agentsclimarketplace

Muapi cinema director

Skill SamurAIGPT/Generative-Media-Skills/.opencode/skills/muapi-cinema-director

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

Install
npx -y skills add SamurAIGPT/Generative-Media-Skills --skill muapi-cinema-director

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

4.3 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

🎬 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 IntentFramingMovementLighting
Heroic RevealLow Angle / WideCrane Up / OrbitRim Lighting / High Contrast
Tense/UneasyDutch AngleHandheld ShakeLow Key / Harsh Shadows
IntrospectiveClose-UpSlow Push InSoft Rembrandt / Window Light
Majestic/EpicExtreme WideDrone FlyoverGolden Hour / Volumetric
MelancholicProfile / MediumSlow Pull OutBlue 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.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most video audio skills give in ~1.0k tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

  • Read individual rule files for detailed explanationsin 21 of 622, across 10 files
  • Render final videoin 13 of 622, across 6 files
  • Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
  • Use this skill when dealing with Remotion codein 11 of 622, across 4 files
  • Save generated audio to a WAV filein 11 of 622, across 4 files
  • Handle conversion errors gracefullyin 10 of 622, across 6 files
  • Add captions to videos alwaysin 10 of 622, across 4 files
  • Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
  • Do not skip pipeline layersin 9 of 622, across 3 files
  • Do not make one tool do everythingin 9 of 622, across 3 files
  • Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
  • Never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

  • expand the user prompt with technical shot details
  • map creative intent to framing movement and lighting
  • combine shot type subject environment lighting movement and lens
  • use cinematic verbs to describe motion
  • apply specific illumination recipes
  • describe light relationships to trigger model reasoning

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.