remotion-composition
Generates Remotion composition structure focusing ONLY on Sequence ordering, scene transitions, and duration mapping. Input is scene list with durations. Output is COMPOSITION_STRUCTURE.md with Sequence layout and timing calculations. Use when organizing scenes or when asked to "structure composition", "layout scenes", "calculate timing".
What this skill does
# Remotion Composition
Generates composition structure documents that define how scenes are ordered, timed, and transitioned in a Remotion video. This skill focuses exclusively on Sequence layout and timing orchestration.
## What This Skill Does
Generates composition structure for:
1. **Sequence layout** — Ordering and positioning of scene Sequences
2. **Timing calculations** — Start frames, end frames, duration for each scene
3. **Scene transitions** — Overlap and crossfade timing between scenes
4. **Duration mapping** — Converting seconds to frames for all scenes
5. **Timing constants** — Structured timing object for constants.ts
## Scope Boundaries
**IN SCOPE:**
- Sequence component organization
- Frame calculations for scene timing
- Scene overlap and transition timing
- Duration constant generation
- Scene ordering logic
**OUT OF SCOPE:**
- Scene component implementation (use `/remotion-component-gen`)
- Animation parameters (use `/remotion-animation`)
- Visual styling (colors, layouts)
- Asset management (use `/remotion-asset-coordinator`)
## Input/Output Formats
### Input Format: Scene List with Durations
Accepts scene timing specifications:
**Natural Language:**
```
Scene 1 (Intro): 0-5 seconds
Scene 2 (Features): 5-15 seconds
Scene 3 (Demo): 15-25 seconds
Scene 4 (CTA): 25-30 seconds
```
**Structured Format:**
```markdown
## Scene Timing
**Total Duration:** 30 seconds
**Frame Rate:** 30 fps
**Total Frames:** 900
**Scenes:**
1. Scene 1 - Intro: 5 seconds (0s - 5s)
2. Scene 2 - Features: 10 seconds (5s - 15s)
3. Scene 3 - Demo: 10 seconds (15s - 25s)
4. Scene 4 - CTA: 5 seconds (25s - 30s)
**Transitions:**
- Fade transition between scenes: 0.5 seconds (15 frames)
```
### Output Format: COMPOSITION_STRUCTURE.md
Generates composition structure document:
```markdown
# Composition Structure: ProductDemo
## Status
✅ Sequence layout defined
✅ Timing calculations complete
⏳ Ready for scene implementation
## Composition Overview
**Total Duration:** 30 seconds (900 frames @ 30fps)
**Scenes:** 4
**Transitions:** Crossfade (15 frames)
## Scene Timing Constants
```typescript
const FPS = 30;
export const SCENE_TIMING = {
intro: {
start: 0,
end: 150,
duration: 150,
// 0s - 5s
},
features: {
start: 150,
end: 450,
duration: 300,
// 5s - 15s
},
demo: {
start: 450,
end: 750,
duration: 300,
// 15s - 25s
},
cta: {
start: 750,
end: 900,
duration: 150,
// 25s - 30s
},
} as const;
// Transition timing
export const TRANSITIONS = {
crossfadeDuration: 15, // frames (0.5 seconds)
} as const;
```
## Composition Layout
Main composition with Sequence structure:
```typescript
import { AbsoluteFill, Sequence } from "remotion";
import { SCENE_TIMING } from "./constants";
import { Scene1Intro } from "./scenes/Scene1Intro";
import { Scene2Features } from "./scenes/Scene2Features";
import { Scene3Demo } from "./scenes/Scene3Demo";
import { Scene4CTA } from "./scenes/Scene4CTA";
export function ProductDemo() {
return (
<AbsoluteFill>
{/* Scene 1: Intro (0s - 5s) */}
<Sequence
from={SCENE_TIMING.intro.start}
durationInFrames={SCENE_TIMING.intro.duration}
>
<Scene1Intro />
</Sequence>
{/* Scene 2: Features (5s - 15s) */}
<Sequence
from={SCENE_TIMING.features.start}
durationInFrames={SCENE_TIMING.features.duration}
>
<Scene2Features />
</Sequence>
{/* Scene 3: Demo (15s - 25s) */}
<Sequence
from={SCENE_TIMING.demo.start}
durationInFrames={SCENE_TIMING.demo.duration}
>
<Scene3Demo />
</Sequence>
{/* Scene 4: CTA (25s - 30s) */}
<Sequence
from={SCENE_TIMING.cta.start}
durationInFrames={SCENE_TIMING.cta.duration}
>
<Scene4CTA />
