video-production_skill

This skill generates programmable Remotion videos from text prompts, orchestrating scenes, assets, and validation gates for brand-consistent content.
  • Shell

24

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill supercent-io/skills-template --skill video-production

  • SKILL.md6.8 KB

Overview

This skill produces programmable videos with Remotion by combining scene planning, asset orchestration, and validation gates to deliver automated, brand-consistent content. It guides you from a concise video spec through scene outlines, asset checks, Remotion composition code, and QA render steps. The result is repeatable production workflows for marketing, onboarding, and social formats.

How this skill works

Define a video spec (audience, goal, duration, aspect ratio, tone, voice) and create a scene plan that maps visuals, audio cues, text, and transitions. Prepare and validate assets (logos, screenshots, audio, fonts) using a checklist, then implement scenes as Remotion compositions and components. Run preview renders for QA, iterate on timing and audio sync, and perform final renders once validation gates pass.

When to use it

  • Automating production of short marketing or product videos from text prompts
  • Scaling brand-consistent videos across campaigns and platforms
  • Generating programmatic content that combines narration, visuals, and animations
  • Creating mobile-first vertical videos (9:16) or standard 16:9 social content
  • Building reusable templates for frequent updates (feature highlights, CTAs)

Best practices

  • Keep scenes short (typically 5–10 seconds) to maintain pacing and clarity
  • Define typography scale and safe zones up front for cross-format consistency
  • Normalize audio levels and align narration cues to frame-based timing
  • Store reusable compositions and components as templates for fast iteration
  • Compress heavy assets and simplify effects to improve render reliability

Example use cases

  • 60s product intro: 6 scenes (hook, problem, solution, features, proof, CTA) in 16:9
  • 45s onboarding walkthrough using annotated screenshots in 9:16 for mobile
  • Automated feature update videos where copy and screenshots are injected programmatically
  • Social ad variations: same scenes with swapped text, voice, or B-roll assets

FAQ

Use SVG or high-resolution PNG for logos, normalized screenshots, MP3/WAV for audio, and web/local font files (woff2/ttf).

How do I prevent audio and visual drift?

Align narration to frame timings, use frame-based timestamps in Remotion, and preview at target FPS to verify sync.

What if renders fail or are slow?

Reduce asset sizes, simplify animations, and run low-quality preview renders before final output to catch issues early.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational