-second product beat.
- Higgsfield Academy (Higgsfield Open-Source Promo): Higgsfield's 64 s promo for Higgsfield Academy, made almost entirely with Seedance 2.0.
- Seed Audio 1.0 Launch (Higgsfield Open-Source Video): Higgsfield's 106 s launch video for Seed Audio 1.0 (voice cloning, cinematic sound): bold motion design, comedic tone.
- HeyGen's Real Launch Videos as HyperFrames Source: 20 HeyGen product launch videos as editable HyperFrames HTML compositions, each with its storyboard, assets and render command.
- Onetake: Launch films that never cut to the next slide: one continuous camera, measured moves, motion blur, a slideshow oracle.
- Guizang Product Video: Software promos and release-notes videos built from your real product components, with original music and SFX.
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