game design prototyping companion

    1

    Track game design iterations, document branching decisions, and generate visual SVG evolution maps of your prototypes.

    $5

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned

    Works with the AI tools you already use

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

    game design prototyping companion

    Example session with this skill installed

    We just tested a high-speed dashing mechanic for our platformer. It felt responsive but broke the level collisions at high velocities. We chose to tune it down, but I want to log the branches.

    • Read your context and instructions
    • Compiled the game design prototyping
    • Generated the UI component

    I have logged the results of the high-speed dashing prototype and mapped the resulting branches. The high-velocity version is now parked as a potential "Super Mode" if we solve the collision detection issues later.

    Prototype Evolution Log

    FieldDetails
    Node IDP-042-DASH
    QuestionDoes increasing dash velocity by 50% improve game feel without breaking geometry?
    SimulatedModified PlayerController.cs dash_multiplier from 1.5 to 2.25.
    LearnedGame feel improved significantly, but collision detection failed on 1-unit thick walls.
    Result StateBranch Trigger

    Branch Record

    Branch B-042-A (Chosen): Tuned Dash (1.75x). Balanced feel with collision stability. Currently the

    Baseline.
    *

    Branch B-042-B (Parked): Ultra Dash (2.25x). Great feel, but requires "Continuous Collision Detection" or thicker walls. Revisit if we refactor physics.
    *

    Branch B-042-C (Dead End): Dash-Teleport. Tested as a workaround for collisions; felt jarring and broke platforming flow.

    Decision State Summary

    • Current Path: Tuned Dash (B-042-A).

    Backtrack Logic: Re-evaluate B-042-B if the level design moves toward thicker, modular assets or if we switch to a 2.5D physics engine.

    Next steps

    1. Update references/branch-map.json with Node P-042.
    2. Run scripts/branch_map_svg.py to update the visual evolution map.
    3. Apply the 1.75x multiplier to the main dev branch.

    game-design-prototyping-companion.tsx

    TSX · React component

    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

    Document prototype branches to prevent repeating failed experiments.Generate SVG maps to visualize the evolution of game mechanics.Define backtrack conditions for parked design ideas.Maintain a structured log of design decisions and learned outcomes.

    About this skill

    The problem

    Game design prototypes often result in branching paths where valid ideas are discarded or forgotten. Teams lose critical institutional knowledge when they only document the "winning" iteration and erase the context of dead ends or parked concepts.

    What it does

    • Logs specific prototype nodes including the core question, simulation method, and key findings.
    • Tracks branching evolution by categorizing results as baseline, promising, dead ends, or parked.
    • Documents explicit backtrack logic to identify when a previously abandoned path should be revisited.
    • Generates visual SVG branch maps from JSON data to map out the evolution of game mechanics over time.
    • Preserves design memory by treating rejected paths as intelligence rather than failures.

    Frameworks & tools

    Python (for SVG generation scripts), JSON (for branch-map data structures), and SVG for visualization.

    Why this beats prompting it yourself

    Standard LLMs tend to focus only on the current solution, often losing the history of why certain paths were abandoned. This skill enforces a tree-based documentation structure that treats design history as a searchable asset, ensuring you never repeat the same failed experiment twice.

    Use cases

    • Mapping the evolution of a combat system from turn-based to real-time.
    • Tracking failed UI experiments to prevent future design regression.
    • Managing "what-if" scenarios for complex narrative branching.
    • Onboarding new designers by showing the technical history of a mechanic.

    Known limitations

    Requires a specific JSON format for visual map generation and relies on the presence of a local Python execution environment for SVG rendering.

    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 12 days ago

    • Passed all security checks, Safe to install

    Listed12 days ago

    What's inside

    Frequently Asked Questions