rk-chavali
UserRead-only GCP data engineering skills for Claude Code and Codex. Cost audits from real BigQuery job history, Dataform modeling, schema contracts, Terraform, Composer DAGs, incident triage. MIT.
Categories
Indexed Skills (9)
gcp-data-engineering
Build, review, and operate a BigQuery data platform on GCP, running read-only queries against the live warehouse when a connection is available. Use when the user works with BigQuery, Dataform, SQLX, Cloud Composer, Airflow DAGs, Terraform for GCP, Analytics Hub, data contracts, or pipeline incidents. Covers cost audits and query tuning against real job history, dimensional modeling, schema contracts and breaking-change review, infrastructure as code, orchestration, incident triage and backfills, data sharing, and pull request review for pipeline code.
analytics-hub-publisher
Design and publish BigQuery data products through Analytics Hub, including exchanges, listings, subscriber governance, and the decision of whether to share at all. Use when the user mentions Analytics Hub, a data exchange, a listing, sharing datasets across projects or with a partner or vendor, linked datasets, or asks how to give another team read access without copying data.
bq-cost-auditor
Audit BigQuery SQL or a whole project for cost, then return a rewritten query and a projected byte reduction. Use when the user asks why a query is slow or expensive, mentions a BigQuery bill or slot contention, asks to optimize or tune SQL, asks about partitioning or clustering choices, or pastes a query and asks what is wrong with it. Also use before shipping any model that will run on a schedule.
bq-schema-contract
Define, version, and enforce schema contracts between data producers and consumers on BigQuery. Use when the user mentions a data contract, schema drift, a breaking change, a producer or consumer agreement, column deprecation, or asks how to stop upstream teams from breaking downstream tables. Also use when reviewing a schema change PR.
composer-dag-builder
Write and review Airflow DAGs for Cloud Composer using GCP-native operators. Use when the user mentions Airflow, Composer, a DAG, a scheduled pipeline, backfills, task dependencies, sensors, SLAs, or asks how to orchestrate BigQuery, Dataform, Cloud Run, or Dataflow work on a schedule.
dataform-modeler
Write and review Dataform SQLX models, assertions, tags, and release configs for BigQuery. Use when the user mentions Dataform, SQLX, definitions folder, declarations, assertions, incremental models, or asks to build a staging, intermediate, or mart layer in BigQuery. Also use when migrating dbt models to Dataform or when a Dataform compilation or dependency graph is broken.
de-pr-reviewer
Review a data engineering pull request covering SQL, Dataform, Airflow DAGs, or Terraform, and return blocking findings separated from suggestions. Use when the user asks for a code review, pastes a diff or PR link for pipeline code, asks whether a change is safe to merge, or asks what would break if they ship something.
pipeline-incident-triage
Triage a failed or wrong data pipeline on GCP and produce a fix plus a postmortem. Use when the user says a pipeline failed, a DAG is red, a table is stale, numbers look wrong, an assertion failed, a dashboard is broken, a job is stuck, or costs spiked unexpectedly. Also use when the user pastes an error from BigQuery, Airflow, Dataform, or Cloud Run.
terraform-gcp-scaffolder
Generate and review Terraform for GCP data platform resources, including BigQuery datasets, Cloud Run jobs, service accounts, IAM, Pub/Sub, Secret Manager, and Composer environments. Use when the user mentions Terraform, IaC, tfstate, provisioning GCP resources, service account permissions, least privilege, or asks to stand up a new environment or project.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.