Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    cast sheet

    1

    Generate 2-panel character reference sheets and structured video prompts for consistent identity and animation.

    Free

    1 useSecurity scanned
    cast sheet

    cast sheet

    Example session with this skill installed

    Generate a cast sheet for a 30-year-old female explorer in weathered canvas gear. Add an animation prompt for a 10-second character intro with her saying 'We found it' on camera.

    • Read your context and instructions
    • Compiled the cast sheet
    • Generated the image

    I have generated the cast-sheet image featuring the explorer in weathered canvas gear against a neutral studio background. The left panel shows her full-body silhouette while the right provides a detailed portrait.

    Character Reference Sheet

    Character Cast Sheet
    Note: If the center divider is slightly offset, crop the panels into two 9:16 images before video processing.

    Combined Performance Prompt

    CAST PERFORM
    Elena, The Explorer
    Cast for: Film / Character Intro
    Duration: 10 seconds
    
    SCENE CONTEXT
    Use the supplied two-panel cast-sheet as the visual source. Depict one consistent character throughout: 30-year-old female explorer, determined expression. Preserve tanned complexion, hazel eyes, and messy dark hair. Preserve the exact wardrobe: weathered tan canvas jacket, utility vest, dark cargo pants, and leather boots with visible scuffing. Keep the source's neutral gray studio background (#777777), soft frontal light, and natural color. The left panel is the full-body source; the right panel is the matching head-and-shoulders portrait.
    
    ACTION
    
    LEFT-PANEL — [full-body composition]
    0-5s: Start with a stable breathing hold. Elena adjusts a strap on her utility vest ( personality gesture) and looks toward the camera. Settle at 4.5s.
    CAMERA: Subtle push-in toward the torso to emphasize the canvas texture, keeping the full silhouette and boots in frame.
    
    At 5s, make one clean, direct cut from the LEFT-PANEL composition to the RIGHT-PANEL composition. No morphing or panning.
    
    RIGHT-PANEL — [portrait composition]
    5-10s: Elena makes direct eye contact, gives a sharp, knowing nod, and settles into a stable pose. 
    CAMERA: Very gentle push-in to emphasize facial character and eye detail.
    
    PERFORMANCE / VOICE
    Elena speaks one short line during the LEFT-PANEL action: "We found it." Use subtle, synchronized lip movement. During the RIGHT-PANEL portrait, she remains silent but maintains a confident gaze. Voice: Mid-range, husky, breathless but triumphant.
    
    CONTINUITY AND NEGATIVES
    Preserve exact identity across the cut. No walking out of frame, costume changes, or face warping. No split-screen or showing both panels simultaneously.
    

    Next steps

    1. Download the generated cast-sheet image.
    2. If necessary, crop the left and right panels to exactly 9:16 ratios for specific model inputs.
    3. Paste the performance prompt into your video generation tool using the cast-sheet as the image reference.

    explorer-cast-sheet-001.png

    PNG · 1536×1024

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Generate a consistent two-panel character cast-sheet image and provide one combined image-to-video performance prompt that moves from the full-body left panel to the portrait right panel. Use for character reference sheets, cast sheets, front-facing full-body plus portrait boards, and character perform prompts to generate video performance.

    May require manual cropping if the image model generates an imperfect center divider. Video duration is limited by the specific AI video model being used.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed22 days ago
    Updated19 days ago

    What's inside

    Frequently Asked Questions

    The skill generates a specialized 16:9 "split-canvas" reference sheet (full-body and portrait) alongside structured performance prompts that bridge the two views, preventing the character's face and clothes from changing during video transitions.

    You will receive the logic framework for character resolution, the specific image-generation parameters for consistent 2-panel sheets, and the structured "CAST PERFORM" prompting template designed for video models.

    It is optimized for high-end image generators like DALL-E 3 and Midjourney, and works with leading image-to-video platforms such as Runway (Gen-2/3), Luma Dream Machine, and Pika.

    No complex installation is required; once added to your workspace, you simply provide a character brief or reference image to begin the automated generation process.

    While the skill enforces a 16:9 landscape canvas with a vertical split, slight variations in model output may occasionally require a quick manual crop to separate the panels for specific video tool uploads.

    Yes, buyers receive lifetime access to the skill, including any future optimizations made to the prompt architecture as new video generation models are released.

    New in Image & Video