Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    ai avatar social slideshow reel

    2

    Generate consistent AI avatar prompts for realistic, UGC-style social media carousels and video reels.

    $29

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    ai avatar social slideshow reel

    ai avatar social slideshow reel

    Example session with this skill installed

    I need an Instagram Reel concept for a new pair of minimalist leather sneakers. Use an existing female avatar reference. I want both image and video prompts for a 15-second creator-style video.

    • Read your context and instructions
    • Compiled the ai avatar social
    • Generated the image

    I will help you create a realistic creator-style Reel for your minimalist leather sneakers.

    Concept: Minimalist Leather Sneaker Reveal

    • Platform: Instagram
    • Duration: 15 seconds
    • Content Type: Footwear / Fashion
    • Setting: Urban sidewalk with natural afternoon light
    • Story Arc: Hook (On-feet) -> Detail (Leather texture) -> Action (Walking) -> Verdict (Pose)

    Image Prompt

    [Use the supplied avatar reference as the exact identity reference. Preserve facial identity, facial proportions, hair pattern, skin tone, and recognizable features. Do not beautify or redesign the face.]

    A realistic creator-style scene on a clean urban sidewalk. The avatar is in her late 20s, wearing cropped denim and a neutral knit sweater, wearing the minimalist white leather sneakers.

    Action: Standing in a casual pose, one foot slightly forward to show the sneaker profile. Expression: Subtle natural smile.
    Composition: Low angle, vertical 9:16.
    Camera: modern smartphone camera, casual handheld framing, slight natural hand movement, realistic autofocus behavior, mild exposure variation, ordinary smartphone dynamic range.
    Lighting: natural afternoon sunlight, soft shadows, believable falloff.

    Realism: natural pores, subtle skin texture, tiny imperfections, realistic hands, flyaway hairs, authentic fabric wrinkles, physically accurate leather material, no plastic skin, no beauty retouching.
    Product integrity: preserve exact sneaker shape, flat cotton laces, silver eyelets, gum sole geometry, and clean stitching. Do not invent or distort labels.
    Negative: extra fingers, warped hands, deformed footwear, floating objects, face drift, identity drift, glossy CGI look, random text.

    Image-to-Video Prompt

    Animate the supplied image as a short-form creator video. Keep the avatar identity, sneaker geometry, and environment unchanged.
    Duration: 15 seconds.
    Format: vertical 9:16.

    Action sequence
    0–4s: Avatar shifts weight naturally, looking down at the sneakers with a slight smile.
    4–10s: A slow handheld pan down to a close-up of the sneakers as the avatar takes two steps forward.
    10–15s: Avatar stops, looks back at the camera, and gives a small "thumbs up" or casual wave.

    Performance: subtle realistic eye movement, natural blinking, believable breathing. No exaggerated influencer acting.
    Product interaction: The sneakers must bend naturally at the toe box during steps. Leather texture must remain stable.
    Camera: handheld smartphone shot, small natural wrist movement, slight framing correction, tiny autofocus adjustment when subject distance changes.
    Continuity: keep identity, hairstyle, and sneaker design consistent from first frame to last.
    Avoid: face morphing, sneaker warping, hand anomalies, extra fingers, texture melting, artificial beauty smoothing.

    Next steps

    1. Upload your avatar reference image to your preferred image generator using the Image Prompt.
    2. Use the resulting image as the starting frame for your video generator (Veo or Seedance) with the Video Prompt.
    3. Apply a trending "lo-fi" audio track in Instagram for maximum authenticity.

    ai-avatar-social-slideshow-reel.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.

    What you get

    Build multi-scene Reels with a consistent AI model identity.Generate realistic 'unboxing' or 'try-on' prompts for fashion brands.Enforce authentic smartphone camera aesthetics to avoid the AI plastic look.Create high-fidelity Instagram carousels with product-specific details.

    About this skill

    The problem

    Social media managers and creators struggle to produce high-volume UGC-style video content without expensive shoots. AI-generated avatars often look too "perfect" or plastic, breaking the authentic creator-to-audience trust needed for high engagement.

    What it does

    • Generates detailed image and video prompts designed to maintain a consistent AI avatar across multiple scenes.
    • Enforces authentic mobile-phone aesthetics, including natural skin textures, minor autofocus adjustments, and realistic smartphone dynamic range.
    • Builds structured scene breakdowns for social content ranging from 8-second hooks to 2-minute narrative reels.
    • Supports specific product categories like fashion, footwear, and consumer goods with strict product-integrity constraints to prevent warped logos or geometry.

    Frameworks & tools

    Optimized for image and video models including Veo 3.1 Lite, Omni Flash 1.1, Seedance 2.0/2.5, and standard SDXL/Flux-based image generators.

    Why this beats prompting it yourself

    Writing prompts that maintain identity across multiple scenes while avoiding the "AI plastic look" is difficult. This skill uses a specialized prompt architecture that locks in identity references and adds specific realism cues—like flyaway hairs and natural handheld jitter—that most basic prompts ignore.

    Use cases

    • Creating consistent TikTok try-on hauls without a physical studio or model.
    • Generating realistic Instagram carousels for footwear brands that look like user-submitted content.
    • Developing product reveal reels that maintain brand colors and packaging integrity throughout the video.

    Known limitations

    Requires an existing avatar reference image for best results, though it can generate one. Durations over 15 seconds are best handled as multiple generated segments.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 13 days ago

    • Passed all security checks, Safe to install

    Listed13 days ago

    What's inside

    Frequently Asked Questions