Agent Skills

remotion-best-practices

videoremotion-dev551K installs

Router for all Remotion skills

Install

npx skills add https://github.com/remotion-dev/skills --skill remotion-best-practices
SKILL.md

Preserve user changes

Users may make edits in the code outside of the conversation.

If you detect a surprising change made in the meanwhile, don't overwrite it, assume it was intentional or ask for confirmation.

Creating a video

If the user asks to make, create, or build a new video or composition, load Create a new Remotion video, whether or not a Remotion project already exists.

New project setup

If no Remotion project currently exists, load Create a new Remotion project

React Markup Best Practices

If you are writing Remotion React Markup, load Remotion Markup Best Practices

Maps

For static maps, animated routes and markers, geographic explainers, Mapbox, MapLibre, MapTiler, GeoJSON, or 3D geographic flyovers, load Remotion Maps.

Multimedia

For achieving multimedia tasks in the browser, such as trimming, cropping videos, or getting metadata from them, load Remotion Multimedia

Improving Interactivity

By structuring the Remotion markup well, we can allow users to interactively change things in the Studio and write back to code. If relevant: Interactivity Best Practices

Open the preview

If the user asks to "make" a video, "create" a video, etc. Don't render the video by default unless they are very explicit. They want to instead see an interactive preview. Start the preview server after building the composition:

If you have an in-app browser

If you are e.g. Codex, GitHub Copilot or any other desktop agent with an in-app browser, run:

npx remotion studio --no-open

This will start a long-running process and print the server URL for the preview.
If the server is already started, it will print the URL. You can visit a specific composition by navigating to /[composition-id], for example http://localhost:3000/MapAnimation.

:::note The Studio supports WebMCP tools. :::

If you do not have an in-app browser

This will open the Studio in the browser or-refocus it if it is already open.

npx remotion studio

More options

To launch a project in Remotion Studio, open its exact local URL, or configure Studio CLI flags, load Remotion Studio.

Render the video

Only render if the user is very explicit in asking for it.
E.g. "Render the video", "Export", "Give me the MP4".

The preview also has a more intuitive rendering interface, so consider using it instead of the command line for rendering.

npx remotion render

For more options, see Rendering.

For advanced rendering beyond simple npx remotion render, see: Rendering Best Practices

Captions

When working with Captions, load Remotion Captions.

Creating a SaaS, automation or application

Use the Remotion SaaS skill for knowledge about Remotion-powered SaaS apps, such as <Player>, rendering on Lambda, Vercel, Cloudflare, via Express.js, client-side rendering, or for finding the right SaaS template.

Looking up Remotion APIs and documentation

To find and read current Remotion documentation, load Remotion Docs.

Upgrading

To upgrade Remotion, related packages, compatible Mediabunny packages, and installed Remotion Agent Skills, load Remotion Upgrade.

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