Agent Skills

remotion-create

videoremotion-dev105K installs

Create a new Remotion video

Install

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

These are instructions for making a new Remotion project and composition.
If this is not the next task, see Remotion Best Practices

Scaffold a project

If a project already exists, skip this. Ensure Node.js and Git is installed, and the current folder is appropriate for starting a new project.

Inspect the current folder, including hidden files, before choosing where to scaffold.

Empty folder

If it is empty, or contains only disposable operating-system metadata such as .DS_Store, create the project directly in the current folder. Remove only those disposable metadata files first, since create-video rejects non-empty folders. Do not treat all hidden files as disposable: files such as .env and directories such as .git are meaningful contents.

Scaffold in existing folder:

npx create-video@latest --yes --blank --no-tailwind .
npm i

Non-empty folder

If the current folder contains meaningful contents and no project already exists, scaffold into a new subfolder. Replace my-video with a suitable project name.

npx create-video@latest --yes --blank --no-tailwind my-video
cd my-video
npm i

Designing a video

Keep the scaffold and add React Markup. Follow Remotion React Markup Best Practices and Video Layout Rules for video-first layout and text sizing guidance.

Before writing the root that registers <Composition> or <Still> elements, follow Compositions and stills.

Is this a timeline of clips?

If the video arranges multiple video or audio clips on a timeline, follow Video editing before writing the timeline. Give every clip that should be edited independently its own authored JSX node.

Is this a multi-scene video?

If this is a video with multiple subsequent scenes, follow guidance at Multi-scene videos.

Interactivity Best Practices

By structuring the React Markup following Remotion Interactivity Best Practices, you allow the user to make edits in the Studio which write back to code.

TailwindCSS

If Tailwind is requested, see tailwind.md for using TailwindCSS in Remotion.

Follow-up

The video creation process has finished. For follow-up prompts, use Remotion Best Practices

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