New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Direct high-fidelity cinematic video with AI

Muapi cinema director

by SamurAIGPT · MIT license · ★ 4,317 on GitHub · v0.1.0 · updated Sep 8

Muapi cinema director cover

Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai

---
name: muapi-cinema-director
version: 0.1.0
description: Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai
---

# 🎬 AI Cinema Director Skill

**A specialized skill for AI Agents to direct high-fidelity cinematic video.**
The Cinema Director skill translates high-level creative intent into technical cinematographic directives for state-of-the-art video models (Veo3, Kling, Luma).

## Core Competencies

1. **Shot Composition Analysis**: Mapping emotional beats to appropriate framing (e.g., Extreme Close-Up for intimacy, Wide Shot for isolation).
2. **Camera Movement Orchestration**: Directing complex physical movements (Dolly, Truck, Crane) and lens-based effects (Rack Focus, Dolly Zoom).
3. **Lighting & Atmosphere Design**: Specifying temporal and stylistic lighting (Golden Hour, Chiaroscuro, Volumetric God Rays).
4. **Technical Parameter Optimization**: Automatically selecting optimal frame rates, aspect ratios, and model-specific biases.

Overview

A specialized skill for AI Agents to direct high-fidelity cinematic video. The Cinema Director skill translates high-level creative intent into technical cinematographic directives for state-of-the-art video models (Veo3, Kling, Luma).

The SKILL.md below is the copy AgentAlley read and checked. The repo has changed it since; the other files are from commit 5519622.

Manual install (npx, ZIP)
Claude Codenpx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-cinema-director -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/SamurAIGPT/Generative-Media-Skills/tar.gz/5519622e885a \ | tar -xz -C ~/.claude/skills --strip-components=3 Generative-Media-Skills-5519622e885a/.opencode/skills/muapi-cinema-director
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/4df8a40653b14ec53910/muapi-cinema-director.zip" -OutFile "$env:TEMP\muapi-cinema-director.zip"; Expand-Archive "$env:TEMP\muapi-cinema-director.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md4.3 KB
Read the files here
SamurAIGPT/55196221 file
Shared references1SKILL.md reads these from elsewhere in the repo. Not in the ZIP.Get them on GitHub ↗
SKILL.md
Show the full text93 lines

🎬 AI Cinema Director Skill

A specialized skill for AI Agents to direct high-fidelity cinematic video. The Cinema Director skill translates high-level creative intent into technical cinematographic directives for state-of-the-art video models (Veo3, Kling, Luma).

Core Competencies

  1. Shot Composition Analysis: Mapping emotional beats to appropriate framing (e.g., Extreme Close-Up for intimacy, Wide Shot for isolation).
  2. Camera Movement Orchestration: Directing complex physical movements (Dolly, Truck, Crane) and lens-based effects (Rack Focus, Dolly Zoom).
  3. Lighting & Atmosphere Design: Specifying temporal and stylistic lighting (Golden Hour, Chiaroscuro, Volumetric God Rays).
  4. Technical Parameter Optimization: Automatically selecting optimal frame rates, aspect ratios, and model-specific biases.

🏗️ Technical Specification

1. Intent Mapping Table
Creative Intent Framing Movement Lighting
Heroic Reveal Low Angle / Wide Crane Up / Orbit Rim Lighting / High Contrast
Tense/Uneasy Dutch Angle Handheld Shake Low Key / Harsh Shadows
Introspective Close-Up Slow Push In Soft Rembrandt / Window Light
Majestic/Epic Extreme Wide Drone Flyover Golden Hour / Volumetric
Melancholic Profile / Medium Slow Pull Out Blue Hour / Desaturated
2. Physical Camera Movements
  • Dolly In/Out: Physical camera movement on a track toward/away from the subject.
  • Truck Left/Right: Lateral physical movement.
  • Crane/Jib: Sweeping vertical movement from a height.
  • Orbit: Circular movement around a center point.
  • Pedestal: Vertical elevation change (without tilting).
3. Lens & Optical Controls
  • Shallow DOF: Background blur (Bokeh).
  • Anamorphic: Horizontal flares and wide-screen cinematic feel.
  • Rack Focus: Shifting focus between planes within the shot.

🧠 Prompt Optimization Protocol (Agent Instruction)

Before calling the script, the Agent MUST expand the user's raw prompt using these Director's Rules:

  1. TECHNICAL INFUSION: Transform "cool action" into a technical shot.
    • Formula: [Shot Type] + [Subject/Action] + [Environment] + [Lighting] + [Camera Movement] + [Lens Effect]
  2. MOTION DYNAMICS: Use cinematic verbs: Dolly In (intimacy), Crane Up (majestic), Orbit (heroic), Truck (parallel motion).
  3. LIGHTING RECIPES: Apply specific illumination: Volumetric God Rays, Teal-and-Orange Grade, Cyberpunk Rim Lighting, Rembrandt Portrait Lighting.
  4. PHYSICS LOGIC: Describe light relationships (e.g., "Neon reflections shimmering on rain-slicked asphalt") to trigger model reasoning.

🚀 Protocol: Using the Cinema Director

Step 1: Define the Creative Brief

Provide the agent with a subject and a "Director's Intent."

Step 2: Invoke the Script

The generate-film.sh script accepts a --brief which it expands using its internal knowledge of cinematography.

# Directing a scene
bash scripts/generate-film.sh 
  --subject "A lone samurai in a blizzard" 
  --intent "epic reveal" 
  --model "kling-master"
Step 3: Handle the Async Response

Video generation is asynchronous. Use the returned request_id to poll for completion via core/platform/check-result.sh.


⚠️ Constraints & Guardrails

  • Temporal Consistency: Avoid complex subject transformations in a single shot (e.g., "man turns into a bird").
  • Movement Collisions: Do not combine contradictory movements (e.g., "Dolly In" and "Dolly Out" simultaneously).
  • Physical Realism: Prefer movements possible with real-world equipment for a more professional "film" look.
  • Model Bias:
    • Veo3: Best for slow, high-quality aesthetic shots.
    • Kling: Best for complex character motion and physics.
    • Luma: Best for fast-paced, high-action cinematic sequences.

⚙️ Implementation Details

This skill acts as an "Expert Translator" for the core/media/generate-video.sh primitive. It maintains a dictionary of cinematic styles and injects technical directives into the prompt before execution.

