SignalPilot

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_branches, and pgroll migrations.

Load at Step 1 before exploring the project. Covers output shape inference, incremental model handling, and what to trust in YML.

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 output to result.sql and result.csv, turn budget management, and common benchmark traps.

Populate the knowledge base from dbt project research. Proposes entries across all 6 categories at org, project, and connection scopes.

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.

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

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.

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.

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

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.

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.

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

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

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

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

Marketing domain knowledge: attribution models, engagement funnel order.

Media & entertainment domain knowledge: content catalogs, participation tables, ranking determinism.

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

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

Write a technical spec after research. Distills exploration into structured decisions. On retries, read the existing spec instead of re-researching.

BLOCKING REQUIREMENT: If the user's message mentions dbt, SQL, database, or data pipeline - invoke this skill as your FIRST tool call, BEFORE Read, Glob, Grep, Bash, or Agent. Covers: SignalPilot MCP tools, available skills, and the governed workflow for dbt projects, SQL queries, schema discovery, and database access.

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.

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 output to result.sql and result.csv, turn budget management, and common benchmark traps.

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.

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

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.

Load at Step 4 when writing SQL models. Covers column naming, type preservation, JOIN defaults, lookup joins, sibling models, materialization, packages, and filtering rules.

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

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.

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.

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.