@useatlas/create 0.0.5 → 0.0.7

package/templates/nextjs-standalone/data/cybersec.sql

@@ -23,7 +23,7 @@ DROP TABLE IF EXISTS notifications_backup CASCADE;
 DROP TABLE IF EXISTS feature_flags_legacy CASCADE;
 DROP TABLE IF EXISTS temp_asset_import_2024 CASCADE;
 DROP TABLE IF EXISTS old_scan_results_v2 CASCADE;
-DROP TABLE IF EXISTS audit_log CASCADE;
+DROP TABLE IF EXISTS sec_audit_log CASCADE;
 DROP TABLE IF EXISTS integration_events CASCADE;
 DROP TABLE IF EXISTS integrations CASCADE;
 DROP TABLE IF EXISTS dashboard_widgets CASCADE;
@@ -72,7 +72,7 @@ DROP TABLE IF EXISTS invoices CASCADE;
 DROP TABLE IF EXISTS subscription_events CASCADE;
 DROP TABLE IF EXISTS subscriptions CASCADE;
 DROP TABLE IF EXISTS plans CASCADE;
-DROP TABLE IF EXISTS invitations CASCADE;
+DROP TABLE IF EXISTS sec_invitations CASCADE;
 DROP TABLE IF EXISTS team_memberships CASCADE;
 DROP TABLE IF EXISTS teams CASCADE;
 DROP TABLE IF EXISTS users CASCADE;
@@ -145,7 +145,7 @@ CREATE TABLE team_memberships (
     PRIMARY KEY (user_id, team_id)
 );
 
-CREATE TABLE invitations (
+CREATE TABLE sec_invitations (
     id              SERIAL PRIMARY KEY,
     organization_id INTEGER NOT NULL REFERENCES organizations(id),
     email           TEXT NOT NULL,
@@ -709,7 +709,7 @@ CREATE TABLE integration_events (
     created_at     TIMESTAMPTZ NOT NULL DEFAULT now()
 );
 
-CREATE TABLE audit_log (
+CREATE TABLE sec_audit_log (
     id              SERIAL PRIMARY KEY,
     organization_id INTEGER,         -- no FK (standalone audit)
     user_id         INTEGER,         -- no FK
@@ -810,8 +810,8 @@ CREATE INDEX idx_subscriptions_org ON subscriptions(organization_id);
 CREATE INDEX idx_compliance_findings_assessment ON compliance_findings(assessment_id);
 CREATE INDEX idx_api_requests_created ON api_requests(created_at);
 CREATE INDEX idx_login_events_user ON login_events(user_id);
-CREATE INDEX idx_audit_log_org ON audit_log(organization_id);
-CREATE INDEX idx_audit_log_created ON audit_log(created_at);
+CREATE INDEX idx_sec_audit_log_org ON sec_audit_log(organization_id);
+CREATE INDEX idx_sec_audit_log_created ON sec_audit_log(created_at);
 CREATE INDEX idx_scan_results_denorm_org ON scan_results_denormalized(organization_id);
 CREATE INDEX idx_scan_results_denorm_found ON scan_results_denormalized(found_at);
 
@@ -1016,7 +1016,7 @@ FROM (
 ) AS src;
 
 -- ---------- Invitations (150) ----------
-INSERT INTO invitations (organization_id, email, role_name, invited_by, status, created_at, expires_at)
+INSERT INTO sec_invitations (organization_id, email, role_name, invited_by, status, created_at, expires_at)
 SELECT
     1 + floor(random() * 200)::int,
     'invite' || g || '@example.com',
@@ -1859,7 +1859,7 @@ SELECT
 FROM generate_series(1, 5000) AS g;
 
 -- ---------- Audit Log (25,000) ----------
-INSERT INTO audit_log (organization_id, user_id, action, resource_type, resource_id, details, ip_address, created_at)
+INSERT INTO sec_audit_log (organization_id, user_id, action, resource_type, resource_id, details, ip_address, created_at)
 SELECT
     1 + floor(random() * 200)::int,   -- no FK
     1 + floor(random() * 2000)::int,  -- no FK

package/templates/nextjs-standalone/data/demo.sql

@@ -35,6 +35,9 @@ CREATE TABLE IF NOT EXISTS accounts (
   contract_end DATE
 );
 
