Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Cartoon Jake

    1

    A Codex skill for expressive 2D cartoons with consistent characters, readable actions, believable interactions, and coherent lighting, using saved visual references.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Cartoon Jake

    Example session with this skill installed

    $artifact-template-cartoon-jake Draw Usain Bolt taking his first step just after the starting gun at the World Championships.

    • Read your context and instructions
    • Compiled the cartoon jake
    • Generated the image

    Usain Bolt's first step

    Usain Bolt taking his first step from the starting blocks in the Cartoon Jake style, with a Jamaican racing kit, a planted forefoot, and a cast shadow on the track.

    This is the approved image shown in the creator's GitHub repository. It depicts Usain Bolt taking his first step after the starting gun at the World Championships.

    The close-up makes Bolt the clear protagonist, with a dynamic silhouette, a Jamaican racing kit, and a planted forefoot. Smaller background competitors have left their blocks and begun their first strides. The starter, blocks, lanes, crowd, and cast shadows place the action in one shared scene.

    The skill keeps this image as a composition reference for protagonist-led scenes and adapts the framing to the requested subject and activity. Its review process checks character identity, readable action, physical contact, shared timing, supporting participants, and coherent lighting.

    This existing image demonstrates the workflow; individual results depend on the image-generation model and the user's request.

    1794876175169-zwv4.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

    A Codex skill for expressive 2D cartoons with rounded shapes, clean black outlines, and vivid flat colors. It applies the same visual language across sports, everyday activities, conversation, teamwork, animals, fantasy, and quiet scenes.

    The instructions coordinate the entire scene, including background participants, shared objects, physical contact, and lighting.

    They also preserve a clear focal subject. An approved close-up keeps its framing and protagonist scale while corrections address supporting details.

    Usain Bolt's first step

    The approved example shows Usain Bolt taking his first step after the starting gun at the World Championships. The close-up makes Bolt the clear protagonist. Smaller background competitors have also left their blocks and begun their first strides. The skill retains this image as a composition reference for protagonist-led scenes and adapts the framing to each request.

    Default creative direction

    AreaDefault
    Shared timingCoordinate participants around the same event, with small natural differences in reaction and pose.
    Cartoon exaggerationKeep balance, weight, contact, and cause and effect believable while exaggerating shape and elasticity.
    Supporting participantsInclude people or creatures that the situation calls for, following explicit subject counts.
    Background detailSimplify faces and clothing while keeping readable actions, gaze, support, and shadows coherent.
    CameraMake the intended protagonist or group the clear focus while revealing the important action. Preserve approved framing and subject scale during corrections.
    Real subjectsVerify defining appearance, representative clothing, equipment, and key actions using relevant reliable references.
    EffectsUse moderate, purposeful effects that make effort and movement easy to read.
    ReviewInspect the full scene and its readable background participants, then correct material inconsistencies before final delivery.

    Explicit instructions in a request can change these defaults. Specific event years and historical details are researched when they are part of the requested scene.

    Usage

    Use Codex with access to the imagegen skill and an image-generation tool. Invoke $artifact-template-cartoon-jake and describe who or what is in the scene, what is happening, and the moment you want to capture. Add a setting, expression, camera angle, lighting direction, or transparent background requirement when it matters.

    Sport

    $artifact-template-cartoon-jake Draw the first step after the starting gun at a sprint final. Keep all visible competitors in compatible stages of early acceleration, with small natural differences in their strides.
    

    Cooperation and object handling

    $artifact-template-cartoon-jake Draw two friends carrying a wooden table through a doorway. Make their grips, shared load, steps, and the table's angle work together.
    

    Everyday activities

    $artifact-template-cartoon-jake Draw Jake preparing breakfast while a friend hands him a bowl. Show the instant both characters support the bowl, with clear hand contact and coordinated attention.
    

    Quiet and emotional scenes

    $artifact-template-cartoon-jake Draw a student listening to a friend at a cafe. Use their expressions, gaze, posture, and distance to convey a thoughtful conversation.
    

    Fantasy

    $artifact-template-cartoon-jake Draw a small wizard lifting a stone with magic while a companion watches. Make the stone's position, the characters' reactions, and the magical light agree.
    

    The skill carries the saved cartoon style across subjects while retaining their defining appearance and clothing. It adapts the physical details to each activity and the requested fictional rules.

    How scene review works

    For a race start, all visible competitors should respond to the same signal and fit the brief time elapsed. For a handoff, the participants' hands and the object's position should agree. For a conversation, gaze and gestures should explain who is attending to whom.

    Review covers the main subject, interacting props, readable background figures, spatial relationships, and lighting. Focused corrections address material errors while retaining successful visual choices.

    For a protagonist-led scene, review also checks that the main subject retains the intended prominence. Background corrections preserve an approved close-up and its dynamic silhouette.

    What's included

    The package contains SKILL.md, interface metadata, three saved style references, an approved composition example, a template preview, and detailed guides to motion, lighting, and scene coherence. The package matches the skill folder in the creator's GitHub repository.

    Requirements

    An image-generation tool that accepts reference images is required. The skill is a creative workflow and instruction package; it does not include an image model, image-generation credits, or a standalone image editor.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.

    Requires an image-generation tool that accepts reference images. Results depend on the underlying model and may need revisions for anatomy, text, contact, timing, or lighting. This instruction package does not include image-model access or generation credits, and has not been tested with every agent advertised by the platform.

    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 buying a skill.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Software
    Codex
    Optional
    Web browsing for real people
    orspecific events

    Designed for Codex with imagegen. Image-model access and generation credits are separate. Other agents need equivalent image tools and reference-image support.

    Permissions

    Read Files
    Write Files
    Browser
    Network Access

    Reads the bundled SKILL.md, reference guides, and image assets; creates the requested image output. Web research is used when a real subject or specific event needs verification. Does not need shell access, environment variables, or unrelated personal files.

    Listedtoday

    What's inside

    Frequently Asked Questions

    The workflow combines saved visual references with guidance for character identity, focal subjects, shared timing, contact, motion, and lighting. It also asks the agent to review the whole scene and make focused corrections. Results depend on the image model and may require revision.

    The documented workflow uses Codex with access to the imagegen skill and an image-generation tool. Other SKILL.md agents need equivalent image tools and support for inspecting and sending reference images. Compatibility with every model or agent has not been verified.

    Yes. Describe the person or provide a suitable reference image. The workflow aims to preserve defining facial features, clothing, equipment, and colors while applying the rounded shapes, clear outlines, and flat colors of the cartoon references.

    The package contains SKILL.md, interface metadata, three style-reference images, a preview, an approved composition example, and detailed guides to scene coherence, motion, and lighting. It matches the skill folder in the creator's GitHub repository. Image-model access and generation credits are separate.

    The review workflow checks character identity, anatomy, physical support, contact, spatial relationships, readable background participants, and lighting. It guides revisions but does not guarantee an error-free image.

    This is a one-time purchase of the current skill package. Future updates may be offered, but no ongoing update or maintenance commitment is included. Access to third-party image-generation tools is separate.

    New in Image & Video