Skip to content
Marketing
Skill

/launch-video

Use when the user wants a full launch video, hero video, or 20–60s product film combining product proof, brand, narration, music, and authored motion.

From plugin
marketing-studio
25515 skills

Claude Code

$ npx -y skills add ucsandman/marketing-studio --skill launch-video --agent claude-code

SKILL.md

launch-video.SKILL.md
name: launch-video
description: Use when the user wants a full launch video, hero video, or 20–60s product film combining product proof, brand, narration, music, and authored motion.

Launch Video

**REQUIRED BACKGROUND:** marketing-studio skill; also read `${CLAUDE_SKILL_DIR}/../../docs/playbook/remotion.md`, `${CLAUDE_SKILL_DIR}/../../docs/playbook/audio.md`, and `${CLAUDE_SKILL_DIR}/../../docs/playbook/capture.md`. Work in `${CLAUDE_SKILL_DIR}/../..`.

Produces a scored film and its direction, shot plan, stage approvals, render evidence, and review record inside `<product>/marketing/assets/<brand>/`. Read [`docs/production-quality.md`](../../docs/production-quality.md) before production work.

**A film is not done without audio, and audio means a voice explaining the product.** Scoring is not optional and `node scripts/check-audio.mjs <brand> --project <product>` must exit 0 before the word "done". Two postflop cuts shipped silent on 2026-09-01; that is the reason this line exists.

Route

Choose the route from the concept and product proof. Use a bespoke composition under `studio/src/films/<brand>/` when the film needs a product-specific visual world or shot system. Use the directed `LaunchVideo` composition when its authored shot plan can carry the idea without reverting to the legacy five-act deck. A shot may use a real capture, native rebuilt UI, 2D, 3D, or a hybrid. Rebuilding UI is useful for controlled actions; it is not a universal requirement.

Recipe

1. Set `<product>` explicitly with `--project`. Do not create any generated product input or output in engine-local `out/`. 2. Explore distinct directions, choose one with a specific reason, and record its visual metaphor, sound intent, references with provenance, and reviewable style frame in `direction.json`. The preset is only a starting grammar. 3. Write the shot plan before full production. Each shot needs a purpose, duration, scale, camera cadence, transition intent, readable-copy limits, source/reference, and audio beat. Plan narration with the edit; every numeric claim traces to a brief proof point. 4. Build an audio-bearing animatic with scratch voice and music. A named non-author reviewer approves both style frame and animatic, bound to their hashes. A weak visual argument stops here, before finish work. 5. Build the chosen route. Directed LaunchVideo consumes `direction` and authored `shots`; a bespoke film owns its shot components and timeline. Match cuts may overlap, hard cut, wipe, dissolve, or continue motion as the relationship demands. Static end frames are one option, not a rule. 6. Render inexpensive shot proofs and a versioned preview. Inspect the product action at delivery size, the start/middle/end of every shot, and the frames around every cut. Fix the written defect list, then make the full-resolution render once. 7. Build product-owned narration, music, and SFX inputs and score the silent lock with `node scripts/score-film.mjs <brand> <film.mp4> --project <product>`. It refuses overlapping narration and verifies the delivered master. Music-only requires the explicit recorded exception; never imply narration that is absent. 8. Generate hash-bound evidence from the exact final render: `node scripts/contact-sheet.mjs <brand> --project <product> --plan <production-plan.json> --render <final.mp4>`. 9. In Mission Control, a named director, operator, or independent reviewer watches the complete scored cut, records defects and the “would I share this?” verdict. Then run `node scripts/judge-production.mjs <brand> --project <product> --plan <production-plan.json> --render <final.mp4> --strict`. 10. Run the existing audio, palette, studio test/lint, and smoke gates. They prove properties and runtime, not taste. Only the scored, strict-PASS lock proceeds to the production matrix and post kit.

Read more
@ucsandman
Ships withmarketing-studio

An agent-driven local marketing studio. The bundled Claude Code plugin adds /marketing and /launch: the agent onboards your brand, films your app, writes the asset suite and review evidence into that product repo, then prepares guarded distribution to X,

Stars on GitHub

Momentum

stars in total
255
Star history of ucsandman/marketing-studio on GitHub, a chart by star-history.com

Other skills on marketing-studio.

announce

announce

Use when a product or feature is ready to go public — after shipping, when the user says "announce it", "go live", "tell people…

audio-track

audio-track

Use when the user wants music, voiceover, narration, or a soundtrack added to a video asset, OR wants standalone generated audio…

de-vibe

de-vibe

Audit and fix the tells that software was vibe-coded / AI-generated, then give it a small distinctive identity, so it ships…

launch

launch

Take a developed project end-to-end through launch — domain, hosting, payments, email infra, algorithm-researched copy, and…

logo-reveal

logo-reveal

Use when the user wants a logo reveal / logo animation / brand intro video for any product (e.g. "/logo-reveal", "make a logo…

More skills from other plugins.

seo

seo

Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability,…

@agricidaniel@agricidanielInstall Skill
brag

brag

Turn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone says "/brag",…

brag2w21k
@latent-spaces@latent-spacesInstall Skill
geo-audit

geo-audit

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit…

Questions about launch-video.

Which coding agents can use launch-video?
launch-video installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.