+-- Ensure idempotent seeding (safe to re-run without doubling rows)
+TRUNCATE TABLE accounts, people, companies RESTART IDENTITY CASCADE;
+
 -- Seed data: 50 companies
 INSERT INTO companies (name, industry, employee_count, founded_year, country, revenue, valuation) VALUES
   ('Acme Corp', 'Technology', 450, 2010, 'US', 85000000, 340000000),

package/templates/nextjs-standalone/data/ecommerce-semantic/catalog.yml

@@ -0,0 +1,221 @@
+version: "1.0"
+name: NovaMart — E-Commerce DTC Brand
+description: |
+  Direct-to-consumer e-commerce marketplace dataset for NovaMart. Covers the full
+  lifecycle: product catalog with multi-seller marketplace, customer acquisition and
+  loyalty, orders and payments, shipping and fulfillment, returns, marketing campaigns,
+  product reviews, and inventory management. Use this dataset to explore revenue
+  analysis, conversion funnels, customer lifetime value, fulfillment performance,
+  marketplace seller health, and marketing attribution.
+
+  Note: The database contains 52 tables total, but 4 are legacy/abandoned
+  (old_orders_v1, temp_product_import_2023, legacy_analytics_events,
+  payment_methods_backup) and several are low-value junction or cache tables.
+  This semantic layer covers the 13 most important entities.
+
+entities:
+  - name: Customers
+    file: entities/customers.yml
+    grain: one row per customer
+    description: >
+      Registered customers with contact info, acquisition source, and activity status.
+      Central dimension for all customer-level analysis.
+    use_for:
+      - Customer segmentation by acquisition source
+      - Active vs inactive customer analysis
+      - Cohort analysis by signup date
+    common_questions:
+      - How many active customers do we have?
+      - What are our top acquisition channels?
+      - How has customer growth trended month over month?
+      - What percentage of customers are inactive?
+
+  - name: Products
+    file: entities/products.yml
+    grain: one row per product
+    description: >
+      Product catalog with pricing, category, seller, and status. Some products
+      have seller_id for marketplace items. price is in dollars; price_cents is
+      sometimes NULL.
+    use_for:
+      - Product catalog analysis by category and seller
+      - Pricing distribution and tier analysis
+      - Product status and lifecycle tracking
+    common_questions:
+      - How many active products do we have?
+      - What is the average product price by category?
+      - Which sellers have the most products listed?
+      - How many products have missing price_cents values?
+
+  - name: Categories
+    file: entities/categories.yml
+    grain: one row per category
+    description: >
+      Hierarchical product categories with self-referencing parent_id.
+      Used to organize the product catalog.
+    use_for:
+      - Category hierarchy navigation
+      - Product distribution across categories
+    common_questions:
+      - How many top-level categories exist?
+      - Which categories have the most products?
+
+  - name: Orders
+    file: entities/orders.yml
+    grain: one row per order
+    description: >
+      Customer orders with monetary totals (in cents), status, shipping address,
+      and optional promotion. shipping_cost uses mixed units (dollars and cents).
+    use_for:
+      - Revenue and GMV analysis
+      - Order status and fulfillment tracking
+      - Promotion impact analysis
+    common_questions:
+      - What is our total GMV this quarter?
+      - What is the average order value?
+      - What percentage of orders used a promotion?
+      - How does order volume trend by month?
+
+  - name: Order Items
+    file: entities/order_items.yml
+    grain: one row per line item in an order
+    description: >
+      Individual line items within orders. Contains product name (denormalized),
+      quantity, and pricing in cents. product_variant_id has no foreign key constraint.
+    use_for:
+      - Product-level revenue attribution
+      - Basket analysis and cross-sell patterns
+      - Average items per order
+    common_questions:
+      - What are the top-selling products by revenue?
+      - What is the average number of items per order?
+      - Which products are most frequently purchased together?
+
+  - name: Payments
+    file: entities/payments.yml
+    grain: one row per payment transaction
+    description: >
+      Payment transactions for orders. Multiple payments can exist per order
+      (split payments, retries). order_id has no foreign key constraint.
+    use_for:
+      - Payment method analysis
