--- title: "cinetic: directed launch films from code — AI video generator workflow for launch videos" description: "Makes the agent direct a short film: three concepts first, a plan drawn from 273 measured techniques, one beat grid for picture and sound, then pixel and audio- Install in Claude Code, Codex and Grok with one command." url: https://varg.ai/how-to/skills/cinetic-launch-films updated: 2026-11-03 --- # cinetic: directed launch films from code — 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="` 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 `.md` to its path. Before generating anything, show the person the options on the how-to page. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install ` with no key, every varg model after `vargai login`. Makes the agent direct a short film: three concepts first, a plan drawn from 273 measured techniques, one beat grid for picture and sound, then pixel and audio- - **Type:** [Workflow](https://varg.ai/how-to/workflows.md) · [Launch videos](https://varg.ai/how-to/browse/skills/launch.md) - **Slug:** `cinetic-launch-films` - **Status:** live - **Publisher:** Leon (Leonxlnx) (community) - **License:** MIT - **Source:** https://github.com/Leonxlnx/cinetic - **Works in:** Claude Code, Codex - **Requires:** Node, ffmpeg, Remotion or HyperFrames - **Adoption:** 967 GitHub stars (GitHub, 2026-11-02) ## What it does pick.py draws a film plan weighted for format and energy so two films do not share the same moves; look comes from three personality words; copy arrives in fragments; timeline.ts drives picture, soundtrack and QA; true motion blur, BT.709, contact sheets, critic passes and a linter of hard bans against the generated look. Remotion by default or HyperFrames. Sound from the earshot kit (already in catalog). ## Use when - launch teasers that should not look templated - brand films with measured sound sync ## Not for - quick social cuts - talking-head edits ## Install - Claude Code: `npx skills add Leonxlnx/cinetic` - Codex: `npx skills add Leonxlnx/cinetic` - Any agent, with the vargai CLI: `vargai install cinetic-launch-films` **Models it drives:** remotion, hyperframes ## Example output https://raw.githubusercontent.com/Leonxlnx/cinetic/media/quire-streaks-vertical.mp4 — A vertical launch teaser the skill rendered (repo media branch) (credit: Leon (Leonxlnx) (README), https://github.com/Leonxlnx/cinetic) ## More launch videos skills - [Orbit Card](https://varg.ai/how-to/skills/hyperframes-orbit-card.md): 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)](https://varg.ai/how-to/skills/higgsfield-open-higgsfield-academy.md): Higgsfield's 64 s promo for Higgsfield Academy, made almost entirely with Seedance 2.0. - [Seed Audio 1.0 Launch (Higgsfield Open-Source Video)](https://varg.ai/how-to/skills/higgsfield-open-seed-audio-launch.md): 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](https://varg.ai/how-to/skills/heygen-hyperframes-launch-videos-source.md): 20 HeyGen product launch videos as editable HyperFrames HTML compositions, each with its storyboard, assets and render command. - [Check a render against its reference by Refs](https://varg.ai/how-to/skills/refs-check-render.md): Score your render against the reference film: cut timing, brightness, motion, loudness, format, frame-exact fixes. - [Launch video formulas by Refs](https://varg.ai/how-to/skills/refs-formulas.md): 28 video formats distilled from 132 measured films: the shape in timed beats, the constants, a template prompt. ## 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`), then `vargai login` and 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 -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