Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Analytics Engineering Pro — Trusted Business Models

    1

    Turn raw tables into tested, documented, and consistent analytics models, metrics, and marts.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Analytics Engineering Pro — Trusted Business Models

    Analytics Engineering Pro — Trusted Business Models

    Example session with this skill installed

    We need a trusted daily net revenue mart for ecommerce orders. Warehouse is PostgreSQL-compatible, but verify dialect assumptions. Example source schemas supplied:

    orders(order_id, customer_id, order_ts_utc, status, currency, updated_at)
    order_lines(order_id, line_id, sku, quantity, unit_price, discount_amount, refunded_amount, updated_at)

    Business definition: paid and partially refunded orders count; cancelled and test orders do not. Net line revenue = quantity * unit_price - discount_amount - refunded_amount. Report in USD, but source currency conversion table and rate date are not provided. An order may have multiple lines; orders.status can change; late corrections arrive up to 7 days after order date. We need daily revenue by order date and SKU, with a 7-day incremental lookback. Identify missing semantics, define grain and joins, draft SQL models and tests, explain how to avoid fanout, and give backfill/validation/rollback steps. Do not assume an FX rate or make up column values.

    • Read your context and instructions
    • Compiled the analytics engineering pro

    Trusted Revenue Mart — Design Review

    Decision and contract

    Consumer: daily SKU revenue reporting.

    Metric: net line revenue for paid or partially refunded orders; exclude cancelled/test orders.

    Time: UTC order date until a business reporting timezone is chosen.

    Currency: USD output is blocked until an authoritative FX source, rate date, and conversion policy are supplied. Do not label unconverted source-currency totals as USD.

    Grain: one row per order_id × line_id in the core fact; one row per order_date × sku × currency in the aggregate mart until conversion is defined. order_lines is line grain; join to orders on order_id only after checking uniqueness of orders.order_id. Do not join line rows directly to other one-to-many tables such as payments or refunds without first aggregating each relation to the intended key.

    Draft transformation (PostgreSQL-style; validate types and dialect)

    -- stg_order_lines: preserve source line grain and source currency
    select order_id, line_id, sku, quantity, unit_price,
           discount_amount, refunded_amount, updated_at as source_updated_at
    from raw.order_lines;
    
    -- fct_order_line_revenue: one row per order_id + line_id
    select o.order_id, l.line_id, o.customer_id, l.sku,
    
               o.order_ts_utc::date as order_date_utc,
               o.currency as source_currency,
               l.quantity * l.unit_price
    
             - coalesce(l.discount_amount, 0)
             - coalesce(l.refunded_amount, 0) as net_revenue_source_currency,
           greatest(o.updated_at, l.source_updated_at) as updated_at
    from stg_order_lines l
    join raw.orders o using (order_id)
    where o.status in ('paid', 'partially_refunded')
      and coalesce(o.is_test, false) = false;
    

    is_test is not in the supplied schema, so the predicate is an explicit contract gap: confirm the authoritative test-order field before implementation. Confirm whether discounts/refunds are line-level, whether negative net lines are valid, how status history is retained, and whether order date means purchase, payment, or fulfillment time. If status is overwritten, use a reliable updated timestamp and a 7-day reprocessing window; late changes outside the lookback need a monitored exception/backfill path.

    Aggregate and controls

    Aggregate only after the core fact passes uniqueness at (order_id, line_id). Group by UTC order date, SKU, and source currency; apply FX later using the approved rate-date policy. Candidate tests: unique/not-null order and line keys; accepted order statuses; nonnegative quantity (confirm returns); revenue arithmetic reconciliation to source at the same grain; relationship test for every order; freshness on updated_at; currency accepted values; and a fanout row-count/revenue comparison before and after joins.

    Incremental, deployment, and rollback

    Use updated_at watermark with a 7-day lookback, deduplicate changed source keys deterministically, and merge by (order_id, line_id). Test a representative historical backfill, compare row counts and revenue by date/currency to the source, and record known exclusions. Deploy behind a versioned model or parallel table; compare outputs with consumers, then switch the semantic reference. Roll back by restoring the prior model/version and retain the new output for investigation. Document owner, contract version, lineage, freshness SLA, access/PII review, and change notice before production use.

    Open blockers: authoritative test-order indicator; source uniqueness/history; refund and discount semantics; currency conversion authority/date; business timezone; accepted quantity and negative-revenue rules; SQL dialect/type details. No production SQL or USD KPI should be certified until resolved.

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

    About this skill

    Analytics Engineering Pro turns business decisions and metric semantics into dependable, maintainable data products. It works vendor-neutrally across warehouses, lakehouses, SQL transformation frameworks, orchestration tools, catalogs, semantic layers, BI platforms, and version-controlled analytics projects.

    The agent starts by establishing the decision, metric definition, source authority, grain, keys, relationship cardinality, history, event and load times, units, currency, time zone, ownership, and consumers. It designs staging, intermediate, core, mart, and semantic layers only where they clarify responsibility. It defines facts, dimensions, snapshots, bridges, slowly changing dimensions, and canonical measures while guarding against fanout, double counting, metric drift, inconsistent filters, and duplicated business logic.

    It produces readable deterministic transformations, suitable incremental and backfill strategies, data contracts, tests for real failure modes, documentation that explains business meaning, lineage and change-impact notes, privacy/access considerations, and BI-ready semantic definitions. It addresses freshness, schema evolution, observability, performance, warehouse cost, CI, deployment, migration, validation, and rollback—preserving metric correctness before optimization.

    The agent never invents schemas, business definitions, access, performance results, or guaranteed outcomes. When source structure or metric semantics are missing, it calls out assumptions and requests only details that affect correctness. Validate generated SQL against your warehouse dialect, permissions, data contracts, and production environment before deployment. It does not run migrations or deploy changes unless the user explicitly authorizes that action.

    Output correctness depends on accurate source schemas, keys, history, metric definitions, and business rules. Generated SQL is a design draft and may need changes for the warehouse dialect, framework version, permissions, data volume, and runtime behavior. Tests cannot prove data correctness if contracts or expected values are wrong. Incremental lookbacks may miss late changes outside the chosen window unless monitoring and backfill paths exist. Performance and cost must be measured in the target environment. Production deployment, regulatory/privacy review, and metric ownership require the user's organization and authorized reviewers.

    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 1 month ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    *.sql
    *.yml
    *.yaml
    *.md
    *.csv
    *.json
    *.toml

    Read and edit only user-authorized analytics project files. Validate SQL, framework syntax, data contracts, and permissions in a non-production environment. Do not access secrets, connect to production data, run destructive migrations, publish releases, or deploy without explicit authorization and a verified rollback plan.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Grain states exactly what one row represents, such as one order line or one customer-day. Declaring it before joining tables helps detect one-to-many joins that can multiply rows, inflate revenue, and break metrics. Each fact and aggregate should document its grain and key.

    The agent records each model's grain and key, checks relationship cardinality before joins, and recommends pre-aggregating one-to-many relations to the intended key. It defines canonical metric logic, filters, time grain, units, and aggregation behavior once, then adds uniqueness, relationship, reconciliation, and business-invariant tests around those definitions.

    It can draft model, test, migration, backfill, and rollback plans. Generated SQL must be validated against your warehouse and contracts. The agent does not deploy or run destructive production changes without explicit authorization, approved access, review, and a verified rollback plan.

    New in Data & Databases