basedosdados

Onboarding Pipeline — Data skill for Claude Code

Data community

Build a recurring Prefect 3 pipeline for an already-onboarded Data Basis dataset.

How to install Onboarding Pipeline

Installs to ~/.claude/skills/basedosdados-pipelines-onboarding-pipeline/SKILL.md

Terminal

mkdir -p ~/.claude/skills/basedosdados-pipelines-onboarding-pipeline && curl -fsSL https://raw.githubusercontent.com/basedosdados/pipelines/HEAD/.claude/skills/onboarding-pipeline.md -o ~/.claude/skills/basedosdados-pipelines-onboarding-pipeline/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Onboarding Pipeline does

description: Build a recurring Prefect 3 pipeline for an already-onboarded Data Basis dataset argument-hint: [--cadence monthly|daily|annual]

Spawn the `pipeline` agent with: $ARGUMENTS

Use this **after** a dataset's static onboarding is verified in dev, when the source publishes on a cadence and should refresh automatically. The agent reads `pipelines/datasets/br_ibge_ipca` and `pipelines/datasets/us_bls_cpi` as references, confirms the shared `pipelines/utils` signat

Alternatives in Data

Dummy Dataset — Generate realistic dummy datasets in CSV, JSON, or SQL 7.8k ★
Skill Production Pipeline — Claude-skills — Effective: 2026-03-07 Applies to ALL new skills, improvements, and deployments 5.3k ★
Ars Full — ARS full pipeline — research → write → review → revise → finalize 4.5k ★