+      - Payment success/failure rate tracking
+      - Revenue reconciliation
+    common_questions:
+      - What is our payment success rate?
+      - Which payment methods are most popular?
+      - How much revenue is pending vs captured?
+
+  - name: Returns
+    file: entities/returns.yml
+    grain: one row per return request
+    description: >
+      Return requests with reason (case-inconsistent values), status, and
+      resolution timing. Linked to orders and customers.
+    use_for:
+      - Return rate analysis
+      - Return reason categorization
+      - Resolution time tracking
+    common_questions:
+      - What is our overall return rate?
+      - What are the most common return reasons?
+      - What is the average time to resolve a return?
+
+  - name: Shipments
+    file: entities/shipments.yml
+    grain: one row per shipment
+    description: >
+      Shipment tracking with carrier, warehouse origin, and delivery timestamps.
+      carrier is a text field; carrier_id has no foreign key constraint.
+    use_for:
+      - Fulfillment speed analysis
+      - Carrier performance comparison
+      - Warehouse throughput tracking
+    common_questions:
+      - What is our average delivery time?
+      - Which carrier has the best on-time rate?
+      - How does fulfillment time vary by warehouse?
+
+  - name: Sellers
+    file: entities/sellers.yml
+    grain: one row per marketplace seller
+    description: >
+      Third-party marketplace sellers with commission rates and status.
+      Products link to sellers via seller_id.
+    use_for:
+      - Marketplace seller health and performance
+      - Commission rate analysis
+      - Seller onboarding and retention tracking
+    common_questions:
+      - How many active sellers are on the marketplace?
+      - What is the average commission rate?
+      - Which sellers generate the most GMV?
+
+  - name: Promotions
+    file: entities/promotions.yml
+    grain: one row per promotion
+    description: >
+      Discount codes and promotions with type, value, usage tracking,
+      and validity period.
+    use_for:
+      - Promotion effectiveness analysis
+      - Discount impact on revenue
+      - Usage rate and capacity tracking
+    common_questions:
+      - Which promotions have the highest usage?
+      - What is the average discount value applied?
+      - How many promotions are currently active?
+
+  - name: Product Reviews
+    file: entities/product_reviews.yml
+    grain: one row per review
+    description: >
+      Customer product reviews with 1-5 rating, optional decimal rating
+      (70% NULL), title, body, and verification status.
+    use_for:
+      - Product quality and sentiment analysis
+      - Review volume and rating trends
+      - Verified vs unverified review comparison
+    common_questions:
+      - What is the average product rating?
+      - Which products have the lowest ratings?
+      - What percentage of reviews are verified purchases?
+
+  - name: Email Campaigns
+    file: entities/email_campaigns.yml
+    grain: one row per email campaign
+    description: >
+      Marketing email campaigns with type, status, and send date.
+      Linked to email_sends for per-recipient delivery tracking.
+    use_for:
+      - Campaign performance analysis (open rate, click rate)
+      - Campaign type comparison
+      - Send volume and cadence tracking
+    common_questions:
+      - What are our average open and click rates?
+      - Which campaign types perform best?
+      - How many campaigns did we send this month?
+
+  - name: Inventory Levels
+    file: entities/inventory_levels.yml
+    grain: one row per variant-warehouse combination
+    description: >
+      Current inventory quantities per product variant per warehouse.
+      variant_id has no foreign key constraint. Includes reorder point thresholds.
+    use_for:
+      - Stock level monitoring and low-stock alerts
+      - Inventory distribution across warehouses
+      - Reorder point analysis
+    common_questions:
+      - Which variants are below reorder point?
+      - What is total inventory by warehouse?
+      - How is stock distributed across locations?
+
+glossary: glossary.yml
+metrics:
+  - file: metrics/revenue.yml
+    description: Revenue metrics (GMV, AOV, revenue by category/channel, refund rate)
+  - file: metrics/customers.yml
+    description: Customer metrics (LTV, repeat rate, cohort retention, acquisition)
+  - file: metrics/operations.yml
+    description: Operations metrics (fulfillment time, return rate, inventory turnover)

