skill

genpark-zero-query-inspiration-graph-matcher-skill

GenPark Zero-Query Inspiration Graph Matcher - Eliminates search boxes by transforming ambient visual wallpapers and lifestyle scenes into high-converting retail product recommendations.

alphaparkinc/genpark-zero-query-inspiration-graph-matcher-skillcommunitylistedunreviewed

Use skill

Set up

Skills are installed by placing their folder where your agent loads skills.

Download ZIP from GitHub Open the repository

The download comes from github.com/alphaparkinc/genpark-zero-query-inspiration-graph-matcher-skill itself, not from our server, so what you get is exactly what its author published.

Install instructions come from the README

Skills do not use an MCP config. Follow the steps in the README below.

README

synced Oct 28, 2026

genpark-zero-query-inspiration-graph-matcher-skill

Executive Overview & Architectural Motivation

Following the strategic investment by L Catterton (the premier consumer-focused private equity firm managing ~$40B in assets, backed by LVMH) in GenPark (backed by InMobi, Google, and Jio), digital commerce is undergoing an epochal shift from reactive search-box queries to ambient, inspiration-led agentic discovery.

GenPark transforms the smartphone lock screen ("Screen Zero") and ambient connected screens into zero-friction, generative shopping portals. This skill library distills the core mathematical logic and agent orchestration models powering this ecosystem:

Zero-Friction Discovery: Instantaneous micro-moment interactions without unlocking devices.
Generative Aesthetics & Try-On: Context-aware outfit synthesis and visual matching.
Multi-Touch Ambient Attribution: Cross-surface state tracking across mobile lock screens and smart displays.
Enterprise Protocol Parity: Full native Model Context Protocol (MCP) compliance for agentic runtime integration.

Architecture Diagram

flowchart TD
    subgraph ScreenZero["Screen Zero (Lock Screen Ambient Layer)"]
        Wake[Device Wake Event] --> Gaze[Gaze & Dwell Detector]
        Gaze --> Sensor[Circadian & Ambient Context]
    end

    subgraph AgentCore["GenPark AI Agent Intelligence Core"]
        Sensor --> CoreEngine["GenParkZeroQueryInspirationGraphMatcher"]
        CoreEngine --> DecisionEngine[Multi-Signal Mathematical Inference]
        DecisionEngine --> OutputPayload[Personalized Shopping Action / MCP Response]
    end

    subgraph RetailEcosystem["L Catterton & Retail Media Network"]
        OutputPayload --> Brands[Luxury / DTC / Fashion Brands]
        OutputPayload --> Checkout[1-Tap Cross-Surface Conversion]
    end

Technical Specifications & Features

Capability	Specification
Runtime Environment	Python 3.9+ (Standard Library Only)
External Dependencies	None (0 packages)
Protocol Compatibility	Anthropic Model Context Protocol (MCP) STDIO JSON-RPC 2.0
Architecture Paradigm	Pure Functional & Mathematical Modeling
Deployment Mode	Headless Agent Skill, CLI Client, or MCP Server

Quickstart & Usage

1. Direct Python Client Execution

python example_usage.py

2. Standalone MCP Server Launch

Run the native STDIO MCP server for Claude Desktop, Cursor, or Antigravity integration:

python mcp_server.py

3. Model Context Protocol (MCP) Config

Add to your claude_desktop_config.json or agent runner config:

{
  "mcpServers": {
    "genpark-zero-query-inspiration-graph-matcher-skill": {
      "command": "python",
      "args": ["path/to/genpark-zero-query-inspiration-graph-matcher-skill/mcp_server.py"]
    }
  }
}

Frequently Asked Questions (FAQ)

Q1: What makes GenPark AI Shopping Agent Skills unique?

Engineered with zero external dependencies using pure Python standard library code. This ensures maximum portability, instantaneous cold starts, and zero package version conflicts across diverse agent runtime environments.

Q2: How do I test this MCP server locally?

Run python mcp_server.py --test to verify MCP protocol discovery and tool schema negotiation.

License

This project is licensed under the MIT License - see the LICENSE file for details.