Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
alirezarezvani avatar

Demo Video

  • 618 installs
  • 23.5k repo stars
  • Updated July 17, 2026
  • alirezarezvani/claude-skills

demo-video is a Claude Code skill that maintains a scene design system for AI-generated demo and explainer videos so developers and product teams keep consistent visual language, timing, and voice across releases.

About

demo-video is a design-system skill from alirezarezvani/claude-skills that documents how to structure AI-generated demo and explainer videos with repeatable scene rules. It defines a six-color semantic palette such as #c5d5ff for trust titles, #7c6af5 for premium subtitles, #4ade80 for success states, and #0d0e12 for dark backgrounds, plus animation timing bands from 0.5-0.8s element entrances to 1.0-2.0s post-animation holds. Typography guidance sets title sizes between 48-72px with prescribed cubic-bezier easing for entrances and 0.3-0.5s crossfade scene transitions. Developers reach for demo-video when multiple generated walkthroughs must look like one product brand instead of ad hoc clips with mismatched pacing or colors.

  • Complete color language with 6 semantic tokens mapped to exact hex values and usage rules
  • Precise animation timing table with cubic-bezier curves and gap recommendations
  • Typography scale and Inter font rules for titles, subtitles, and bullets
  • Fixed 1920x1080 HTML scene layout with percentage-based zones
  • 4 edge-tts voice profiles with clear best-use mapping

Demo Video by the numbers

  • 618 all-time installs (skills.sh)
  • Ranked #1,543 of 16,565 AI & Agent Building skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Jul 31, 2026 (Skillselion catalog sync)
npx skills add https://github.com/alirezarezvani/claude-skills --skill demo-video

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs618
repo stars23.5k
Security audit3 / 3 scanners passed
Last updatedJuly 17, 2026
Repositoryalirezarezvani/claude-skills

How do you keep AI demo videos visually consistent?

Maintain consistent visual language, timing, and voice across all AI-generated demo and explainer videos.

Who is it for?

Product marketers and developers producing recurring AI-generated demo or explainer videos who need a shared visual and timing language.

Skip if: Teams only editing raw screen recordings without generative scenes, or projects with no video marketing deliverables.

When should I use this skill?

A new AI demo or explainer video needs colors, animation timing, typography, or voice pacing aligned with prior product clips.

What you get

A reusable scene design spec covering color semantics, animation durations, typography scales, and voice pacing for branded explainer videos.

  • Scene color and typography spec
  • Animation timing reference
  • Consistent demo video creative brief

By the numbers

  • Documents a 6-color semantic palette with hex codes
  • Specifies title typography between 48-72px

Files

SKILL.mdMarkdownGitHub ↗

Demo Video

You are a video producer. Not a slideshow maker. Every frame has a job. Every second earns the next.

Overview

Create polished demo videos by orchestrating browser rendering, text-to-speech, and video compositing. Think like a video producer — story arc, pacing, emotion, visual hierarchy. Turns screenshots and scene descriptions into shareable product demos.

When to Use This Skill

  • User asks to create a demo video, product walkthrough, or feature showcase
  • User wants an animated presentation, marketing video, or product teaser
  • User wants to turn screenshots or UI captures into a polished video or GIF
  • User says "make a video", "create a demo", "record a demo", "promo video"

Core Workflow

1. Choose a rendering mode

Before starting, verify available tools:

  • playwright MCP available? — needed for automated screenshots. Fallback: ask user to screenshot the HTML files manually.
  • edge-tts available? — needed for narration audio. Fallback: output narration text files for user to record or use any TTS tool.
  • ffmpeg available? — needed for compositing. Fallback: output individual scene images + audio files with manual ffmpeg commands the user can run.

If none are available, produce HTML scene files + scenes.json manifest + narration scripts. The user can composite manually or use any video editor.

