Hook-First AI Video Prompt Studio

    2

    Turn a video idea into paste-ready, shot-by-shot prompts for Wan, Veo 3, Kling, Sora and more, with hook, loop and caption copy.

    Free

    3 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Hook-First AI Video Prompt Studio

    Example session with this skill installed

    I want a 5 second vertical video for Reels of a pair of sneakers. Model is Wan. Make it feel premium.

    • Read your context and instructions
    • Compiled the hook-first ai video

    Concept

    Format

    Slow orbit with a

    macro reveal start. A premium close-up of the sneaker pulls out into a full orbit, so the first frame already shows material detail.

    Main prompt

    A pair of white leather sneakers with a thin gum sole and tonal stitching, sitting on a matte black pedestal. The camera starts in an extreme close-up on the stitched toe cap, then glides back and circles the shoes in one smooth 120-degree orbit. Studio setting with a soft seamless gray backdrop. A single large softbox from the upper left gives clean highlights along the leather and a gentle shadow on the pedestal. Polished commercial product film look, shallow depth of field. 0-1s: macro on the toe stitching. 1-4s: pull back and orbit. 4-5s: settle on a clean three-quarter view. The shoes stay perfectly still and sharp throughout.
    

    Negative prompt

    text, logos, hands, people, extra shoes, warped laces, flickering, camera shake, morphing
    

    Variations

    • A (camera): replace the orbit with a straight slow push-in from the macro to a full side view.
    • B (style): swap the gray studio for a dark moody set lit by one amber edge light.

    Post copy

    • Caption: Detail you can see before you feel it.
    • Hashtags: #sneakers #productvideo #aivideo #reels #cinematic
    • First-line hook: "Look closer at the stitching."

    Pre-flight

    One action (orbit), first frame defined (macro), camera named, no text or logos, 108 words (within Wan range). No fixes needed.

    Next steps

    Generate the clip, then ask for a variation, or paste what went wrong (warping, flat look) to get a corrected prompt.

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

    About this skill

    Stop re-rolling AI video generations. Hook-First AI Video Prompt Studio turns a rough idea into a directed shot: one clear motion, a strong first frame, a loop-friendly ending, and model-specific wording.

    What it does

    • Picks a proven hook format (transformation, slow orbit, macro reveal, time-lapse build, object-comes-alive, loop morph and more) from a 12-format library.
    • Writes the prompt with a 7-slot formula: subject, action, camera, environment, light and style, timing beats, constraints.
    • Adapts length and wording to Wan, Veo 3, Kling, Sora, Runway or Hailuo, and tells you to check current docs when it is unsure of a model's behavior.
    • Delivers a paste-ready prompt, a negative prompt, two single-change variations, a caption, hashtags and a first-line hook.
    • Runs a 10-point pre-flight checklist before handing the prompt over.

    Fix a bad prompt

    Paste a prompt that produced warped, flat or ignored-image results. It names the likely cause (too many actions, vague camera, adjective pile, image-to-video re-describing the image) and returns a corrected version.

    What is inside

    SKILL.md plus references for hook formats, model notes and the quality checklist, and a full worked example.

    Honest scope

    It improves your prompts. It does not generate video, and it does not promise views or virality.

    No support for copyrighted characters or real public figures. Avoids readable text. Optimized for clips 10 seconds or shorter.

    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

    3 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    It uses a specialized 7-slot formula that translates creative ideas into technical parameters like camera physics and motion constraints, preventing the 'morphing' and 'keyword soup' errors common with basic prompting.

    The AI Video Prompt Director is optimized for leading high-fidelity models including Wan, Kling, Sora, Runway Gen-3, Veo 3, and Hailuo, adapting its vocabulary to each model's specific architectural requirements.

    This skill is designed for single-shot cinematic clips under 10 seconds and does not support the generation of copyrighted characters, real public figures, or specific readable text.

    No complex setup is required; once added to your workspace, you simply provide your video concept, target model, and aspect ratio to begin generating structured prompts.

    You receive the core prompt transformation engine, the 7-slot cinematic framework, specialized motion control logic, and a prompt auditing tool to fix existing failing prompts.

    Yes, the skill is regularly updated to include new model-specific vocabularies and weight adjustments as new AI video generators are released or updated.

    New in Image & Video