6 tagged duckdb, measured the same way as everything else here.
edwinweber/dbt_duckdb_demo_public
Agent Claude Code
Use ONLY for genuine architectural crossroads — decisions with broad, hard-to-reverse impact: new storage layer, migrating Silver storage format, adding a new medallion tier, major schema changes that ripple across all layers, evaluating DuckLake vs DuckDB trade-offs, reviewing a complex multi-file PR for correctness…
edwinweber/dbt_duckdb_demo_public
Agent Claude Code
Default agent for all implementation work — Python modules, dbt SQL and macros, Dagster assets/jobs/schedules/sensors, dlt pipelines, configuration changes, and pytest tests. Use this for any task that results in a code commit. Only escalate to the architect agent when facing a genuine architectural crossroads (new…
edwinweber/dbt_duckdb_demo_public
Agent Claude Code
Use when something is broken or behaving unexpectedly — Dagster run failures, silent dlt extraction errors, DuckDB state that doesn't match expectations, Metabase connection issues, CI failures, test failures with unclear causes. Read-only mindset: diagnose first, propose fixes second. Do not use for greenfield…
Agent Claude Code
Specialized research agent for deep knowledge synthesis using Distillery. Use for /pour and /radar workflows that require multi-pass retrieval, synthesis across many entries, or ambient intelligence digests. Pre-wired with the configured Distillery MCP tools listed in the frontmatter.
Agent Claude Code
Read-only warehouse invariant checker. Use after a refresh, when a query result looks wrong, or when data staleness is suspected. Reports a pass/fail table — never writes.