MCPInstall

create-video-start

Master orchestrator that chains all Remotion video creation skills together in a single automated pipeline. Takes a creative brief and produces a complete, production-ready Remotion video project. Use when starting a new video from scratch, when asked to "create a video", "make a video", "build a complete video", or "video from idea to code".

Installs
158
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/ncklrs/startup-os-skills --skill create-video-start
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads create-video-start automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Create Video Start

Master orchestrator skill that chains the entire Remotion video pipeline together. Takes a single creative brief and automatically invokes each specialized skill in sequence, passing outputs between them.

What This Skill Does

Orchestrates the complete video creation pipeline:

  1. motion-designer → Creates VIDEO_SPEC.md from creative brief
  2. remotion-scaffold → Sets up project structure
  3. remotion-animation → Generates animation configurations
  4. remotion-composition → Creates Sequence layout
  5. remotion-component-gen → Generates each scene component
  6. remotion-render-config → Configures output settings
  7. remotion-asset-coordinator → Prepares asset manifest

Pipeline Execution

When invoked, execute this pipeline in order:

Step 0: Setup

Create a working directory for pipeline artifacts:

# Create pipeline working directory
PIPELINE_DIR=".remotion-pipeline/$(date +%Y%m%d_%H%M%S)"
mkdir -p "$PIPELINE_DIR"
echo "Pipeline artifacts: $PIPELINE_DIR"

Step 1: Motion Designer → VIDEO_SPEC.md

Generate the motion design specification from the creative brief:

# Invoke motion-designer skill
claude -p "You are using the /motion-designer skill.

Create a detailed VIDEO_SPEC.md for this creative brief:

$CREATIVE_BRIEF

Output a complete motion design specification with:
- Overview (duration, fps, dimensions)
- Color palette with hex codes
- Scene-by-scene breakdown with timing
- Animation details for each element
- Audio specifications

Write the spec to: $PIPELINE_DIR/VIDEO_SPEC.md" \
  --allowedTools "Read,Write,Edit,Bash"

Checkpoint: Verify VIDEO_SPEC.md exists and contains all required sections.

Step 2: Remotion Scaffold → SCAFFOLD_MANIFEST.md

Create project folder structure:

# Invoke remotion-scaffold skill
claude -p "You are using the /remotion-scaffold skill.

Based on this VIDEO_SPEC.md:
$(cat $PIPELINE_DIR/VIDEO_SPEC.md)

Create the Remotion project scaffold:
1. Create folder structure for the composition
2. Create empty template files
3. Setup asset directories
4. Register composition in Root.tsx

Write manifest to: $PIPELINE_DIR/SCAFFOLD_MANIFEST.md
Write actual files to the project." \
  --allowedTools "Read,Write,Edit,Bash,Glob"

Checkpoint: Verify scaffold directories and files exist.

Step 3: Remotion Animation → ANIMATION_CONFIG.md

Generate animation configurations:

# Invoke remotion-animation skill
claude -p "You are using the /remotion-animation skill.

Based on this VIDEO_SPEC.md:
$(cat $PIPELINE_DIR/VIDEO_SPEC.md)

Generate animation configurations:
1. Spring configs for each animation type
2. Interpolation mappings
3. Timing constants
4. Stagger delay patterns

Write to: $PIPELINE_DIR/ANIMATION_CONFIG.md

Output TypeScript constants that can be copied to constants.ts" \
  --allowedTools "Read,Write,Edit"

Checkpoint: Verify ANIMATION_CONFIG.md contains spring configs and timing.

Step 4: Remotion Composition → COMPOSITION_STRUCTURE.md

Generate Sequence layout:

# Invoke remotion-composition skill
claude -p "You are using the /remotion-composition skill.

Based on this VIDEO_SPEC.md:
$(cat $PIPELINE_DIR/VIDEO_SPEC.md)

Generate composition structure:
1. Sequence ordering for all scenes
2. Transition timing between scenes
3. Duration calculations
4. Scene timing constants

Write to: $PIPELINE_DIR/COMPOSITION_STRUCTURE.md

Output the main composition JSX structure." \
  --allowedTools "Read,Write,Edit"

Checkpoint: Verify COMPOSITION_STRUCTURE.md contains Sequence layout.

Step 5: Remotion Component Gen → SCENE_COMPONENT.md (per scene)

Generate each scene component:

# For each scene in the spec, invoke remotion-component-gen
for SCENE_NUM in $(seq 1 $TOTAL_SCENES); do
  claude -p "You are using the /remotion-component-gen skill.