package/templates/nextjs-standalone/data/ecommerce-semantic/entities/categories.yml

@@ -0,0 +1,91 @@
+name: Categories
+type: dimension_table
+table: categories
+grain: one row per category
+description: |
+  Hierarchical product categories for the NovaMart catalog. Categories can have a
+  parent_id pointing to another category (self-referencing) to form a tree structure.
+  Top-level categories have parent_id = NULL. Used to organize and navigate products.
+
+dimensions:
+  - name: id
+    sql: id
+    type: number
+    description: Primary key — unique category identifier
+    primary_key: true
+
+  - name: name
+    sql: name
+    type: string
+    description: Category display name
+    sample_values: [Electronics, Clothing, Home & Garden, Sports, Beauty]
+
+  - name: parent_id
+    sql: parent_id
+    type: number
+    description: |
+      Self-referencing foreign key to parent category.
+      NULL = top-level category.
+
+  - name: slug
+    sql: slug
+    type: string
+    description: URL-safe category identifier
+
+  - name: description
+    sql: description
+    type: string
+    description: Category description text
+
+  - name: created_at
+    sql: created_at
+    type: timestamp
+    description: When the category was created
+
+  - name: is_top_level
+    sql: CASE WHEN parent_id IS NULL THEN true ELSE false END
+    type: boolean
+    description: Whether this is a top-level (root) category
+    virtual: true
+
+measures:
+  - name: category_count
+    sql: id
+    type: count_distinct
+    description: Number of unique categories
+
+joins:
+  - target_entity: Categories
+    relationship: many_to_one
+    join_columns:
+      from: parent_id
+      to: id
+    description: Self-join to parent category for hierarchy traversal
+
+use_cases:
+  - Product catalog organization and navigation
+  - Revenue and sales analysis by category hierarchy
+  - Category-level inventory and stock analysis
+  - Join to products for category performance metrics
+
+query_patterns:
+  - name: top_level_categories
+    description: List all top-level categories with product counts
+    sql: |-
+      SELECT c.name AS category,
+             COUNT(p.id) AS product_count
+      FROM categories c
+      LEFT JOIN products p ON p.category_id = c.id AND p.status = 'active'
+      WHERE c.parent_id IS NULL
+      GROUP BY c.name
+      ORDER BY product_count DESC
+
+  - name: category_hierarchy
+    description: Categories with their parent category names
+    sql: |-
+      SELECT child.name AS category,
+             parent.name AS parent_category,
+             child.slug
+      FROM categories child
+      LEFT JOIN categories parent ON child.parent_id = parent.id
+      ORDER BY parent.name NULLS FIRST, child.name

package/templates/nextjs-standalone/data/ecommerce-semantic/entities/customers.yml

