Skip to main content
ClaudeWave
EN, English
Skill1.1k repo starsupdated 19d ago

walkthrough-video

# Walkthrough Video Generator This Claude Code skill generates professional MP4 walkthrough videos from app screenshots or live websites using Remotion. It combines screenshots into polished compositions with smooth transitions (fade, slide, wipe), zoom effects on UI areas, text overlays for titles and descriptions, progress indicators, and optional voiceover narration. Users provide existing screenshots, capture them from a running app via Playwright, or supply a live URL for automatic capture. The skill creates a screens.json manifest defining each frame's duration, transitions, and zoom targets, then orchestrates these into a Remotion video composition. Output videos work for product demos, feature showcases, onboarding documentation, or marketing materials.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/jezweb/claude-skills /tmp/walkthrough-video && cp -r /tmp/walkthrough-video/plugins/frontend/skills/walkthrough-video ~/.claude/skills/walkthrough-video
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Walkthrough Video Generator

Create professional walkthrough videos from app screenshots or live sites using Remotion. Produces smooth, polished MP4 videos with transitions, zoom effects, and text overlays.

## Overview

This skill takes a set of screenshots (or captures them from a running app) and orchestrates them into a Remotion video composition with:

- **Smooth transitions** between screens (fade, slide, wipe)
- **Zoom effects** to highlight specific UI areas
- **Text overlays** with titles, descriptions, and callouts
- **Progress indicators** showing position in the walkthrough
- **Optional voiceover** narration track

## Prerequisites

- **Node.js** 18+ installed
- **Screenshots** of the app (or a running app to screenshot)
- No Remotion experience needed — the skill generates all code

## Workflow

### Step 1: Gather Screenshots

Choose one approach:

#### Option A: From Existing Screenshots

If the user already has screenshots (e.g. from `design-loop` or `product-showcase`):

```
Read screenshots from:
- .design/screenshots/
- .jez/screenshots/
- User-specified directory
```

Sort them in walkthrough order (alphabetically by filename, or as user specifies).

#### Option B: Capture from Running App

If the app is running locally:

1. Start Playwright CLI session
2. Navigate through each screen in sequence
3. Screenshot at consistent dimensions (1280x720 recommended for video)
4. Save to `video/public/screens/`

```bash
playwright-cli -s=walkthrough open http://localhost:3000
playwright-cli -s=walkthrough resize 1280 720
playwright-cli -s=walkthrough screenshot --filename=video/public/screens/01-home.png
# Navigate to next page...
playwright-cli -s=walkthrough screenshot --filename=video/public/screens/02-dashboard.png
```

#### Option C: From Live URL

Same as Option B but with a public URL. Screenshot each key page.

### Step 2: Create Screen Manifest

Build a `screens.json` describing the walkthrough:

```json
{
  "projectName": "My App Walkthrough",
  "fps": 30,
  "width": 1280,
  "height": 720,
  "screens": [
    {
      "id": "home",
      "title": "Welcome to MyApp",
      "description": "The landing page introduces the core value proposition",
      "imagePath": "screens/01-home.png",
      "durationSeconds": 4,
      "transition": "fade",
      "zoomTarget": null
    },
    {
      "id": "dashboard",
      "title": "Your Dashboard",
      "description": "See all your projects at a glance",
      "imagePath": "screens/02-dashboard.png",
      "durationSeconds": 5,
      "transition": "slide-left",
      "zoomTarget": { "x": 100, "y": 200, "width": 400, "height": 300, "delay": 2 }
    }
  ]
}
```

| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Unique screen identifier |
| `title` | string | Text overlay title |
| `description` | string | Subtitle or narration text |
| `imagePath` | string | Path relative to `video/public/` |
| `durationSeconds` | number | How long to show this screen |
| `transition` | string | `fade`, `slide-left`, `slide-right`, `slide-up`, `wipe`, `none` |
| `zoomTarget` | object/null | If set, zoom into this region after `delay` seconds |

### Step 3: Scaffold Remotion Project

If no Remotion project exists:

```bash
mkdir -p video
cd video
npm init -y
npm install remotion @remotion/cli @remotion/transitions react react-dom
npm install -D typescript @types/react
```

Create the project structure:

```
video/
├── src/
│   ├── Root.tsx                    # Remotion entry point
│   ├── WalkthroughComposition.tsx  # Main composition
│   ├── components/
│   │   ├── ScreenSlide.tsx         # Individual screen display
│   │   ├── TextOverlay.tsx         # Title/description overlay
│   │   ├── ProgressBar.tsx         # Walkthrough progress indicator
│   │   └── ZoomEffect.tsx          # Zoom into regions
│   └── config.ts                   # Load screens.json, calculate durations
├── public/
│   └── screens/                    # Screenshot assets
│       ├── 01-home.png
│       └── 02-dashboard.png
├── screens.json                    # Screen manifest
├── remotion.config.ts
├── tsconfig.json
└── package.json
```

