Agent Skills

remotion-video-toolkit

Complete toolkit for programmatic video creation with Remotion + React. Covers animations, timing, rendering (CLI/Node.js/Lambda/Cloud Run), captions, 3D, charts, text effects, transitions, and media handling. Use when writing Remotion code, building video generation pipelines, or creating data-driven video templates.

Install

npx skills add https://github.com/shreefentsar/remotion-video-toolkit --skill remotion-video-toolkit
SKILL.md

Remotion Video Toolkit

Write React components, get real MP4 videos. This skill teaches your AI agent how to build with Remotion — from a first animation to a production rendering pipeline.

29 rules. Every major Remotion feature covered.


What you can build with this

Personalized video at scale Feed user data as JSON props, render a unique video per user. Think Spotify Wrapped, GitHub Unwrapped, onboarding walkthroughs — one template, thousands of outputs.

Automated social media clips Pull live data (stats, leaderboards, product metrics) and render daily or weekly video posts without anyone touching a timeline editor.

Dynamic ads and marketing videos Swap in customer name, product image, pricing. Same template, infinite variations. Render server-side via API or Lambda.

Animated data visualizations Turn dashboards and KPI reports into shareable video clips with animated charts and transitions.

TikTok and Reels captions Transcribe audio, display word-by-word highlighted subtitles, export ready for upload.

Product showcase videos Auto-generate from your database — images, specs, pricing — straight to MP4.

Educational and explainer content Animated course materials, certificate videos, step-by-step walkthroughs — all driven by code.

Video generation as a service Expose rendering as an HTTP endpoint. Your app sends JSON, gets back a video file.


Requirements

  • Node.js 18+
  • React 18+ (Remotion renders React components frame-by-frame)
  • Remotion — scaffold with npx create-video@latest
  • FFmpeg — ships with @remotion/renderer, no separate install needed
  • For serverless rendering: AWS account (Lambda) or GCP account (Cloud Run)

What's inside

Core

Rule Description
Compositions Define videos, stills, folders, default props, dynamic metadata
Rendering CLI, Node.js API, AWS Lambda, Cloud Run, Express server patterns
Calculate metadata Set duration, dimensions, and props dynamically at render time

Animation and timing

Rule Description
Animations Fade, scale, rotate, slide
Timing Interpolation curves, easing, spring physics
Sequencing Delay, chain, and orchestrate scenes
Transitions Scene-to-scene transitions
Trimming Cut the start or end of any animation

Text and typography

Rule Description
Text animations Typewriter, word highlight, reveal effects
Fonts Google Fonts and local font loading
Measuring text Fit text to containers, detect overflow

Media

Rule Description
Videos Embed, trim, speed, volume, loop, pitch shift
Audio Import, trim, fade, volume and speed control
Images The Img component
GIFs Timeline-synced GIF playback
Assets Importing any media into compositions
Decode check Validate browser compatibility

Captions and subtitles

Rule Description
Transcribe captions Audio to captions via Whisper, Deepgram, or AssemblyAI
Display captions TikTok-style word-by-word highlighting
Import SRT Load existing .srt files

Data visualization

Rule Description
Charts Animated bar charts, line graphs, data-driven visuals

Advanced

Rule Description
3D content Three.js and React Three Fiber
Lottie After Effects animations via Lottie
TailwindCSS Style compositions with Tailwind
DOM measurement Measure element dimensions at render time

Media utilities

Rule Description
Video duration Get length in seconds
Video dimensions Get width and height
Audio duration Get audio length
Extract frames Pull frames at specific timestamps

Quick start

# Scaffold a project
npx create-video@latest my-video

# Preview in browser
cd my-video && npm start

# Render to MP4
npx remotion render src/index.ts MyComposition out/video.mp4

# Pass dynamic data
npx remotion render src/index.ts MyComposition out.mp4 --props '{"title": "Hello"}'

Contribute

Source: github.com/shreefentsar/remotion-video-toolkit

Missing something? Found a better approach? Open a PR — new rules, improved examples, bug fixes all welcome.

Built by Zone 99

Related skills

video-editgenmedia-labs715KEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets shai-video-generationgenmedia-labs714KGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 qualitai-musicgenmedia-labs714KGenerate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model fimage-to-videogenmedia-labs713KAnimate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterat

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers