Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    bimshi knitwear store analytics

    1

    Manage knitwear inventory and generate threshold-based stock analytics using a mock Python orchestrator.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    bimshi knitwear store analytics

    Example session with this skill installed

    Check the current stock for 'Men's Wool Sweater' and generate an inventory insight report to see if we need to restock anything.

    • Read your context and instructions
    • Compiled the bimshi knitwear store

    I have retrieved the current inventory levels and generated the analytics report from the BIMSHI orchestrator.

    Inventory Status and Insights

    MetricValue
    Current Stock: Men's Wool Sweater12 pieces
    Total Items in Store145 pieces
    Men's Items Total42 pieces
    Women's Items Total68 pieces
    Kids' Items Total35 pieces
    Fast-Selling Items (<=20 pcs)Men's Wool Sweater, Women's Cardigan
    Slow-Selling Items (>40 pcs)Women's Cotton Scarf
    Restock Recommendation (<15 pcs)Men's Wool Sweater

    Next steps

    1. Use Orchestrator.update_stock("Men's Wool Sweater", 20) to add stock for the recommended item.
    2. Verify the inventory.json file to ensure the update persisted.
    3. Check the Women's Cardigan status, as it is approaching the restock threshold.

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

    About this skill

    Managing knitwear inventory through manual JSON edits or basic spreadsheets leads to stockouts and tracking errors. This skill provides a specialized agent interface to interact with the BIMSHI inventory demo, allowing you to manage stock levels and generate category-based analytics via a mock orchestration layer.

    What it does

    • Inventory Inspection retrieves the full current stock list from the local JSON store.
    • Stock Updates modifies quantities for existing items or creates new entries using signed integers.
    • Categorized Summaries calculates stock totals specifically for Men, Women, and Kids product lines.
    • Threshold Analysis identifies fast-selling and slow-selling items based on fixed quantity triggers.
    • Restock Logic flags products falling below the 15-piece threshold for immediate attention.

    How it works

    1. Load Context by connecting the agent to the Orchestrator in agent/mock_orchestrate.py.
    2. Execute Commands using get_inventory() for lookups or update_stock() for adjustments.
    3. Generate Insights by triggering the AnalyticsAgent to process current JSON data.
    4. Confirm Changes by verifying product names and signed quantities before the orchestrator writes to disk.

    Frameworks & tools

    Python, Streamlit, Pandas, and Numpy. The system relies on a local inventory.json file for persistence and a mock orchestration pattern for agent communication.

    Why this beats prompting it yourself

    Standard prompts lack the logic to interface with specific Python orchestrator methods and local file structures. This skill is grounded in the BIMSHI architecture, ensuring it follows the demo's specific threshold rules and inventory schemas without inventing stock data.

    Use cases

    • Update inventory levels after a physical stock count.
    • Generate a restocking report for items under 15 pieces.
    • Compare stock distribution between Men's and Women's knitwear categories.
    • Identify overstocked "slow-selling" items with more than 40 units.

    Known limitations

    This is a local demo using fixed thresholds, not predictive AI or real-time POS integration. It does not enforce a non-negative stock floor and uses an empty sales CSV.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    • Uses sample inventory data stored locally in a JSON file.
    • Does not connect to live POS, ERP, supplier, or e-commerce systems.
    • Does not calculate actual sales velocity or provide predictive sales forecasting.
    • Requires a local Python environment with the project's dependencies installed.
    • Stock updates should be verified against physical inventory records.
    • This is a demonstration project, not a production-ready inventory 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
    Python

    Requires a local copy of the BIMSHI project and a Python environment with the required dependencies installed. Uses locally stored JSON inventory data. Does not include live POS, ERP, supplier, or external e-commerce integrations.

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    agent/**
    Listedtoday

    What's inside

    Frequently Asked Questions

    BIMSHI provides a structured Python-based workflow for inspecting knitwear inventory, updating stock quantities, and generating inventory summaries through a mock Orchestrator. It applies predefined thresholds to identify low-stock items below 15 pieces and highlight products with more than 40 pieces. This helps organize routine inventory reviews without manually editing JSON files. All inventory data is stored locally.

    The package includes the core `AnalyticsAgent` logic, the `mock_orchestrate.py` file for system communication, a sample `inventory.json` file, and a Streamlit dashboard interface for visualizing your stock data.

    This skill is designed to work within a Python environment; once you load the orchestrator, you can interface with it using any LLM or agent framework capable of executing Python functions and maintaining state.

    Yes, while it excels at tracking Men, Women, and Kids knitwear, you can add any product to the `inventory.json` file, and the analytics agent will process the metadata as long as it follows the established schema.

    No, this is a local analytics tool centered on a mock orchestration pattern; it is designed for inventory forecasting and manual updates rather than direct API integration with live retail software.

    Setup requires a local Python installation with the Pandas and Numpy libraries; simply connect your agent to the provided orchestration script to begin auditing and updating your inventory data.

    New in Agents & Orchestration