More screenshots

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Product design using AI

    1

    An end-to-end product design orchestrator that models experience flows and validates rendered UI against project context.

    $9.99

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned
    Product design using AI

    Product design using AI

    Example session with this skill installed

    Design an end-to-end experience for a developer-focused API monitoring dashboard. The user needs to see real-time error spikes and trace them to specific endpoints.

    • Read your context and instructions
    • Compiled the product design using
    • Generated the UI component

    I have established the project context for the API monitoring dashboard, focusing on high-density data visualization and rapid incident response. I've modeled the flow from initial alert orientation to deep-dive trace analysis, ensuring state persistence during filtering.

    Visual Direction: Technical Density

    ElementSpecificationRationale
    Visual ThesisHigh-density utilityPrioritizes data throughput for expert users over aesthetic whitespace.
    TypographyJetBrains Mono (Data), Inter (UI)Monospaced fonts for error codes and timestamps ensure alignment and readability.
    Color Palette#0F172A (Bg), #F8FAFC (Text), #EF4444 (Alert)High-contrast dark mode to reduce eye strain during prolonged monitoring.
    Signature Element"Pulse" SparklinesProvides immediate 60-second history without needing to open full charts.

    Experience Model & States

    {
      "intent": "Identify and isolate API failures",
      "states": {
        "idle": "Real-time stream of success/warning/error pings",
        "focused": "Endpoint specific filtering with active trace log",
        "error_recovery": "Automatic retry of failed trace fetches with toast notification"
      },
      "breakpoints": {
        "desktop": "4-column grid: Sidebar, Metrics, Trace Log, Details Pane",
        "mobile": "Single column: Prioritize Alert Feed and Critical Toggle"
      }
    }
    

    Implementation Strategy

    1. Context View: Use a CSS Grid layout to maintain a fixed sidebar for environment switching (Prod, Staging, Dev).
    2. Data Handling: Implement a virtualized list for the trace log to handle 10,000+ entries without UI lag.
    3. Accessibility: Ensure all error status icons have aria-label descriptions and maintain a 7:1 contrast ratio.

    Next steps

    • Review the proposed interaction model for the trace-to-code navigation.
    • Validate the "Technical Density" visual direction against your existing brand library.
    • Execute the validate_context.py script to persist these requirements.

    product-design-using-ai.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

    Design a new product feature from a brief including research and prototyping.Redesign complex user flows to improve conversion and state management.Generate validated visual directions for new technical interfaces.Inspect rendered designs for accessibility and interaction defects.

    About this skill

    This skill is an end-to-end product design orchestrator for developers who need to move from a brief to a validated interface without losing project context. It eliminates the problem of "hallucinated" design decisions by forcing a structured workflow that separates facts from inferences and requires research before styling.

    What it does

    • Project context modeling builds a validated map of constraints, evidence, and user decisions to ensure design continuity.
    • Evidence-backed research synthesizes market context and competitor behavior into actionable design implications rather than just links.
    • Experience architecture defines user intent, state requirements, failure paths, and object relationships before any UI is drawn.
    • Visual thesis development creates distinct aesthetic directions evaluated by task fit, implementation cost, and accessibility risk.
    • Rendered inspection validates the final output against interaction, overflow, and console failures to ensure production readiness.

    How it works

    1. Initialize the project context using the provided schema to lock in known facts and existing decisions.
    2. Execute search via the bundled Python scripts to retrieve focused design guidance and empirical evidence for the specific problem space.
    3. Model the flow by defining the information architecture, required permissions, and success/recovery states.
    4. Inspect and correct the rendered artifacts to fix visibility or accessibility issues before final delivery.

    Frameworks & tools

    The skill utilizes Python-based validation scripts, JSON schemas for context persistence, and standard web technologies for rendered output. It is designed to work within environments like Claude Code or Cursor where local script execution and file system access are available.

    Why this beats prompting it yourself

    Standard prompts often produce generic, "fashionable" screens that ignore technical constraints or edge cases. This skill enforces a rigorous design engineering process that treats UI as a functional system, ensuring every component has a documented reason for existing based on retrieved research and state modeling.

    Use cases

    • End-to-end feature creation from a raw product brief to a validated, high-fidelity prototype.
    • Complex flow redesign to resolve user friction while preserving existing brand and technical constraints.
    • Experience modeling for expert tools or dashboards where data density and state management are critical.

    Known limitations

    Requires a local Python environment to run context validation and search scripts. Not intended for isolated audits or simple component styling where specialist skills are more efficient.

    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 2 days ago

    • Passed all security checks, Safe to install

    Needs access to

    Json Schema
    Ariosity

    Listed2 days ago

    What's inside

    Frequently Asked Questions