1---
2name: muapi-cinema-director
3version: 0.1.0
4description: Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai
5---
6 
7# 🎬 AI Cinema Director Skill
8 
9**A specialized skill for AI Agents to direct high-fidelity cinematic video.**
10The Cinema Director skill translates high-level creative intent into technical cinematographic directives for state-of-the-art video models (Veo3, Kling, Luma).
11 
12## Core Competencies
13 
141. **Shot Composition Analysis**: Mapping emotional beats to appropriate framing (e.g., Extreme Close-Up for intimacy, Wide Shot for isolation).
152. **Camera Movement Orchestration**: Directing complex physical movements (Dolly, Truck, Crane) and lens-based effects (Rack Focus, Dolly Zoom).
163. **Lighting & Atmosphere Design**: Specifying temporal and stylistic lighting (Golden Hour, Chiaroscuro, Volumetric God Rays).
174. **Technical Parameter Optimization**: Automatically selecting optimal frame rates, aspect ratios, and model-specific biases.
18 
19---
20 
21## 🏗️ Technical Specification
22 
23### 1. Intent Mapping Table
24 
25| Creative Intent | Framing | Movement | Lighting |
26| :--- | :--- | :--- | :--- |
27| **Heroic Reveal** | Low Angle / Wide | Crane Up / Orbit | Rim Lighting / High Contrast |
28| **Tense/Uneasy** | Dutch Angle | Handheld Shake | Low Key / Harsh Shadows |
29| **Introspective** | Close-Up | Slow Push In | Soft Rembrandt / Window Light |
30| **Majestic/Epic** | Extreme Wide | Drone Flyover | Golden Hour / Volumetric |
31| **Melancholic** | Profile / Medium | Slow Pull Out | Blue Hour / Desaturated |
32 
33### 2. Physical Camera Movements
34- `Dolly In/Out`: Physical camera movement on a track toward/away from the subject.
35- `Truck Left/Right`: Lateral physical movement.
36- `Crane/Jib`: Sweeping vertical movement from a height.
37- `Orbit`: Circular movement around a center point.
38- `Pedestal`: Vertical elevation change (without tilting).
39 
40### 3. Lens & Optical Controls
41- `Shallow DOF`: Background blur (Bokeh).
42- `Anamorphic`: Horizontal flares and wide-screen cinematic feel.
43- `Rack Focus`: Shifting focus between planes within the shot.
44 
45---
46 
47## 🧠 Prompt Optimization Protocol (Agent Instruction)
48 
49**Before calling the script, the Agent MUST expand the user's raw prompt using these Director's Rules:**
50 
511. **TECHNICAL INFUSION**: Transform "cool action" into a technical shot.
52 - *Formula*: `[Shot Type] + [Subject/Action] + [Environment] + [Lighting] + [Camera Movement] + [Lens Effect]`
532. **MOTION DYNAMICS**: Use cinematic verbs: *Dolly In* (intimacy), *Crane Up* (majestic), *Orbit* (heroic), *Truck* (parallel motion).
543. **LIGHTING RECIPES**: Apply specific illumination: *Volumetric God Rays*, *Teal-and-Orange Grade*, *Cyberpunk Rim Lighting*, *Rembrandt Portrait Lighting*.
554. **PHYSICS LOGIC**: Describe light relationships (e.g., "Neon reflections shimmering on rain-slicked asphalt") to trigger model reasoning.
56 
57---
58 
59## 🚀 Protocol: Using the Cinema Director
60 
61### Step 1: Define the Creative Brief
62Provide the agent with a subject and a "Director's Intent."
63 
64### Step 2: Invoke the Script
65The `generate-film.sh` script accepts a `--brief` which it expands using its internal knowledge of cinematography.
66 
67```bash
68# Directing a scene
69bash scripts/generate-film.sh
70 --subject "A lone samurai in a blizzard"
71 --intent "epic reveal"
72 --model "kling-master"
73```
74 
75### Step 3: Handle the Async Response
76Video generation is asynchronous. Use the returned `request_id` to poll for completion via `core/platform/check-result.sh`.
77 
78---
79 
80## ⚠️ Constraints & Guardrails
81 
82- **Temporal Consistency**: Avoid complex subject transformations in a single shot (e.g., "man turns into a bird").
83- **Movement Collisions**: Do not combine contradictory movements (e.g., "Dolly In" and "Dolly Out" simultaneously).
84- **Physical Realism**: Prefer movements possible with real-world equipment for a more professional "film" look.
85- **Model Bias**:
86 - `Veo3`: Best for slow, high-quality aesthetic shots.
87 - `Kling`: Best for complex character motion and physics.
88 - `Luma`: Best for fast-paced, high-action cinematic sequences.
89 
90---
91 
92## ⚙️ Implementation Details
93This skill acts as an "Expert Translator" for the `core/media/generate-video.sh` primitive. It maintains a dictionary of cinematic styles and injects technical directives into the prompt before execution.
View all files on GitHub →

Details

Version
0.1.0
Updated
Sep 8, 2026
License
MIT
Stars on the repo
★ 4,317
Checked
Source
SamurAIGPT/Generative-Media-Skills ↗
Creator
SamurAIGPT · 16 listings
View creator

