New to Claude Skills? Learn how to install them →

alirezarezvani on GitHub

Demo Video

Free

Create polished demo videos from screenshots or descriptions.

Get this skill

Free · Opens the source repo

What Demo Video does

The Demo Video skill enables users to produce high-quality demo videos, product walkthroughs, and marketing content by orchestrating various media components. By leveraging tools such as Playwright for automated screenshots, Edge TTS for narration, and FFmpeg for video compositing, this skill transforms static screenshots and textual scene descriptions into engaging video presentations. It emphasizes a structured storytelling approach, ensuring that each video has a clear narrative arc and visual hierarchy, which is essential for capturing audience attention.

Users can choose between a fully automated workflow, where all necessary tools are available, or a manual process if some components are not accessible. In the automated mode, the skill handles everything from rendering HTML scenes to generating audio narration and composing the final video. Alternatively, if the required tools are unavailable, it provides HTML files and instructions for users to create the video manually, ensuring flexibility in various environments.

This skill is particularly useful for product managers, marketers, and developers who need to showcase features or demonstrate applications visually. It allows for the creation of various video formats, including animated presentations and GIFs, making it a versatile tool for different marketing and educational needs. The skill also includes a design system reference, ensuring that users can maintain consistency in visual style and pacing across their videos.

In summary, the Demo Video skill is a comprehensive solution for anyone looking to produce polished video content efficiently, with a focus on storytelling and viewer engagement.

When to use it

Use this skill when you need to create a demo video, product walkthrough, or marketing video quickly and effectively.

When not to use it

This skill may not be suitable for users looking for highly customized video editing features or those needing advanced animation capabilities beyond the provided templates.

What you can build with it

Creating a Product Demo

A product manager wants to showcase new features of an application. They use the skill to turn screenshots into a polished demo video.

Marketing Video for a Launch

A marketing team needs a quick promotional video for a product launch. They utilize the skill to create an engaging teaser video.

Animated Presentation for a Webinar

A presenter wants to create an animated presentation for an upcoming webinar. They leverage the skill to transform scene descriptions into a visually appealing video.

How to install Demo Video

View source

1. Install with the skills CLI

npx skills add alirezarezvani/claude-skills/demo-video --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by alirezarezvani

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

Frequently asked questions about Demo Video

Similar skills