Based on Scene $SCENE_NUM from this VIDEO_SPEC.md:
$(cat $PIPELINE_DIR/VIDEO_SPEC.md)

And these animation configs:
$(cat $PIPELINE_DIR/ANIMATION_CONFIG.md)

Generate the complete Scene${SCENE_NUM} component:
1. Full TSX implementation
2. Animation logic using the configs
3. Proper imports and types
4. AbsoluteFill wrapper

Write to: $PIPELINE_DIR/SCENE_${SCENE_NUM}_COMPONENT.md
Also write the actual .tsx file to the scenes/ folder." \
    --allowedTools "Read,Write,Edit,Glob"
done

Checkpoint: Verify all scene components are generated.

Step 6: Remotion Render Config → RENDER_CONFIG.md

Generate render settings:

# Invoke remotion-render-config skill
claude -p "You are using the /remotion-render-config skill.

Based on this VIDEO_SPEC.md:
$(cat $PIPELINE_DIR/VIDEO_SPEC.md)

Generate render configuration:
1. Output format and codec settings
2. Quality settings
3. Resolution confirmation
4. Render command examples

Write to: $PIPELINE_DIR/RENDER_CONFIG.md" \
  --allowedTools "Read,Write,Edit"

Step 7: Remotion Asset Coordinator → ASSET_MANIFEST.md

Generate asset preparation guide:

# Invoke remotion-asset-coordinator skill
claude -p "You are using the /remotion-asset-coordinator skill.

Based on this VIDEO_SPEC.md:
$(cat $PIPELINE_DIR/VIDEO_SPEC.md)

And this SCAFFOLD_MANIFEST.md:
$(cat $PIPELINE_DIR/SCAFFOLD_MANIFEST.md)

Generate asset manifest:
1. List all required assets
2. Recommend sources for each
3. Provide preparation instructions
4. Generate import code snippets

Write to: $PIPELINE_DIR/ASSET_MANIFEST.md" \
  --allowedTools "Read,Write,Edit,WebSearch"

Step 8: Assemble Final Output

Combine all outputs into final summary:

# Create final summary
claude -p "Create a PIPELINE_COMPLETE.md summary that:

1. Lists all generated files
2. Provides next steps for the developer
3. Includes quick-start commands
4. Notes any TODOs that need manual attention

Pipeline artifacts:
- VIDEO_SPEC.md: $(cat $PIPELINE_DIR/VIDEO_SPEC.md | head -20)
- SCAFFOLD_MANIFEST.md: $(cat $PIPELINE_DIR/SCAFFOLD_MANIFEST.md | head -20)
- ANIMATION_CONFIG.md: $(cat $PIPELINE_DIR/ANIMATION_CONFIG.md | head -20)
- COMPOSITION_STRUCTURE.md: $(cat $PIPELINE_DIR/COMPOSITION_STRUCTURE.md | head -20)
- Scene components: $(ls $PIPELINE_DIR/SCENE_*_COMPONENT.md)
- RENDER_CONFIG.md: $(cat $PIPELINE_DIR/RENDER_CONFIG.md | head -20)
- ASSET_MANIFEST.md: $(cat $PIPELINE_DIR/ASSET_MANIFEST.md | head -20)

Write to: $PIPELINE_DIR/PIPELINE_COMPLETE.md" \
  --allowedTools "Read,Write,Edit,Glob"

Input Format

Creative Brief (Natural Language)

Create a 30-second product demo video for Vello, an AI task management app.
Show the main features: smart scheduling, team collaboration, and AI suggestions.
Use modern, clean aesthetic with the brand colors (orange #FF6B35, dark background).
Include upbeat background music and subtle sound effects for transitions.
Target platform: YouTube and Twitter.

Structured Brief

## Video Brief

**Product:** Vello - AI Task Management
**Duration:** 30 seconds
**Style:** Modern, clean, tech-forward
**Brand Colors:**
  - Primary: #FF6B35 (Orange)
  - Background: #0A0A0A (Dark)
  - Accent: #4ECDC4 (Teal)

