Software Development Skills

Convert or import a Databricks Metric View into ThoughtSpot as a Model. Use when Databricks is the source and the goal is a ThoughtSpot Model — whether migrating Databricks metrics and semantic definitions into ThoughtSpot or making a Metric View available for Spotter and search-based analytics. Direction is always Databricks → ThoughtSpot. Not for ThoughtSpot → Databricks, standalone DDL generation, or adding AI context to existing ThoughtSpot models.

Convert a Looker semantic model (LookML project) into ThoughtSpot — parses model + view .lkml files, generates Table TML and Model TML per explore, validates invariants, and imports. Optionally converts LookML dashboards to ThoughtSpot Liveboards. Direction is always Looker → ThoughtSpot.

Convert or import a Snowflake Semantic View into ThoughtSpot as a Model. Use when Snowflake is the source and the goal is a ThoughtSpot Model — whether migrating Snowflake metrics and semantic definitions into ThoughtSpot or making a Semantic View available for Spotter and search-based analytics. Direction is always Snowflake → ThoughtSpot. Not for ThoughtSpot → Snowflake, standalone DDL generation, or adding AI context to existing ThoughtSpot models.

Convert or import a Tableau workbook (.twb or .twbx) into ThoughtSpot — parses TWB XML, generates table + model TMLs, validates and imports. Optionally migrates dashboards to liveboards with layout approximation. Direction is always Tableau → ThoughtSpot. Not for ThoughtSpot → Tableau or standalone TML exports.

Convert or export a ThoughtSpot Worksheet or Model into a Databricks Metric View. Use when ThoughtSpot is the source and the goal is a Databricks Metric View — whether converting metrics and formulas for Databricks AI/BI access, generating CREATE VIEW WITH METRICS DDL, writing a .sql file for later execution, or publishing ThoughtSpot semantics to Unity Catalog. Direction is always ThoughtSpot → Databricks. Not for Databricks → ThoughtSpot, standalone TML exports, or adding synonyms/AI context to ThoughtSpot models.

Convert or export a ThoughtSpot Worksheet or Model into a Snowflake Semantic View. Use when ThoughtSpot is the source and the goal is a Snowflake Semantic View — whether converting metrics and formulas for Cortex Analyst access, generating CREATE SEMANTIC VIEW DDL, writing a .sql file for later execution, or updating an existing Snowflake SV from a changed model. Direction is always ThoughtSpot → Snowflake. Not for Snowflake → ThoughtSpot, standalone TML exports, or adding synonyms/AI context to ThoughtSpot models.

Safely audit, remove, or repoint columns and objects across a ThoughtSpot environment — generates a risk-rated impact report, backs up TML before any change, and supports full rollback.

Load source data (CSV, Tableau download, manifest) into a warehouse. Infers schema, generates synthetic data for schema-only sources, and provisions tables. Snowflake and Databricks supported.

Promote formulas and parameters from a saved ThoughtSpot Answer into a Model — makes them available to all users who search against it.

Audit a ThoughtSpot Model's Liveboards and Answers to recommend, generate, and wire aggregate Models (26.6 aggregate-aware routing). Analyses which query shapes repeat, profiles compression against the warehouse, presents a marginal-gain curve, and creates warehouse DDL + aggregate Model TML + the aggregatedmodels association with confirmation gates.

Prepare a ThoughtSpot Model to work well with Spotter. Use when you want to improve how a Model responds to natural language queries — reviewing and writing AI context, synonyms, reference questions, business terms, and data model instructions. Mines real language from existing Liveboards, Answers, and optionally Snowflake query history to ground the coaching in how users actually talk about the data.

Ask a question of a ThoughtSpot Model and get the answer as data — write SpotQL (Semantic SQL), validate it to warehouse SQL, execute it, and review the results. Use this whenever someone wants to query a ThoughtSpot Model with SpotQL, turn a natural-language question into SpotQL, see the SQL ThoughtSpot generates for a question, pull rows from a Model programmatically, learn how the SpotQL APIs behave, or build a question set to accuracy-test / regression-test / feature-test SpotQL. Triggers on "query this model", "ask the model", "run SpotQL", "what SQL does ThoughtSpot generate", "get the data for...", even when SpotQL isn't named explicitly.

Set up and manage Snowflake connection profiles. Use when configuring a new Snowflake connection, updating credentials, or testing whether an existing profile is working. Supports Python connector (key pair or password) and Snowflake CLI. Credentials are stored securely in the OS keychain.

Manage ThoughtSpot connection profiles for Snowflake workspaces — add, list, update, delete, and test profiles. Supports both bearer token and password authentication. Sets up External Access Integration and stores credentials securely using Snowflake Secrets. Token profiles expire after ~24 hours; password profiles remain valid until the password changes.

Creates three Snowflake scalar UDFs for calculating business-day (weekday-only) date differences and elapsed time, then shows the ThoughtSpot formula syntax to use them in any Model. Use this skill whenever the user asks about weekday date calculations, business day counts, working day differences, SLA tracking, ticket age, order fulfillment time, or wants to exclude weekends from any date difference in ThoughtSpot or Snowflake. ThoughtSpot's built-in diffdays/diffhours/diffminutes count calendar days — if a user needs weekday-only equivalents, invoke this skill.

Creates four Snowflake scalar UDFs that format integer durations (seconds or minutes) as human-readable time strings — HH:MM:SS, DD:HH:MM:SS, HH:MM, DD:HH:MM — then shows the ThoughtSpot formula syntax to display them in any Model. Use this skill whenever the user asks about displaying durations, formatting elapsed time, converting seconds or minutes to a readable format, showing call duration, handle time, SLA elapsed time, ticket age as HH:MM:SS, or any scenario where an integer count of seconds or minutes should appear as a formatted time string in ThoughtSpot.