### Step 4: Generate Remotion Components

Generate each component file. Key patterns:

#### Root.tsx

```tsx
import { Composition } from "remotion";
import { WalkthroughComposition } from "./WalkthroughComposition";
import { screens, totalDurationInFrames, FPS, WIDTH, HEIGHT } from "./config";

export const RemotionRoot = () => (
  <Composition
    id="Walkthrough"
    component={WalkthroughComposition}
    durationInFrames={totalDurationInFrames}
    fps={FPS}
    width={WIDTH}
    height={HEIGHT}
    defaultProps={{ screens }}
  />
);
```

#### ScreenSlide.tsx Pattern

```tsx
import { AbsoluteFill, Img, spring, useCurrentFrame, useVideoConfig } from "remotion";

interface ScreenSlideProps {
  imageSrc: string;
  title: string;
  description: string;
}

export const ScreenSlide: React.FC<ScreenSlideProps> = ({ imageSrc, title, description }) => {
  const frame = useCurrentFrame();
  const { fps } = useVideoConfig();

  // Fade in
  const opacity = spring({ frame, fps, config: { damping: 20 } });

  // Subtle zoom (Ken Burns effect)
  const scale = 1 + frame * 0.0002;

  return (
    <AbsoluteFill style={{ backgroundColor: "#000" }}>
      <Img
        src={imageSrc}
        style={{
          width: "100%",
          height: "100%",
          objectFit: "contain",
          opacity,
          transform: `scale(${scale})`,
        }}
      />
      {/* Text overlay at bottom */}
      <div style={{
        position: "absolute",
        bottom: 40,
        left: 40,
        right: 40,
        opacity: spring({ frame: frame - 15, fps, config: { damping: 20 } }),
      }}>
        <h2 style={{ color: "#fff", fontSize: 32, fontWeight: 700, textShadow: "0 2px 8px rgba(0,0,0,0.8)" }}>
          {title}
        </h2>
        <p style={{ color: "#ccc", fontSize: 18, textShadow: "0 1px 4px rgba(0,0,0,0.8)" }}>
          {de
ai-image-generatorSkill

Generate AI images using Gemini or GPT APIs directly. Covers model selection (Gemini for scenes; GPT Image 2 for text rendering, batch variations, multi-reference compositing; GPT Image 1.5 for transparent icons), the 5-part prompting framework, API calling patterns, multi-turn editing, and quality assurance. Produces photorealistic scenes, icons, illustrations, OG images, posters, infographics, and product shots. Use when building websites that need images, creating marketing assets, or generating visual content. Triggers: 'generate image', 'ai image', 'create hero image', 'make an icon', 'generate illustration', 'create og image', 'poster', 'infographic', 'image variations', 'gpt-image-2', 'ai art', 'image generation'.

app-docsSkill

Generate complete user documentation for a web app with screenshots. Browses the app via browser automation, screenshots every screen, and produces a structured user guide with step-by-step instructions, annotated screenshots, workflow diagrams, and reference tables. Supports quick (key screens), standard (all pages), thorough (every state and flow), and exhaustive (publishable documentation suite). Triggers: 'document the app', 'user guide', 'app documentation', 'screenshot docs', 'generate user docs', 'help docs', 'how-to guide', 'write the docs'.

aussie-business-englishSkill

Australian business English for professional writing — warm, direct, EN-AU spelling (colour, organise, centre), no filler words. Use whenever the user is writing for an Australian audience: emails, chat messages, proposals, client communications, blog posts, web copy, or any business writing. Apply to drafting, editing, and tone-checking professional text.

award-applicationSkill

Write compelling award submissions, grant applications, and competition entries. Maps achievements to selection criteria using evidence-based narratives. Use whenever the user is applying for a business award (Telstra, chamber of commerce, industry awards), a grant, a competition, or any submission demonstrating merit against defined criteria.

brains-trustSkill

Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs. Supports single opinion, multi-model consensus, and devil's advocate patterns. Use whenever the user says 'brains trust', 'second opinion', 'ask gemini', 'ask gpt', 'peer review', 'consult another model', 'challenge this', or 'devil's advocate'.

cloudflare-apiSkill

Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide resource audits. Produces curl commands or scripts. Triggers: 'cloudflare api', 'bulk dns', 'custom hostname', 'email routing', 'cache purge', 'waf rule', 'd1 query', 'r2 bucket', 'kv bulk', 'vectorize query', 'audit resources', 'fleet operation'.

cloudflare-worker-builderSkill

Scaffold and deploy Cloudflare Workers with Hono routing, Vite plugin, and Static Assets. Describe project, scaffold structure, configure bindings, deploy. Use whenever the user wants to create a Worker project, set up Hono on Cloudflare, configure D1 / R2 / KV / Queues bindings, or troubleshoot Worker export syntax, API route conflicts, HMR issues, or deployment failures.

codex-reviewSkill

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'independent code review', 'what does codex think', 'get codex to review'.