🔀 Orquestrador de fluxos de captura, ingestão e tratamento de dados da BD
Agent Claude Code
Fetches or creates architecture tables for a Data Basis dataset on Google Drive. Each table in the dataset gets one Google Sheets file defining column names, types, descriptions, and metadata.
Agent Claude Code
Writes and runs Python data cleaning code for a Data Basis dataset, producing partitioned Parquet output that conforms to the architecture table schema.
Agent Claude Code
Gathers all context needed to onboard a dataset to Data Basis — raw source URLs, documentation, organization, themes, coverage, and Drive folder path.
Agent Claude Code
Writes DBT SQL model files and schema.yml for a Data Basis dataset, then runs and fixes tests.
Agent Claude Code
Resolves all reference IDs from the Data Basis backend needed for metadata creation — organizations, themes, tags, entities, statuses, and existing dataset/table IDs.
Agent Claude Code
Registers or updates all metadata in the Data Basis backend — dataset, tables, columns, observation levels, coverage, and updates. Handles both dev and prod environments.
Agent Claude Code
Orchestrates the full dataset onboarding workflow for Data Basis — from raw data → clean data → BigQuery → metadata in the backend. Spawn this agent when the user asks to onboard a dataset.
Agent Claude Code
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…
Agent Claude Code
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.
Agent Claude Code
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.
Agent Claude Code
Opens a GitHub pull request for a Data Basis dataset onboarding, with a structured changelog and checklist.
Agent Claude Code
Downloads raw data files for a Data Basis dataset from the source URL(s). Handles diverse download mechanisms including direct HTTP, FTP, APIs, paginated endpoints, and portal scraping.
Agent Claude Code
Uploads cleaned Parquet files to BigQuery via the basedosdados Python package. Handles dev and prod environments.
Agent Claude Code
Runs DBT tests and validates data quality for a Data Basis dataset. Flags anomalies and proposes fixes or escalates to the user.