signalpilot-dbt

Plugin signalpilot-dbt from marketplace signalpilot in SignalPilot-Labs/signalpilot-plugin. Commands read from the repo's manifest — 17 days ago.

Skills (27)

• bigquery-sql

  BigQuery-specific SQL patterns: UNNEST for array expansion, STRUCT, ARRAY_AGG, DATE_DIFF/DATE_ADD, backtick-quoted table references, EXCEPT/REPLACE in SELECT, approximate aggregation, partitioned and wildcard tables.

• context

  Load before you read, write, or suggest a change to the team's context folder. Covers the folder layout, every file type and its exact format, the save checks, and how to use context in an answer.

• dashboard

  Load when the user asks for a dashboard. Covers the dashboard JSON file, SQL datasets, chart types, and the two check tools.

• dbt-debugging

  Load when dbt run or dbt parse fails. Covers YML duplicate patches, ref errors, passthrough model warnings, current_date fixes, DuckDB error messages, and zero-row diagnosis.

• dbt-snapshots

  Load when task involves dbt snapshots, SCD Type 2, or tracking data changes over time. Covers strategy selection, column casing, verification, and common pitfalls.

• dbt-testing

  Load when task involves adding, writing, or fixing dbt unit tests. Covers unit_tests YAML format, given/expect blocks, edge-case coverage, and the difference between unit tests and schema tests.

• dbt-versioning

  Load when task involves dbt model versioning, creating v2 of a model, or backward-compatible model changes. Covers versions YAML config, defined_in, latest_version, and ref() with version pins.

• dbt-workflow

  Load FIRST before any dbt project work. Covers the full 8-step dbt workflow: project scanning, skill loading, validation, macro discovery, research, technical spec, SQL writing, and verification. Also covers output shape inference, incremental model handling, and what to trust in YML.

• dbt-write

  Loaded at Step 2 for the full workflow. Covers column naming, type preservation, JOIN defaults, lookup joins, sibling models, materialization, packages, filtering rules, and efficient models.

• domain-ecommerce

  E-commerce domain knowledge: transaction lifecycle, driving tables, status filtering.

• domain-financial

  Financial reporting rules: grain consistency, balance sheets, double-entry ledgers, fiscal year boundaries, period-over-period calculations.

• domain-healthcare

  Healthcare data science rules: encounter-based grain, clinical coding hierarchies, cost allocation, NULL semantics in clinical data.

• domain-hr

  HR & operations rules: SCD current-record filtering, issue resolution metrics.

• domain-marketing

  Marketing domain knowledge: attribution models, engagement funnel order.

• domain-media

  Media & entertainment domain knowledge: content catalogs and participation tables.

• domain-product

  Product analytics rules: calendar spine cross-joins, date boundary caps, event type pivoting, first-run NULL behavior.

• duckdb-sql

  Load when hitting DuckDB syntax errors or writing DuckDB-specific SQL. Covers gotchas that differ from PostgreSQL/MySQL.

• github

  Load before any git or GitHub work in a chat: committing model changes, pushing a branch, opening a pull request, updating a pull request, or commenting on one. Covers the sandbox git checkout, the signalpilot/ branch rule, and the open_pull_request, update_pull_request, and comment_on_pull_request

• notebook

  Load before you write or run an analysis notebook in chat. Covers the notebook file format, run_notebook, the sp SDK, governed queries, files, and charts.

• recommendations

  Chat only. Load in the same message as the verifier subagents, after you send the answer. Covers how to decide if this run found a context gap or a dbt gap, and how to file it with the make_recommendations tool.

• signalpilot

  SignalPilot MCP tool catalog for governed database access.

• snowflake-sql

  Snowflake-specific SQL patterns: QUALIFY for window filtering, LATERAL FLATTEN for arrays, semi-structured VARIANT data, ILIKE for case-insensitive matching, date functions, and time travel.

• sql-workflow

  Use this skill before writing any SQL query. Covers: output shape inference (cardinality clues from the question), efficient schema exploration, iterative CTE-based query building, structured verification loop (row count, NULL audit, fan-out check, sample inspection), error recovery protocol, saving

• sqlite-sql

  SQLite-specific SQL patterns: substr/instr for string ops, || for concatenation, LIKE (no ILIKE), date()/strftime() for dates, CAST for type coercion, no FULL OUTER JOIN, GROUP_CONCAT, typeof(), COALESCE/IFNULL, printf() formatting.

• tableau

  Load when the user asks about Tableau: find, build, copy, edit, redesign, or check a Tableau workbook, dashboard, view, or data source. Covers the tableau_* tools, the .twb builder with its design layer, data sources on SignalPilot connections, the design standard, and the render review.

• write-report

  Generates an HTML report summarizing dbt project work: decisions, SQL, queries, verifier results, and visual charts. Only load when explicitly requested.

• xata

  Load when working with Xata Postgres branches: forking a branch, building or testing dbt models on a branch, wiring dbt to a branch's credentials, diffing two branches, or the pre-merge impact report. Covers create_xata_branch, delete_xata_branch, get_dbt_profile, xata_branch_diff, schema_diff_branc

Subagents (2)

• value-verifier

  Read-only value verification for supplied relation-bearing dbt models.

• verifier

  Read-only structure verification for supplied dbt nodes.

Similar plugins