Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    retail basket affinity analyst

    1

    Analyzes transaction baskets to identify product affinity patterns. Computes association rules with support, confidence, and lift metrics to find co-purchased items and cross-sell opportunities.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    retail basket affinity analyst

    retail basket affinity analyst

    Example session with this skill installed

    Analyze these 500 transactions to find product affinities. Use a min_support of 0.02 and min_lift of 1.2. Identify the top cross-sell opportunities.

    • Read your context and instructions
    • Compiled the retail basket affinity

    Analysis of 500 transaction records is complete. I have identified 12 significant association rules meeting your thresholds.

    Market Basket Analysis Results

    1. Summary

    MetricValue
    Transactions analyzed500
    Unique items142
    Unique pairs observed864
    Association rules12
    Average basket size3.4

    2. Association Rules

    AntecedentConsequentSupportConfidenceLift
    ORGANIC_BANANASWHOLE_MILK0.04200.32001.8500
    AVOCADOLIME0.02800.45002.1000
    COFFEE_BEANSPAPER_FILTERS0.02100.68004.2500
    PASTA_SAUCESPAGHETTI0.03500.52003.1500

    3. Top Product Pairs

    Product AProduct BPair CountSupportLift
    COFFEE_BEANSPAPER_FILTERS110.02104.2500
    PASTA_SAUCESPAGHETTI180.03503.1500
    AVOCADOLIME140.02802.1000

    4. Findings

    High Affinity Bundle: COFFEE_BEANS and PAPER_FILTERS show a lift of 4.25, indicating a very strong logical pairing for a morning routine bundle.

    • Cross-Sell Opportunity: PASTA_SAUCE and SPAGHETTI have high confidence (0.52). Consider a "Meal Kit" promotion.

    Fresh Produce Link: AVOCADO and LIME show significant lift (2.10), suggesting these should be merchandised in close proximity.

    Next steps

    1. Validate the COFFEE_BEANS affinity against current inventory levels for bundling.
    2. Review the PASTA_SAUCE findings to see if specific brands drive higher confidence.
    3. Apply these rules to your recommendation engine for the "Frequently Bought Together" section.

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

    About this skill

    Retailers often struggle to identify which products are actually bought together versus what they assume is paired. This skill automates market basket analysis to find hidden product affinities and cross-sell opportunities using transaction data.

    What it does

    • Association Rule Mining calculates support, confidence, and lift metrics for product pairings.
    • Cross-Sell Identification highlights strong affinities that suggest effective bundling or placement strategies.
    • Basket Composition Analysis reports on average basket size and unique item distribution across transactions.
    • Rule Ranking filters and sorts co-purchase patterns by statistical strength to prioritize merchandising focus.

    How it works

    1. Prepare a JSON request containing transaction records with unique IDs and lists of product IDs.
    2. Configure optional thresholds for minimum support, confidence, and lift to filter out noise.
    3. Execute the analysis via the provided Python script to process the transaction data.
    4. Review the generated summary table and association rules to identify high-lift product pairs.

    Frameworks & tools

    The skill uses a Python-based execution environment to run deterministic association rule mining scripts. It processes structured JSON transaction data.

    Why this beats prompting it yourself

    Manual prompting often leads to hallucinated patterns or incorrect statistical calculations for lift and confidence. This skill uses a deterministic script to ensure every metric is mathematically accurate and reproducible across thousands of transactions.

    Use cases

    • Identify products for "Frequently Bought Together" website sections.
    • Optimize physical store layouts by placing high-affinity items near each other.
    • Design promotional bundles based on statistically significant co-purchase rates.
    • Discover unexpected product relationships that contradict gut-feeling merchandising.

    Known limitations

    Requires consistent product identifiers across all transactions. Analysis is limited to association patterns and does not account for external factors like seasonality or active promotions.

    Requires consistent product IDs. Does not account for seasonality or active promotions. Analytical estimates require business validation.

    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 today

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables
    Listedtoday

    What's inside

    Frequently Asked Questions

    The skill requires a structured JSON file containing unique transaction IDs and lists of associated product identifiers. You can also customize the analysis by setting thresholds for support, confidence, and lift to filter for the most meaningful patterns.

    Unlike LLM prompting, which can hallucinate correlations or fail at complex math, this skill uses deterministic Python scripts. This ensures that every 'lift' and 'confidence' score is mathematically precise and reproducible across large datasets.

    Yes, this skill is designed to work within any AI agent environment that supports Python execution. It can be integrated into your existing data workflows or used as a standalone analytical tool for retail research.

    You will receive the core Python analysis script, documentation on data formatting, and a guide on interpreting metrics like lift and confidence to inform your merchandising strategy.

    The current version focuses on identifying purchase correlations within a single dataset. It does not currently factor in external variables like seasonal trends, specific marketing campaigns, or chronological purchase sequences.