video-cog
Long-form AI video production: the frontier of multi-agent coordination. CellCog orchestrates 6-7 foundation models to produce up to 4-minute videos from a single prompt — scripted, filmed, voiced, lipsync'd, scored, and edited automatically. Create marketing videos, product demos, explainer videos, educational content, spokesperson videos, training materials, UGC content, news reports.
What this skill does
# Video Cog - The Frontier of Multi-Agent Video Production
**Long-form AI video production is the hardest challenge in multi-agent coordination.** CellCog may be the only platform that pulls it off.
6-7 foundation models orchestrated to produce up to 4-minute videos from a single prompt: script writing, scene generation, voice synthesis, lipsync, music scoring, and editing — all automatic. Marketing videos, product demos, explainers, educational content, AI spokesperson videos, UGC, news reports, and more.
---
## Prerequisites
This skill requires the CellCog mothership skill for SDK setup and API calls.
```bash
clawhub install cellcog
```
**Read the cellcog skill first** for SDK setup. This skill shows you what's possible.
**Quick pattern (v1.0+):**
```python
# Fire-and-forget - returns immediately
result = client.create_chat(
prompt="[your video request]",
notify_session_key="agent:main:main",
task_label="video-task",
chat_mode="agent team"
)
# Daemon notifies you when complete - do NOT poll
```
---
## What Videos You Can Create
### Marketing Videos
Promotional content for products and services:
- **Product Demos**: "Create a 30-second product demo video for our new fitness app showing key features"
- **Brand Videos**: "Generate a 60-second brand story video for an eco-friendly clothing company"
- **Social Ads**: "Create a 15-second Instagram ad for a coffee subscription service"
- **Launch Videos**: "Make a product launch announcement video for a new AI writing tool"
### Explainer Videos
Educational content that breaks down complex topics:
- **Product Explainers**: "Create an explainer video showing how our SaaS platform works"
- **Concept Explanations**: "Make a video explaining how blockchain works for beginners"
- **Process Walkthroughs**: "Generate a video explaining the mortgage application process"
- **Feature Tours**: "Create a video tour of our app's new dashboard features"
### Educational Videos
Learning content for courses and training:
- **Tutorial Videos**: "Create a tutorial video on Python list comprehensions"
- **Course Content**: "Generate a lesson video on the causes of World War I"
- **Training Materials**: "Make an employee onboarding video about our company values"
- **How-To Guides**: "Create a how-to video for setting up a home studio for podcasting"
### Documentary Style
Informative, story-driven content:
- **Mini Documentaries**: "Create a 3-minute documentary-style video about the rise of electric vehicles"
- **Company Stories**: "Generate a documentary about our startup journey"
- **Industry Deep Dives**: "Make a documentary exploring the future of space tourism"
- **Historical Content**: "Create a documentary-style video about the history of Silicon Valley"
### Cinematic / Creative
Artistic and visually striking content:
- **Short Films**: "Create a 2-minute cinematic short about a day in Tokyo"
- **Mood Pieces**: "Generate a cinematic video capturing the energy of a busy coffee shop"
- **Music Video Style**: "Create a visually dynamic video for an electronic music track"
- **Artistic Showcases**: "Make a cinematic portfolio video for a photographer"
### UGC (User Generated Content) Style
Authentic, relatable content that feels personal:
- **Testimonial Style**: "Create a UGC-style testimonial video for a skincare product"
- **Unboxing Style**: "Generate an unboxing-style video for a new tech gadget"
- **Day-in-the-Life**: "Make a day-in-the-life style video featuring a remote worker using our app"
- **Review Style**: "Create a casual review-style video for a meal delivery service"
### News / Reporting Style
Professional news-format content:
- **News Reports**: "Create a news-style report video about the latest AI developments"
- **Market Updates**: "Generate a financial news video about tech stock earnings"
- **Industry News**: "Make a news report about new regulations in the fintech space"
- **Analysis Pieces**: "Create a news analysis video about the state of remote work"
---
## Lipsync & Spokesperson Videos
CellCog can generate videos with AI characters speaking your script:
- **AI Spokesperson**: "Create a video with a professional spokesperson explaining our product"
- **Avatar Presentations**: "Generate a video with an AI presenter delivering our quarterly update"
- **Character Narration**: "Make a video with a friendly character explaining our children's app"
For lipsync videos:
1. The starting frame should show only one human face prominently
2. Provide the script/dialogue
3. CellCog handles voice synthesis and lip synchronization
---
## Video Specifications
| Aspect | Options |
|--------|---------|
| **Duration** | 15 seconds to 5+ minutes |
| **Aspect Ratios** | 16:9 (landscape), 9:16 (portrait/mobile), 1:1 (square) |
| **Styles** | Photorealistic, animated, cinematic, documentary, casual |
| **Audio** | Background music, voiceover, sound effects, or silent |
---
## When to Use Agent Team Mode
For video generation, **always use `chat_mode="agent team"`** (the default).
Video creation involves:
- Script writing
- Scene planning
- Image generation for frames
- Audio generation
- Video synthesis
- Quality review
This multi-step process requires the full agent team for best results.
---
## Example Video Prompts
**Marketing video:**
> "Create a 30-second marketing video for 'FreshBrew' - a premium coffee subscription. Show beautiful coffee preparation scenes, happy customers, and end with our tagline 'Freshness Delivered Daily'. Upbeat background music, no voiceover. 16:9 for YouTube."
**Explainer with voiceover:**
> "Create a 90-second explainer video for our project management tool. Walk through: 1) Creating a project, 2) Adding team members, 3) Tracking progress. Professional female voiceover, clean animated style, include captions. 16:9 format."
**Educational content:**
> "Generate a 3-minute educational video explaining photosynthesis for middle school students. Use engaging animations, clear narration, and include a summary at the end. Friendly, approachable style."
**Spokesperson video:**
> "Create a 60-second video with an AI spokesperson (professional male, 30s) announcing our Series B funding. Script: 'Today, we're thrilled to announce...' [provide full script]. Business casual setting, confident tone."
---
## Tips for Better Videos
1. **Specify duration**: "30 seconds" or "2 minutes" helps scope the content appropriately.
2. **Define aspect ratio**: 16:9 for YouTube/web, 9:16 for TikTok/Reels/Shorts, 1:1 for Instagram feed.
3. **Describe the style**: "Cinematic", "casual UGC", "corporate professional", "playful animated".
4. **Audio preferences**: "Upbeat music", "calm narration", "no audio", "sound effects only".
5. **Include key moments**: Describe the scenes or beats you want to hit.
6. **Provide scripts**: For spokesperson/voiceover videos, write out exactly what should be said.
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.