Similar skills

See all →
PromptYüklenen ve Doğum bilgileri girilen görselin Astrolojik 20262026 Size Neler getirecekf/prompts.chat · by Ali AydınlıYüklenen ve Doğum bilgileri girilen görselin Astrolojik 2026 yılıNew listingPromptCreate a 15-second ultra-realistic cinematic winterArctic winter adventure vlogYouMind-OpenLab/awesome-seedance-2-prompts · by ayzalnoorCreate a 15-second ultra-realistic cinematic winter adventure video set in a breathtaking Arctic-style snowy mountain landscape.New listingPromptA prompt for generating polished semi-realistic anime artComic / Storyboard - Cinematic 2D Anime IllustrationYouMind-OpenLab/awesome-nano-banana-pro-prompts · by ZayanA prompt for generating polished semi-realistic anime art with a nostalgic 90s/00s vibe and moody teal-and-amber color grading.New listingPromptA candid, photorealistic iPhone-style selfie capturingA moment shared with the wildf/prompts.chat · by Semih KışlarA candid, photorealistic iPhone-style selfie capturing a relaxed moment between a human and a wild {WILD_ANIMAL} in its natural habitat. Natural light, subtle motion, and authentic details create the feeling of a real, spontaneous encounter in the wild.New listingPromptGenerates a photorealisticAlpine golden hour granola portraitf/prompts.chat · by Alejandro García GarayGenerates a photorealistic, vertical 3:4 medium shot of a young woman with a relaxed "granola girl" aesthetic by a tranquil mountain lake. She wears a patterned sherpa fleece jacket and messy bun, looking over her shoulder with a warm smile. Bathed in golden hour sunlight, the image features crisp deep focus on both the subject and the dramatic alpine cliffs, rendered in sharp 8K iPhone 16 Pro Max quality.New listingPrompt[medium front-facing shot of student seated at deskCelebratory student exam result revealf/prompts.chat · by Ahmet Sonuç"composition": ["medium front-facing shot of student seated at desk, holding up smartphone toward camera with green screen display…New listing

More from SamurAIGPT

SkillGenerate a high-converting ad creative setMuapi ad creativeSamurAIGPT/Generative-Media-Skills · by SamurAIGPTGenerate a high-converting ad creative set — hero image, ad copy variations, and platform-optimized crops for Meta, Google Display, and LinkedIn.★ 4.3k GitHub starsSkillTurn a long video into N viral-ready short clipsMuapi AI clippingSamurAIGPT/Generative-Media-Skills · by SamurAIGPTTurn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's `/ai-clipping` endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe, and vertical face-tracking auto-crop server-side. No local Whisper, no local LLM, no GPU.★ 4.3k GitHub starsSkillGenerate a high-cut-density action / fight scene by firstMuapi AI fight sceneSamurAIGPT/Generative-Media-Skills · by SamurAIGPTGenerate a high-cut-density action / fight scene by first composing a 16-cell storyboard image, then driving Seedance 2.0 image-to-video off that storyboard. Stacks GPT-Image-2 (character sheet + storyboard), Nano-Banana-2 (environment concept), and Seedance 2.0 i2v.★ 4.3k GitHub starsSkillTurn a real lifestyle photo into a polished chibi cloneMuapi chibi collage effectSamurAIGPT/Generative-Media-Skills · by SamurAIGPTTurn a real lifestyle photo into a polished "chibi clone sticker diary" image — the original person stays photorealistic, surrounded by 5–8 kawaii chibi mini-clones, scrapbook doodles, and handwritten-style captions that match the scene.★ 4.3k GitHub starsSkillCreate a polished, on-brand Instagram postMuapi instagram postSamurAIGPT/Generative-Media-Skills · by SamurAIGPTCreate a polished, on-brand Instagram post — square or portrait hero image with matching caption and hashtags.★ 4.3k GitHub starsSkillEngineer professional-grade brand logos using geometricMuapi logo creatorSamurAIGPT/Generative-Media-Skills · by SamurAIGPTEngineer professional-grade brand logos using geometric primitives and negative space — generates minimalist, scalable vector-style marks via muapi.ai★ 4.3k GitHub stars