@@ -0,0 +1,133 @@
+name: Customers
+type: dimension_table
+table: customers
+grain: one row per customer
+description: |
+  Registered NovaMart customers. Contains contact information, acquisition channel,
+  and activity status. Each customer can have multiple orders, returns, reviews, and
+  loyalty transactions. This is the central dimension for all customer-level analysis.
+
+  Data quality note: acquisition_source has case inconsistencies (e.g. 'Organic' vs
+  'organic'). Use LOWER(acquisition_source) for reliable grouping.
+
+dimensions:
+  - name: id
+    sql: id
+    type: number
+    description: Primary key — unique customer identifier
+    primary_key: true
+
+  - name: email
+    sql: email
+    type: string
+    description: Customer email address — unique per customer
+
+  - name: full_name
+    sql: full_name
+    type: string
+    description: Customer full name
+
+  - name: phone
+    sql: phone
+    type: string
+    description: Primary phone number (landline or unspecified)
+
+  - name: mobile_phone
+    sql: mobile_phone
+    type: string
+    description: Mobile phone number — may differ from phone
+
+  - name: acquisition_source
+    sql: acquisition_source
+    type: string
+    description: |
+      How this customer was acquired. WARNING: case-inconsistent values.
+      Use LOWER(acquisition_source) for reliable grouping.
+    sample_values: [organic, paid_search, social, referral, email, direct]
+
+  - name: created_at
+    sql: created_at
+    type: timestamp
+    description: When the customer account was created (signup date)
+
+  - name: updated_at
+    sql: updated_at
+    type: timestamp
+    description: Last update to the customer record
+
+  - name: is_active
+    sql: is_active
+    type: boolean
+    description: Whether the customer is currently active
+
+  - name: acquisition_source_normalized
+    sql: LOWER(acquisition_source)
+    type: string
+    description: Acquisition source normalized to lowercase for consistent grouping
+    virtual: true
+    sample_values: [organic, paid_search, social, referral, email, direct]
+
+  - name: signup_month
+    sql: TO_CHAR(created_at, 'YYYY-MM')
+    type: string
+    description: Year-month the customer signed up — useful for cohort analysis
+    virtual: true
+
+  - name: signup_year
+    sql: EXTRACT(YEAR FROM created_at)
+    type: number
+    description: Year the customer signed up
+    virtual: true
+
+  - name: has_phone
+    sql: CASE WHEN phone IS NOT NULL OR mobile_phone IS NOT NULL THEN true ELSE false END
+    type: boolean
+    description: Whether the customer has any phone number on file
+    virtual: true
+
+measures:
+  - name: customer_count
+    sql: id
+    type: count_distinct
+    description: Number of unique customers
+
+  - name: active_customer_count
+    sql: CASE WHEN is_active THEN id END
+    type: count_distinct
+    description: Number of active customers
+
+use_cases:
+  - Customer segmentation by acquisition source and signup cohort
+  - Active vs inactive customer analysis and re-engagement targeting
+  - Growth tracking — new signups over time
+  - Join to orders for purchase behavior and LTV analysis
+  - Join to product_reviews for review engagement by customer segment
+
+query_patterns:
+  - name: customers_by_acquisition_source
+    description: Customer count by normalized acquisition channel
+    sql: |-
+      SELECT LOWER(acquisition_source) AS channel,
+             COUNT(*) AS customer_count,
+             COUNT(*) FILTER (WHERE is_active) AS active_count
+      FROM customers
+      GROUP BY LOWER(acquisition_source)
+      ORDER BY customer_count DESC
+
+  - name: customer_signups_by_month
+    description: Monthly signup trend
+    sql: |-
+      SELECT TO_CHAR(created_at, 'YYYY-MM') AS signup_month,
+             COUNT(*) AS new_customers
+      FROM customers
+      GROUP BY TO_CHAR(created_at, 'YYYY-MM')
+      ORDER BY signup_month
+
+  - name: active_vs_inactive_customers
+    description: Breakdown of active vs inactive customers
+    sql: |-
+      SELECT is_active,
+             COUNT(*) AS customer_count,
+             ROUND(100.0 * COUNT(*) / SUM(COUNT(*)) OVER (), 1) AS pct
+      FROM customers
+      GROUP BY is_active

package/templates/nextjs-standalone/data/ecommerce-semantic/entities/email_campaigns.yml