</Sequence>
</AbsoluteFill>
);
}
```
## Scene Timing Breakdown
| Scene | Name | Duration | Frames | Start Frame | End Frame |
|-------|------|----------|--------|-------------|-----------|
| 1 | Intro | 5s | 150 | 0 | 150 |
| 2 | Features | 10s | 300 | 150 | 450 |
| 3 | Demo | 10s | 300 | 450 | 750 |
| 4 | CTA | 5s | 150 | 750 | 900 |
**Total:** 30 seconds (900 frames)
## Timeline Visualization
```
Frame: 0 150 450 750 900
Time: 0s 5s 15s 25s 30s
|---------|---------|---------|---------|
Scene: | Intro | Features| Demo | CTA |
|---------|---------|---------|---------|
```
## Next Steps
1. **Implement scenes** via `/remotion-component-gen`
2. **Add transitions** if needed (crossfades, wipes)
3. **Integrate constants** into composition constants.ts
4. **Test timing** in Remotion preview
5. **Adjust durations** if scenes feel too fast/slow
## Checklist
- [x] Scene timing calculated
- [x] Sequence layout defined
- [x] Constants generated
- [x] Timing constants structured
- [ ] Scene components implemented (next step)
- [ ] Transitions added (if needed)
- [ ] Timing tested in preview
```
## Composition Patterns
### Pattern 1: Sequential Scenes (No Overlap)
Standard sequential layout where scenes don't overlap:
```typescript
<Sequence from={0} durationInFrames={150}>
<Scene1 />
</Sequence>
<Sequence from={150} durationInFrames={300}>
<Scene2 />
</Sequence>
<Sequence from={450} durationInFrames={300}>
<Scene3 />
</Sequence>
```
### Pattern 2: Overlapping Scenes (Crossfade)
Scenes overlap for smooth transitions:
```typescript
const CROSSFADE = 15; // frames
// Scene 1: Full duration
<Sequence from={0} durationInFrames={150}>
<Scene1 />
</Sequence>
// Scene 2: Starts before Scene 1 ends
<Sequence from={150 - CROSSFADE} durationInFrames={300 + CROSSFADE}>
<Scene2 />
</Sequence>
// Scene 3: Starts before Scene 2 ends
<Sequence from={450 - CROSSFADE} durationInFrames={300 + CROSSFADE}>
<Scene3 />
</Sequence>
```
### Pattern 3: Layered Composition
Background + foreground scenes running simultaneously:
```typescript
{/* Background layer - runs full duration */}
<Sequence from={0} durationInFrames={900}>
<BackgroundScene />
</Sequence>
{/* Foreground scenes - sequential */}
<Sequence from={0} durationInFrames={150}>
<Scene1 />
</Sequence>
<Sequence from={150} durationInFrames={300}>
<Scene2 />
</Sequence>
```
### Pattern 4: Nested Sequences
Sub-scenes within main scenes:
```typescript
<Sequence from={0} durationInFrames={300}>
<AbsoluteFill>
{/* Sub-scene 1 */}
<Sequence from={0} durationInFrames={100}>
<Intro />
</Sequence>
{/* Sub-scene 2 */}
<Sequence from={100} durationInFrames={200}>
<MainContent />
</Sequence>
</AbsoluteFill>
</Sequence>
```
## Timing Calculation Helpers
Common frame calculations:
```typescript
// Convert seconds to frames
const secondsToFrames = (seconds: number, fps: number = 30): number =>
Math.round(seconds * fps);
// Calculate scene timing
interface SceneTiming {
start: number;
end: number;
duration: number;
}
const calculateSceneTiming = (
startSeconds: number,
durationSeconds: number,
fps: number = 30
): SceneTiming => {
const start = secondsToFrames(startSeconds, fps);
const duration = secondsToFrames(durationSeconds, fps);
const end = start + duration;
return { start, end, duration };
};
// Calculate crossfade overlap
const calculateCrossfade = (
scene1Start: number,
scene1Duration: number,
crossfadeDuration: number
) => ({
scene1: {
from: scene1Start,
durationInFrames: scene1Duration,
},
scene2: {
from: scene1Start + scene1Duration - crossfadeDuration,
durationInFrames: crossfadeDuration, // or more if scene is longer
},
});
// Validate total duration
const validateDuration = (
scenes: SceneTiming[],
expectedTotal: number
): boolean => {
const lastScene = scenes[scenes.length - 1];
return lastScene.end === expectedTotal;
};
```
## Scene Timing Generation
Automated timing generatioRelated 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.