ModeHowWhen
MCP OrchestrationHTML → playwright screenshots → edge-tts audio → ffmpeg compositeUse when playwright + edge-tts + ffmpeg MCPs are all connected
ManualWrite HTML scene files, provide ffmpeg commands for user to runUse when MCPs are not available

2. Pick a story structure

The Classic Demo (30-60s): Hook (3s) -> Problem (5s) -> Magic Moment (5s) -> Proof (15s) -> Social Proof (4s) -> Invite (4s)

The Problem-Solution (20-40s): Before (6s) -> After (6s) -> How (10s) -> CTA (4s)

The 15-Second Teaser: Hook (2s) -> Demo (8s) -> Logo (3s) -> Tagline (2s)

3. Design scenes

If no screenshots are provided:

  • For CLI/terminal tools: generate HTML scenes with terminal-style dark background, monospace font, and animated typing effect
  • For conceptual demos: use text-heavy scenes with the color language and typography system
  • Ask the user for screenshots only if the product is visual and descriptions are insufficient

Every scene has exactly ONE primary focus:

  • Title scenes: product name
  • Problem scenes: the pain (red, chaotic)
  • Solution scenes: the result (green, spacious)
  • Feature scenes: the highlighted screenshot region
  • End scenes: URL / CTA button

4. Write narration

  • One idea per scene. If you need "and" you need two scenes.
  • Lead with the verb. "Organize your tabs" not "Tab organization is provided."
  • No jargon. "Your tabs organize themselves" not "AI-powered tab categorization."
  • Use contrast. "24 tabs. One click. 5 groups."

Output Artifacts

For each video, produce these files in a demo-output/ directory:

1. scenes/ — one HTML file per scene (1920x1080 viewport) 2. narration/ — one .txt file per scene (for edge-tts input) 3. scenes.json — manifest listing scenes in order with durations and narration text 4. build.sh — shell script that runs the full pipeline:

  • playwright screenshot each HTML scene → frames/
  • edge-tts each narration file → audio/
  • ffmpeg concat with crossfade transitions → output.mp4

If MCPs are unavailable, still produce items 1-3. Include the ffmpeg commands in build.sh for the user to run manually.

Scene Design System

See references/scene-design-system.md for the full design system: color language, animation timing, typography, HTML layout, voice options, and pacing guide.

Quality Checklist

  • [ ] Video has audio stream
  • [ ] Resolution is 1920x1080
  • [ ] No black frames between scenes
  • [ ] First 3 seconds grab attention
  • [ ] Every scene has one focus point
  • [ ] End card has URL and CTA

Anti-Patterns

Anti-patternFix
Slideshow pacing — every scene same duration, no rhythmVary durations: hooks 3s, proof 8s, CTA 4s
Wall of text on screenMove info to narration, simplify visuals
Generic narration — "This feature lets you..."Use specific numbers and concrete verbs
No story arc — just listing featuresUse problem -> solution -> proof structure
Raw screenshotsAlways add rounded corners, shadows, dark background
Using `ease` or `linear` animationsUse spring curve: cubic-bezier(0.16, 1, 0.3, 1)

Cross-References

  • Related: engineering/browser-automation — for playwright-based browser workflows
  • See also: framecraft — open-source scene rendering pipeline

Related skills

How it compares

Use demo-video for repeatable scene styling rules, not for video encoding pipelines or hosting setup.

FAQ

What colors does demo-video define?

demo-video assigns six hex roles: #c5d5ff trust titles, #7c6af5 premium subtitles, #4ade80 success after states, #f28b82 problem before states, #fbbf24 energy callouts, and #0d0e12 dark backgrounds.

What animation timing does demo-video recommend?

demo-video recommends 0.5-0.8s element entrances with cubic-bezier(0.16, 1, 0.3, 1), 0.2-0.4s gaps between elements, 0.3-0.5s crossfade scene transitions, and a 1.0-2.0s hold after the last animation.

Is Demo Video safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.