**Key Messages:**
1. Smart AI scheduling
2. Team collaboration
3. Instant AI suggestions

**Scenes:**
1. Logo intro (5s)
2. Feature showcase (15s)
3. Social proof (5s)
4. CTA (5s)

**Audio:**
- Background: Upbeat electronic
- SFX: Subtle whooshes, clicks

**Target Platforms:** YouTube, Twitter

Output Format

PIPELINE_COMPLETE.md

# Pipeline Complete: [Video Name]

## Execution Summary

| Step | Skill | Output | Status |
|------|-------|--------|--------|
| 1 | motion-designer | VIDEO_SPEC.md | ✅ |
| 2 | remotion-scaffold | SCAFFOLD_MANIFEST.md | ✅ |
| 3 | remotion-animation | ANIMATION_CONFIG.md | ✅ |
| 4 | remotion-composition | COMPOSITION_STRUCTURE.md | ✅ |
| 5 | remotion-component-gen | SCENE_*_COMPONENT.md | ✅ |
| 6 | remotion-render-config | RENDER_CONFIG.md | ✅ |
| 7 | remotion-asset-coordinator | ASSET_MANIFEST.md | ✅ |

## Generated Files

### Pipeline Artifacts

.remotion-pipeline/20240123_143052/ ├── VIDEO_SPEC.md ├── SCAFFOLD_MANIFEST.md ├── ANIMATION_CONFIG.md ├── COMPOSITION_STRUCTURE.md ├── SCENE_1_COMPONENT.md ├── SCENE_2_COMPONENT.md ├── SCENE_3_COMPONENT.md ├── SCENE_4_COMPONENT.md ├── RENDER_CONFIG.md ├── ASSET_MANIFEST.md └── PIPELINE_COMPLETE.md


### Project Files Created

src/remotion/compositions/VideoName/ ├── index.tsx ✅ Main composition ├── constants.ts ✅ Colors, springs, timing ├── types.ts ✅ TypeScript interfaces └── scenes/ ├── Scene1Intro.tsx ✅ Implemented ├── Scene2Features.tsx ✅ Implemented ├── Scene3Proof.tsx ✅ Implemented └── Scene4CTA.tsx ✅ Implemented

public/ ├── images/ 📁 Ready for assets ├── audio/ │ ├── music/ 📁 Ready for music │ └── sfx/ 📁 Ready for sound effects └── fonts/ 📁 Ready for fonts


## Quick Start

```bash
# Preview the video
npm run dev

# Open Remotion Studio
# Navigate to http://localhost:3000

# Render final video
npx remotion render src/index.tsx VideoName output.mp4

Next Steps

Required Actions

  1. Add background music to public/audio/music/
  2. Add sound effects to public/audio/sfx/
  3. Add product images to public/images/
  4. Review and customize colors in constants.ts

Optional Enhancements

  • Run /remotion-video-reviewer for QA check
  • Run /remotion-performance-optimizer for render optimization

Render Commands

From RENDER_CONFIG.md:

# YouTube (1080p, high quality)
npx remotion render src/index.tsx VideoName youtube-output.mp4 \
  --codec h264 --crf 18

# Twitter (optimized file size)
npx remotion render src/index.tsx VideoName twitter-output.mp4 \
  --codec h264 --crf 23

# Preview frames
npx remotion still src/index.tsx VideoName preview.png --frame=150

Pipeline Timing

  • Total execution time: ~3-5 minutes
  • Motion design: ~45s
  • Scaffold: ~15s
  • Animation config: ~20s
  • Composition: ~15s
  • Scene components: ~30s per scene
  • Render config: ~10s
  • Asset manifest: ~20s

## Execution Instructions

When this skill is invoked:

1. **Parse the creative brief** from the user's input
2. **Create pipeline directory** with timestamp
3. **Execute each step sequentially** using `claude -p` for skill invocation
4. **Validate output** after each step before proceeding
5. **Handle errors gracefully** - if a step fails, report and offer to retry
6. **Assemble final summary** with all artifacts and next steps

### Error Handling

If any step fails:

```bash
# Retry pattern
MAX_RETRIES=2
RETRY_COUNT=0

while [ $RETRY_COUNT -lt $MAX_RETRIES ]; do
  # Attempt skill invocation
  if claude -p "..." --allowedTools "..."; then
    break
  fi
  RETRY_COUNT=$((RETRY_COUNT + 1))
  echo "Retry $RETRY_COUNT of $MAX_RETRIES"
done

if [ $RETRY_COUNT -eq $MAX_RETRIES ]; then
  echo "Step failed after $MAX_RETRIES retries"
  # Log error and continue with partial output
fi

Integration Notes

This skill coordinates these sub-skills:

SkillInvocationOutput
/motion-designerclaude -p "..."VIDEO_SPEC.md
/remotion-scaffoldclaude -p "..."SCAFFOLD_MANIFEST.md + files
/remotion-animationclaude -p "..."ANIMATION_CONFIG.md
/remotion-compositionclaude -p "..."COMPOSITION_STRUCTURE.md
/remotion-component-genclaude -p "..." (×N)SCENE_*_COMPONENT.md + files
/remotion-render-configclaude -p "..."RENDER_CONFIG.md
/remotion-asset-coordinatorclaude -p "..."ASSET_MANIFEST.md

Each claude -p invocation includes:

  • The skill context/instructions
  • Relevant output from previous steps
  • Specific output file path
  • Allowed tools for that step

Example Usage

# Invoke with natural language brief
/create-video-start Create a 30-second demo video for our AI task app Vello

# Invoke with detailed brief
/create-video-start <<EOF
Product: Vello AI Task Manager
Duration: 45 seconds
Style: Modern tech, dark theme
Scenes: Intro, Features (3), Testimonial, CTA
Brand: Orange #FF6B35, Dark #0A0A0A
Target: YouTube, LinkedIn
EOF

Skill Dependencies

Requires these skills to be installed:

  • /motion-designer - Video specification creation
  • /remotion-scaffold - Project structure setup
  • /remotion-animation - Animation configuration
  • /remotion-composition - Sequence layout
  • /remotion-component-gen - Scene component generation
  • /remotion-render-config - Render settings
  • /remotion-asset-coordinator - Asset preparation

This orchestrator eliminates the manual handoff between skills, creating a complete video project from a single creative brief.

FAQ

What does the create-video-start skill do?

Master orchestrator that chains all Remotion video creation skills together in a single automated pipeline. Takes a creative brief and produces a complete, production-ready Remotion video project. Use when starting a new video from scratch, when asked to "create a video", "make a video", "build a complete video", or "video from idea to code".

How do I install create-video-start?

Run npx skills add https://github.com/ncklrs/startup-os-skills --skill create-video-start in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/create-video-start/ (personal) or .claude/skills/create-video-start/ (project).

Which AI agents can use create-video-start?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is create-video-start safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains create-video-start?

It is published by ncklrs in ncklrs/startup-os-skills. It has 158 recorded installs.

More from ncklrs/startup-os-skills

View all →

community-builder

ncklrs/startup-os-skills

Expert community-led growth and community management guidance. Use when building developer communities, Discord/Slack communities, online communities, managing community platforms, designing member onboarding, creating engagement programs, running ambassador programs, measuring community health, setting up moderation systems, or implementing DevRel strategies. Use for community-led growth, member activation, user-generated content programs, and community governance.

Marketing & SEO630 installs

proposal-writer

ncklrs/startup-os-skills

Expert sales proposal and pricing presentation strategist. Use when writing proposals, executive summaries, ROI business cases, pricing presentations, SOWs (Statement of Work), RFP responses, or competitive positioning documents. Covers proposal structure, terms positioning, design formatting, follow-up strategy, and win-rate optimization.

Docs & Writing594 installs

motion-designer

ncklrs/startup-os-skills

Advanced motion designer with decades of After Effects and motion graphics experience, specialized in creating engaging video specifications for Remotion. Use when creating video specs, planning motion graphics, designing animations, or when asked to "create a video", "design motion graphics", "plan video content", or "spec out a video". Produces detailed scene-by-scene specifications with timing, audio, sound effects, and animation descriptions.

Frontend & Design574 installs

website-copy-specialist

ncklrs/startup-os-skills

Expert website copywriting for SaaS and B2B companies. Use when writing homepage copy, feature pages, about pages, pricing pages, comparison pages, product tours, integration pages, use case pages, demo/contact pages, or navigation microcopy. Use for website messaging hierarchy, value proposition development, and page-level conversion optimization.

Marketing & SEO552 installs

vsl-storyboard-writer

ncklrs/startup-os-skills

Open the skill to read its SKILL.md instructions.

Docs & Writing467 installs

remotion-animation

ncklrs/startup-os-skills

Open the skill to read its SKILL.md instructions.

Frontend & Design442 installs

Popular media & creative skills

View category →

hyperframes

heygen-com/hyperframes

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.

Media & Creative1.2M installs

media-use

heygen-com/hyperframes

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

Media & Creative1.1M installs

hyperframes-registry

heygen-com/hyperframes

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Media & Creative1M installs

hyperframes-creative

heygen-com/hyperframes

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.

Media & Creative916.5K installs

ai-video-generation

101-skills/superpowers

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

Media & Creative881.5K installs

ai-image-generation

101-skills/superpowers

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Media & Creative880.3K installs