Media

brand-video - Claude MCP Skill

Generate branded video content with Remotion. Combines brand tokens, voiceover, and screen captures into polished product videos.

SEO Guide: Enhance your AI agent with the brand-video tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to generate branded video content with remotion. combines brand tokens, voiceover, and screen captures ... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟1 stars • 1 forks
📥0 downloads

Documentation

SKILL.md
# /brand-video

Create branded video content using Remotion compositions.

## What This Does

Chains brand tokens, voiceover generation, and Remotion rendering into
branded video content. Consumes `tokens.ts` for consistent visual identity.

## Prerequisites

- `brand.yaml` in project root (run `/brand-init`)
- Compiled tokens (run `/brand-compile`)
- Remotion installed in project or available globally

## Process

### Phase 1: Script + Voiceover

1. Generate or accept video script
2. Run `/voiceover` to generate audio with ElevenLabs
3. Extract word-level timestamps from ElevenLabs response

### Phase 2: Scene Composition

Import brand tokens into Remotion compositions:

```typescript
import { brand } from "./brand-output/tokens.js";

// Available branded scenes:
// - TitleScene: Brand name + tagline with accent gradient
// - FeatureScene: Feature title + description + screenshot
// - EndCard: CTA with brand colors
// - CaptionOverlay: Synced captions using voiceover timestamps
```

### Phase 3: Assembly

Compose scenes with voiceover sync:
1. TitleScene (2-3s)
2. FeatureScene[] (per feature, synced to voiceover)
3. Screen capture segments (if demo)
4. EndCard (3s)

### Phase 4: Render

```bash
npx remotion render src/video/BrandVideo.tsx brand-video.mp4 \
  --props '{"brandTokens": "./brand-output/tokens.ts", "voiceover": "./voiceover.mp3"}'
```

## Video Types

| Type | Scenes | Duration |
|------|--------|----------|
| `demo` | Title → Screen capture → Features → End | 60-90s |
| `feature` | Title → Feature deep-dive → End | 30-45s |
| `launch` | Title → Problem → Solution → Features → CTA | 45-60s |

## Scene Templates

Templates live in the project's Remotion source and import `tokens.ts`:
- Branded title cards with primary color gradient
- Feature callouts with accent highlights
- Caption overlays with brand typography
- End cards with CTA and brand logo

## Related Skills

- `/brand-compile` — Compile tokens (prerequisite)
- `/voiceover` — Generate voiceover audio
- `/demo-video` — Legacy demo video (enhanced by brand-video)
- `/ai-video-generation` — AI-native video (Veo 3.1, Seedance, OmniHuman for avatars/lipsync) when React-based composition isn't needed
- `/remotion-render` — Cloud render Remotion components via inference.sh
- `/remotion-best-practices` — Remotion component structure, timing, and sequence patterns

Signals

Avg rating0.0
Reviews0
Favorites0

Information

Repository
phrazzld/claude-config
Author
phrazzld
Last Sync
3/2/2026
Repo Updated
3/1/2026
Created
2/17/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

Related Skills

firecrawl-build-search

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.

35092

firecrawl-build-onboarding

Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.

35092

firecrawl-build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.

35092

firecrawl-build-interact

Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.

35092

Related Guides