More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    mixmatter

    1

    Reconstructs photographs into contemporary editorial print compositions using source-aware graphic disassembly.

    $6

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    mixmatter

    mixmatter

    Example session with this skill installed

    Transform this photograph of the Brooklyn Bridge using MixMatter. Preserve its recognizable architectural features, reconstruct the composition using halftone, flattened graphic forms, and tactile collage. Derive the color palette from the original image. Do not add new text.

    • Read your context and instructions
    • Compiled the mixmatter

    I have analyzed the source image of the Brooklyn Bridge, identifying the suspension cables and the gothic arches as the primary structural anchors. I am reconstructing the composition by compressing the depth between the bridge and the Manhattan skyline, using a bold duotone palette derived from the sunset highlights and water shadows.

    MixMatter Reconstruction: Brooklyn Bridge

    Structural Anchors: Suspension cable diagonals, Granite tower arches.
    Visual States: Halftone (Sky/Water), Graphic (Towers), Photographic (Cable fragments).
    Palette: Deep Cobalt, Burnt Umber, Ochre, Off-White.

    [Agent invokes image tool with the following logic: Reconstruct source image by isolating bridge towers as flat graphic planes. Apply heavy halftone textures to the river and sky regions. Deconstruct the cable grid into overlapping geometric fragments. Palette: #0047AB, #8B4513, #CC7722. Aspect ratio: 1:1. No new text.]

    Next steps

    Increase Intensity: I can push the "Collaged" state further if you want more torn-paper edges and interrupted continuity.

    • Shift Palette: We can re-derive the colors from a different region of the source, such as the city lights.

    Change Composition: I can focus exclusively on a tight crop of the stone textures while maintaining the bridge's identity.

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

    About this skill

    Your image generation tools often produce generic filters or predictable "artistic" styles that lose the soul of the original photo. MixMatter solves this by treating your source imagery as raw material for a structural reconstruction. Instead of applying a blanket overlay, it disassembles the photograph into architectural anchors and graphic components, then rebuilds them into a contemporary editorial print composition.

    What it does

    • Source-Aware Reconstruction preserves the semantic identity of specific landmarks or figures while radically altering the visual structure.
    • Multi-State Rendering assigns distinct treatments like halftone, duotone, and flattened graphic fields to specific regions of the same image.
    • Structural Disassembly breaks photos into 3-7 meaningful layers—architecture, background, and light masses—to create new visual hierarchies.
    • Source-Text Protection handles existing signage and text as textural fragments or protected anchors rather than generating hallucinations.
    • Art Direction Briefing generates high-fidelity prompts optimized for image models when direct rendering is unavailable.

    How it works

    1. Analyze the attached photograph to identify 1-3 structural anchors that must remain recognizable.
    2. Deconstruct the scene into separate graphic elements like textures, shadows, and subjects.
    3. Recompose the image using deliberate cropping, planar overlap, and compressed depth to move away from standard camera composition.
    4. Materialize the result using your host's image generation tools or return a specific editing brief if the host lacks vision-to-image capabilities.

    Frameworks & tools

    This skill is designed for image-capable LLMs and AI assistants like Claude or GPT-4. It interfaces with native image generation tools (DALL-E, Midjourney, or Stable Diffusion via MCP) to transform visual inputs.

    Why this beats prompting it yourself

    Standard prompts often result in "scrapbook" aesthetics or generic filters that ignore the specific geometry of your photo. This skill enforces a strict source-aware contract that maintains structural integrity while applying sophisticated editorial print techniques that simple prompts cannot consistently replicate.

    Use cases

    • Transform architectural photography into bold, high-contrast graphic prints.
    • Reconstruct street scenes into contemporary duotone collage layouts.
    • Convert portraiture into flattened, source-derived color fields for editorial use.
    • Revise existing AI-generated art to increase graphic intensity and structural complexity.

    Known limitations

    Requires a source image to function; it cannot generate scenes from scratch. Output quality depends on the host's ability to maintain source consistency during generation.

    Requires a user-supplied source image. Cannot generate images from text-only prompts. Does not include a standalone image processing engine; relies on host tools.

    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

    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 1 month ago

    Permissions

    Read Files

    MixMatter reads user-provided images and its bundled reference files. Image generation and editing are handled by the host agent's available tools. No external account, API key, shell execution, or direct network access is required.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    MixMatter analyzes the source image, identifies defining visual structures, and reconstructs the composition through cropping, graphic reduction, selective halftone, duotone, and tactile collage. Each result is guided by the original image rather than a fixed visual preset.

    MixMatter follows the Agent Skills format and is designed for compatible hosts such as Claude Code and Codex. For direct image output, the host must provide image-generation or image-editing capabilities. Otherwise, MixMatter delivers a source-specific editing brief that can be used with an image model.

    MixMatter requires a user-supplied source image. Its workflow analyzes and reconstructs existing visual material while preserving recognizable features. It is designed for image-to-image transformation rather than generating unrelated images from text alone.

    The free package includes the MixMatter Agent Skill, its image-reconstruction instructions, visual guidance, quality-evaluation criteria, and usage examples. No separate MixMatter subscription, API key, or backend is required. Availability and costs of image-generation tools depend on the host platform.

    MixMatter aims to preserve important source text and signage when they contribute to the image's identity. It adds no new text by default and instructs the host to avoid invented, translated, or duplicated lettering. Exact text reproduction depends on the image model and cannot be guaranteed.

    New in Image & Video