fivetran

Build a new Fivetran connector from a description. Use when the user wants to create, generate, or scaffold a new connector for an API or data source.

Package and deploy a Fivetran connector to Fivetran. Use when the user wants to deploy or ship their connector.

Evaluate a Fivetran connector for correctness, SDK compliance, security, and reliability. Use when the user wants a code review or quality report before deploying.

Test a Fivetran connector by running fivetran debug and checking the results. Use when the user wants to validate or run their connector locally.

Build a new Fivetran connector from a description. Use when the user wants to create, generate, or scaffold a new connector for an API or data source.

Package and deploy a Fivetran connector to Fivetran. Use when the user wants to deploy or ship their connector.

Evaluate a Fivetran connector for correctness, SDK compliance, security, and reliability. Use when the user wants a code review or quality report before deploying.

Test a Fivetran connector by running fivetran debug and checking the results. Use when the user wants to validate or run their connector locally.

Answer marketing automation questions using Fivetran-synced data via BigQuery, Snowflake, or Databricks. Today supports Marketo via the fivetran/marketo dbt package; designed to extend to HubSpot Marketing, Pardot, Iterable, Braze, etc. as additional connector options. Analyzes funnel velocity (MQL/SAL/SQL transitions), nurture stream performance, email engagement (sends/opens/clicks/unsubscribes), campaign and program performance, lead source attribution, and lead engagement scoring using marketo__leads, marketo__lead_history, marketo__email_sends, marketo__campaigns, marketo__programs, and marketo__email_templates. Use when someone asks about lead funnel, MQL/SAL/SQL transitions, nurture performance, email engagement rates, campaign performance, lead source quality, or any marketing- automation metric. Trigger on: "funnel velocity", "MQL", "SAL", "SQL", "lead funnel", "nurture", "email open rate", "email click rate", "unsubscribe rate", "bounce rate", "campaign performance", "lead source", "attribution", "l

Answer ad performance questions using data from Fivetran's ad connectors via BigQuery, Snowflake, or Databricks. Cross-channel analysis across Google Ads, Facebook Ads, Microsoft Ads, LinkedIn Ads, TikTok Ads, Pinterest Ads, and Snapchat Ads. Use when someone asks about ad spend, impressions, clicks, conversions, CPC, CPM, ROAS, CTR, or any advertising metrics. Supports cross-channel comparison, campaign drill-down, trend analysis, keyword performance, and anomaly detection. Trigger on: "how are our ads performing", "ad spend", "campaign performance", "cost per click", "ROAS", "impressions", "CTR", "ad performance", "marketing analytics", "compare channels", "cross-channel", "Facebook vs Google", "budget allocation", "LinkedIn ads", "TikTok ads", "Pinterest ads", "Snapchat ads", "LinkedIn performance", "TikTok performance", "Pinterest performance", "Snapchat performance".

Answer HubSpot sales pipeline and funnel questions using Fivetran-synced HubSpot data via BigQuery, Snowflake, or Databricks. Analyzes deal stages, pipeline conversion rates, win/loss outcomes, rep performance, deal velocity, and stage aging using the hubspot dbt package models. Use when someone asks about pipeline health, stage conversion, funnel drop-off, deal velocity, win rates, rep activity, stalled deals, or any HubSpot CRM metric. Trigger on: "pipeline", "stage conversion", "win rate", "funnel", "deal velocity", "how long to close", "stalled deals", "deals by stage", "pipeline by rep", "won deals", "lost deals", "deal aging", "stage drop-off", "pipeline health", "sales cycle", "closed this quarter", "which stage has lowest conversion", "rep performance", "who's closing the most", "where are we losing deals".

Answer e-commerce store performance questions using Fivetran-synced Shopify connector data. Computes GMV, net revenue, AOV, order count, repeat customer rate, refund rate, top products, BFCM and seasonality detection, new vs returning revenue, and customer cohorts — directly from raw Shopify tables (no dbt quickstart required). Use when someone asks about store performance, GMV, AOV, refunds, top sellers, repeat customers, cohorts, BFCM/Q4 performance, or any e-commerce metric. Trigger on: "how is the store doing", "store performance", "GMV", "revenue", "AOV", "average order value", "repeat rate", "refund rate", "top products", "best sellers", "customer cohorts", "new vs returning", "Black Friday", "BFCM", "Cyber Monday", "Q4 performance", "monthly orders", "seasonality".

Answer Zendesk customer support questions using Fivetran-synced data via BigQuery, Snowflake, or Databricks. Analyzes ticket volume and trends, first reply and resolution times (business + calendar hours), backlog aging, agent performance, SLA breach rates, CSAT, and channel/priority breakdowns using the fivetran/zendesk dbt package models (zendesk__ticket_enriched, zendesk__ticket_metrics, zendesk__ticket_field_history, zendesk__ticket_backlog, zendesk__ticket_summary, zendesk__sla_policies). Use when someone asks about support ticket volume, first reply / resolution time, backlog, agent performance, SLA breaches, CSAT, or any Zendesk metric. Trigger on: "first reply time", "first response", "resolution time", "ticket resolution", "ticket backlog", "open tickets", "SLA breach", "CSAT", "satisfaction score", "agent performance", "ticket volume", "support performance", "Zendesk", "customer support".

Explore and query your Fivetran Managed Data Lake Service (MDLS). As part of MDLS, Fivetran manages a Polaris catalog and the underlying Apache Iceberg tables where your connector data lands — your fully managed lakehouse. This skill gives you an agentic interface to explore that data (read-only in the current MDLS release). Use for ANY question about your MDLS tables: schemas, namespaces, row counts, sync status, data freshness, partitioning, snapshots, or running queries against your Iceberg data. Trigger on: "what tables do we have", "explore my lakehouse", "query the lakehouse", "check sync status", "how fresh is our data", "what's in MDLS", "describe this table", "how many rows", "show me our Iceberg tables".

Get a quick overview of the connected Fivetran account.

Use this skill AFTER copy-connections-execute has successfully created connection shells, to help the user attach credentials to their newly-created connections. Identifies what auth each connection uses, offers flexible credential collection (bulk file, one-by-one, or UI self-service), and provides Fivetran UI links for anything the user prefers to handle themselves. Invoke from the copy-connections coordinator after execute reports success.

Use this skill AFTER credentials have been attached to the newly-created connections (via the credentials skill or manually in the Fivetran UI). Runs setup tests to verify credentials and discover the schema, then applies table/column selections, sync modes, and hashing from the copy plan. Invoke from the copy-connections coordinator after credentials are in place.

Use this skill as part of the Copy Connections workflow to execute a validated copy plan. Creates connection shells (without credentials), installs Quickstart packages, and produces a results file with next steps. Refuses to run without a passing validation report. Invoke from the copy-connections coordinator.

Use this skill as part of the Copy Connections workflow to gather the user's intent, fetch their current Fivetran setup (connections, destinations, transformations), and produce a structured copy plan. Invoke this from the copy-connections coordinator, not directly.

Use this skill when the user wants to copy, clone, migrate, or replicate their Fivetran connections from one destination to another — whether same destination type (e.g., splitting one warehouse into two) or different (e.g., Redshift to Snowflake). Handles the end-to-end workflow including scoping, validation, credential handling, and execution.

Use this skill as part of the Copy Connections workflow to validate a copy plan before execution. Checks for naming collisions, type compatibility, schema compatibility, and transformation portability. Can also be used standalone to answer "what would break if I copied these?" without committing to execute. Invoke from the copy-connections coordinator or directly when the user asks to validate an existing plan.

A comprehensive framework for building interactive, UI-based Model Context Protocol (MCP) apps for Claude.