Use when the user asks to describe, profile, summarize, explore, or query tabular data without producing modified output files — e.g., "what's in this CSV", "show distributions", "what columns correlate", or ad-hoc SQL questions. Prefer data-wrangler when the user wants to clean, reshape, dedupe, join, or convert data.
Use when the user asks to clean, transform, reshape, dedupe, join, concatenate, sort, replace, or convert tabular data and produce new output files — e.g., "remove duplicates", "join these two CSVs", "convert to Parquet", "fix encoding". Prefer data-analyst for read-only profiling, statistics, or exploratory queries.
Use when the user asks to analyze policy questions that combine local tabular data with US government sources — jurisdiction comparisons, fiscal-impact analysis, demographic/employment/crime context, or "is policy X working?" questions referencing Census, BLS, FBI Crime Data, or Wikidata. Prefer data-analyst for plain…
Orchestrates repair of failing Prefect 3 pipelines. Runs the pipeline-doctor skill to survey and triage, then dispatches one pipeline-investigator subagent per fixable cluster, each on its own branch and PR. Spawn when asked to fix broken pipelines, work through the failing-pipeline backlog, or get prod flows green…
Investigates and fixes ONE failing Prefect pipeline cluster — reads the run logs, confirms the cause against the source and the code, makes the minimal change on its own branch, and verifies it. Dispatched by the pipeline-fixer orchestrator, one per cluster.
Builds a recurring Prefect 3 pipeline for an already-onboarded Data Basis dataset — download, clean, upload (dev+prod), dbt, and metadata refresh on a schedule.