cinematic-slides
Create cinematic HTML presentations with AI video backgrounds, deployed to GitHub Pages. Use for: slides, presentation, deck, cinematic slides, video presentation, animated slides, live presentation.
What this skill does
# Cinematic Slides
End-to-end pipeline: idea -> structured slides -> HTML -> AI images -> AI videos -> GitHub Pages.
Produces a single-file HTML presentation with looping AI video backgrounds per slide, keyboard navigation, and fullscreen 1920x1080 layout.
## Pipeline
### Step 1: Content Architecture
Use **presentation-architect** skill to create the slide plan:
- Get topic, audience, tone from user
- Output: structured markdown with slide-by-slide content, headlines, descriptions, visual direction
- Each slide needs a **visual prompt** describing the background mood/scene
### Step 2: Build HTML Presentation
Create a single `index.html` (or `slides.html`) with:
**Layout specs:**
- 1920x1080 fixed slides, centered with CSS transform scaling
- `position: fixed` slides, toggle `.active` class
- Keyboard navigation (left/right arrows + click)
- Slide counter at bottom
- RTL direction for Hebrew content
- Google Fonts (Heebo for Hebrew, or as needed)
**Per-slide CSS pattern:**
```css
#slideN {
background: [gradient-overlay], url('presentation/slide-N.jpg') center/cover no-repeat;
}
```
**Video background CSS (global):**
```css
.slide-video {
position: absolute;
top: 0; left: 0;
width: 100%; height: 100%;
object-fit: cover;
z-index: 0;
opacity: 0.25;
}
.slide > *:not(.slide-video) {
position: relative;
z-index: 1;
}
```
**Per-slide video element:**
```html
<video class="slide-video" autoplay muted loop playsinline>
<source src="presentation/videos/slide-N.mp4" type="video/mp4">
</video>
```
**Navigation JS:**
```js
// Arrow keys: Right/Down = next, Left/Up = previous (standard, NOT RTL-flipped)
// Click/touch also advances
// Auto-scale to viewport
```
**Preload images** in `<head>` with `<link rel="preload" as="image">` for each slide.
### Step 3: Generate Images
Use **image-generation** skill for each slide:
- One image per slide based on visual prompt from Step 1
- Save to `presentation/slide-NN-name.jpg`
- Default aspect ratio: 16:9 (matches 1920x1080)
- Run all generations in parallel
### Step 4: Generate Videos
Use **image-generation** skill (video mode) for each slide:
- Image-to-video from each slide's poster image
- **Always use "static camera, no movement, rock steady tripod shot"** in prompt
- Add subtle ambient effects only (light shifts, particles, shimmer)
- Save to `presentation/videos/slide-NN.mp4`
- Run all generations in parallel
### Step 5: Deploy
Use **gh-pages-deploy** skill:
- Copy HTML as `index.html` + `presentation/` folder (images + videos) to deploy directory
- Push to GitHub Pages
- Return live URL
### Step 6: Share (optional)
Use **whatsapp** skill to send the live URL if requested (WAME).
## Video Background Guidelines
- **Static camera only** - no pans, zooms, or Ken Burns effects
- **Opacity 0.25** on video element - keeps text clearly readable over dark backgrounds
- **Gradient overlay** on background image as fallback while video loads
- **autoplay muted loop playsinline** - silent infinite loop
- Ambient motion only: light shifts, floating particles, subtle glow
## File Structure
```
project-folder/
slides.html # Main presentation (renamed to index.html on deploy)
presentation/
slide-01-name.jpg # Poster images
slide-02-name.jpg
...
videos/
slide-01.mp4 # Video backgrounds
slide-02.mp4
...
```
## User Input
Minimum needed from user:
- **Topic/idea** - what the presentation is about
- **Audience** - who is watching
- **Language** - Hebrew (default) or English
- **Slide count** - approximate number (default: 8-12)
- **Repo name** - for GitHub Pages URL (default: derived from topic)
Everything else is handled by the pipeline.
## Quick Reference
| Step | Skill Used | Output |
|------|-----------|--------|
| Content | presentation-architect | Slide plan markdown |
| HTML | (direct) | Single-file HTML presentation |
| Images | image-generation | One JPG per slide |
| Videos | image-generation (video) | One MP4 per slide |
| Deploy | gh-pages-deploy | Live URL |
| Share | whatsapp (optional) | Message sent |
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.