Ai video director
Hub-and-spoke agent-skill clusters, one per stack (Astro·GSAP·Remotion, Tauri, …). Installable via skills.sh.
npx -y skills add Sheshiyer/skill-clusters --skill ai-video-directorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Create AI-generated video content using Kling 3.0 (multi-shot sequences with dialogue), Sora (scene generation with character consistency), or Grok (restricted content). Use when writing shot-by-shot video prompts, building character-consistent animated series, or routing between video generation tools.
SKILL.md
3.4 KB, 699 tokens by cl100k_base, as published. Nobody here has run it
AI Video Director
Write shot-by-shot video prompt sequences for AI video generation tools. Supports multi-shot sequences (up to 6 shots), dialogue with voice control, and character consistency across scenes.
When to Use
- Writing multi-shot video sequences with scene transitions
- Creating AI-generated animated series with consistent characters
- Adding dialogue with emotion/tone control to video prompts
- Routing between video tools (Kling 3.0, Sora, Grok) based on content needs
Tool Routing
| Tool | Best For | Key Capability |
|---|---|---|
| Kling 3.0 | Multi-shot sequences with dialogue | Up to 6 native shots, audio control, subject anchoring |
| Sora | Scene generation, character consistency | Best for narrative scenes, handles [cut] transitions |
| Grok | Restricted/romantic content | Fewer content restrictions than Sora |
| Midjourney | Character source images | Style/Omni reference for initial character design |
Workflow
- Define characters -- Lock identity traits early (appearance, clothing, key features)
- Write shot sequence -- Describe each shot with cinematic language (profile, macro, tracking, POV)
- Add audio -- Structure dialogue as
[Character: Label, tone]: "text" - Route to tool -- Select based on content requirements and shot count
- Generate insert shots -- Create reusable clips for character consistency
Core Principles (Kling 3.0)
- Think in Shots, Not Clips -- Use cinematic language (profile shots, macro close-ups, tracking, shot-reverse-shot)
- Anchor Subjects Early -- Define core subjects clearly at the beginning for consistency
- Describe Motion Explicitly -- Specify camera behavior (tracking, following, freezing, panning) AND subject movement
- Native Audio -- Use
[Character A: Label, tone]: "Dialogue"format with linking words for rhythm - Image-to-Video: Lock First -- Treat input image as anchor, focus on how scene evolves FROM the image
Audio Prompting Rules
| Principle | Guideline | Example |
|---|---|---|
| Structured Naming | Unique, consistent labels | [Character A: Black-suited Agent] |
| Visual Anchoring | Action first, then dialogue | The agent slams the table. [Agent, angrily]: "Where?" |
| Audio Details | Tone and emotion labels | [Agent, raspy, deep voice]: "Don't move." |
| Temporal Control | Linking words for rhythm | [Agent]: "Why?" Immediately, [Assistant]: "Because." |
Character Consistency Workflow (Framer X)
For animated series with consistent characters across multiple scenes:
- Step 1: Generate character source images (Midjourney Style/Omni reference)
- Step 2: Create establishing scenes (Sora) with
[cut]transitions - Step 3: Generate interaction scenes (Sora) in different environments
- Step 4: Create insert shots for reusable character clips
- Step 5: Route restricted content to Grok with custom source images
See references/prompt-templates.md for complete examples.
What ships with it: 8 files
7622.4 KB alongside SKILL.md
references/
- images/cat_inserts.mp41037.8 KB
- images/character_source.jpg211.5 KB
- images/home_scene.mp4532.6 KB
- images/kissing_scene.mp4392.3 KB
- images/kissing_source.jpg123.7 KB
- images/main_teaser.mp44662.1 KB
- images/nyc_street.mp4658.6 KB
- prompt-templates.md3.8 KB