oo-google-bigqueryGoogle BigQuery (cloud.google.com). Use this skill for ANY Google BigQuery request — reading, creating, updating, and deleting data. Whenever a task involves Google BigQuery, use this skill instead of calling the API directly.
Install via ClawdBot CLI:
clawdbot install oomol/oo-google-bigqueryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
curl -fsSL https://cli.oomol.com/install.sh | bashCalls external URL not in known-safe list
https://static.oomol.com/logo/third-party/google_bigquery.pngUses known external API (expected, informational)
cloud.google.comAudited Jun 4, 2026 · audit v1.0
Generated Oct 14, 2026
Data engineering teams migrate on-premises or legacy warehouse workloads to BigQuery by creating datasets and tables, loading data from Google Cloud Storage, and validating query results. They use list/query/patch actions to mirror schemas and metadata, and batch jobs to populate tables.
Analytics teams run scheduled BigQuery SQL queries and poll results to feed dashboards and KPI reports. They use query and get_query_results for read-only reporting, and create_table/insert_all for crafted summary tables that downstream tools consume.
Marketing ops teams consolidate campaign data from ad platforms into BigQuery datasets, then run query jobs to produce attribution and audience segments. They manage datasets, models, and routines through the connector rather than calling Google APIs directly.
Data science teams create, inspect, update, and delete BigQuery ML models and routines using list_models, get_model, patch_model, and delete_model. They track model metadata such as friendly names, descriptions, and labels to support governance and discovery.
Finance and compliance teams list datasets, jobs, and tables to audit access patterns and data lineage. They use read-only actions to retrieve job metadata, inspect table schemas, and extract aggregate query results for regulatory reporting without modifying production data.
A SaaS platform that connects to a customer's BigQuery project and provides scheduled queries, dashboarding, and alerting. The product abstracts BigQuery schema and job management so non-technical users can build reporting without writing SQL or managing credentials.
Consultancies use this skill to automate migration from legacy warehouses to BigQuery, including dataset/table creation, data loading from GCS, and metadata patching. They package repeatable migration playbooks and managed operations for enterprise clients.
Vertical SaaS vendors embed BigQuery-powered analytics directly into their applications using the connector for querying and result retrieval. End customers get real-time insights on their operational data without leaving the host application.
💬 Integration Tip
Always run `oo connector schema` for an action before building its payload, and fetch the live input schema rather than guessing fields. Treat `[write]` and `[destructive]` actions carefully by confirming the exact dataset/table and intended effect with the user before execution.
Scored Sep 2, 2026
Database Designer - POWERFUL Tier Skill
Skill Oracle — Curated documentation of quality ClawHub skills. Markdown tables telling agents which tools work and which are empty. Not an API or code library.
Database Schema Designer
Use when optimizing SQL queries, designing database schemas, or tuning database performance. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis.
Data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka,...
Pinecone vector database — manage indexes, upsert vectors, query similarity search, manage namespaces, and track collections via the Pinecone API. Build sema...