@@ -0,0 +1,119 @@
+name: Email Campaigns
+type: fact_table
+table: email_campaigns
+grain: one row per email campaign
+description: |
+  Marketing email campaigns sent to customers. Each campaign has a type (promotional,
+  transactional, newsletter, etc.), status, and send timestamp. Per-recipient delivery
+  details are in the email_sends table (campaign_id -> email_sends.campaign_id).
+
+dimensions:
+  - name: id
+    sql: id
+    type: number
+    description: Primary key — unique campaign identifier
+    primary_key: true
+
+  - name: name
+    sql: name
+    type: string
+    description: Internal campaign name
+
+  - name: subject
+    sql: subject
+    type: string
+    description: Email subject line
+
+  - name: type
+    sql: type
+    type: string
+    description: Campaign type/category
+    sample_values: [promotional, transactional, newsletter, abandoned_cart, welcome]
+
+  - name: status
+    sql: status
+    type: string
+    description: Campaign status
+    sample_values: [draft, scheduled, sending, sent, cancelled]
+
+  - name: sent_at
+    sql: sent_at
+    type: timestamp
+    description: When the campaign was sent (NULL if draft/scheduled)
+
+  - name: created_at
+    sql: created_at
+    type: timestamp
+    description: When the campaign was created
+
+  - name: sent_month
+    sql: TO_CHAR(sent_at, 'YYYY-MM')
+    type: string
+    description: Year-month the campaign was sent
+    virtual: true
+
+  - name: is_sent
+    sql: CASE WHEN status = 'sent' THEN true ELSE false END
+    type: boolean
+    description: Whether the campaign has been sent
+    virtual: true
+
+measures:
+  - name: campaign_count
+    sql: id
+    type: count_distinct
+    description: Number of unique campaigns
+
+  - name: sent_campaign_count
+    sql: CASE WHEN status = 'sent' THEN id END
+    type: count_distinct
+    description: Number of campaigns that have been sent
+
+use_cases:
+  - Campaign performance analysis — open rates, click rates (via email_sends join)
+  - Campaign type comparison — which types drive the most engagement
+  - Send cadence and volume tracking over time
+  - Campaign status pipeline — draft to sent
+  - Join to email_sends for per-recipient delivery metrics
+
+query_patterns:
+  - name: campaign_performance
+    description: Campaign open and click rates (requires email_sends join)
+    sql: |-
+      SELECT ec.name AS campaign,
+             ec.type,
+             ec.sent_at,
+             COUNT(es.id) AS total_sends,
+             COUNT(es.opened_at) AS opens,
+             COUNT(es.clicked_at) AS clicks,
+             ROUND(100.0 * COUNT(es.opened_at) / NULLIF(COUNT(es.id), 0), 1) AS open_rate,
+             ROUND(100.0 * COUNT(es.clicked_at) / NULLIF(COUNT(es.id), 0), 1) AS click_rate
+      FROM email_campaigns ec
+      JOIN email_sends es ON es.campaign_id = ec.id
+      WHERE ec.status = 'sent'
+      GROUP BY ec.name, ec.type, ec.sent_at
+      ORDER BY ec.sent_at DESC
+
+  - name: campaigns_by_type
+    description: Campaign count and avg engagement by type
+    sql: |-
+      SELECT ec.type,
+             COUNT(DISTINCT ec.id) AS campaign_count,
+             COUNT(es.id) AS total_sends,
+             ROUND(100.0 * COUNT(es.opened_at) / NULLIF(COUNT(es.id), 0), 1) AS avg_open_rate,
+             ROUND(100.0 * COUNT(es.clicked_at) / NULLIF(COUNT(es.id), 0), 1) AS avg_click_rate
+      FROM email_campaigns ec
+      JOIN email_sends es ON es.campaign_id = ec.id
+      WHERE ec.status = 'sent'
+      GROUP BY ec.type
+      ORDER BY campaign_count DESC
+
+  - name: monthly_send_volume
+    description: Monthly campaign send volume
+    sql: |-
+      SELECT TO_CHAR(sent_at, 'YYYY-MM') AS month,
+             COUNT(*) AS campaigns_sent
+      FROM email_campaigns
+      WHERE status = 'sent'
+      GROUP BY TO_CHAR(sent_at, 'YYYY-MM')
+      ORDER BY month