Ricardo Lui Geh
Community@ricardolui · Brazil
Google Cloud Data Analytics Practice Lead #bigquery #datacloud #googlecloud #looker #dataflow
Agent Skills by Ricardo Lui Geh
Showing 48 vetted skills indexed across 1 GitHub repositories.
ricardoluilooker-mcp-gemini-enterprise
Configure Looker MCP server integration with Gemini Enterprise via OAuth and PKCE.
ricardoluicloud-cost-dashboard-ux
Implements UX design patterns for cloud cost dashboards and daily telemetry explorers.
ricardoluimsk-migration
Assess and plan migrations from AWS MSK to Confluent Cloud.
ricardoluibigquery-predeploy-e2e-gate
Runs a 4-tier verification gate covering TDD tests, local E2E pipeline, git safety, and Cloud Run deployment.
ricardoluiconfluent-skill-creator
Create and validate Confluent product skills tested against real Kafka environments.
ricardoluigcp-bigquery-notebook-uploader
Uploads and commits Jupyter notebooks to Google Cloud Dataform repositories via REST API.
ricardoluikafka-schema-registry
Scan projects for Kafka usage, extract schemas, tag PII fields, and generate Terraform for Confluent Schema Registry.
ricardoluiantigravity-arcade
Runs interactive BigQuery and Property Graph demo scenarios against live Google Cloud infrastructure.
ricardoluilooker-pop-modeling
Implements Looker Period-over-Period LookML modeling with surrogate key hashing and BigQuery loading.
ricardoluistart-gpowers-multimodel
Activates the GPowers Multi-Model Orchestrator persona with per-role subagent model routing.
ricardoluienforcing-resource-attribution
Applies attribution labels to bq and gcloud CLI commands for resource tracking.
ricardoluibigquery-agentic-e2e-tester
Runs headless end-to-end validation of BigQuery agentic demo deployments and outputs console deep links.
ricardoluiconfluent-skill-reviewer
Audits Confluent agent skills against the Agent Skills spec, repo conventions, and eval contracts.
ricardoluigemini-enterprise-cleanup
Audits and deletes Gemini Enterprise agents, OAuth authorizations, and BigQuery Data Agents via REST APIs.
ricardoluijetski-disable-codesearch
Configures isolated Git projects to block Google3 code_search and enforce local search tools.
ricardoluidatabricks-bq-parity-checker
Validates hourly data parity between BigQuery Iceberg tables and Databricks Unity Catalog tables.
ricardoluibigquery-bigframes
Generates Python code using BigQuery DataFrames for pandas-style analysis and ML on BigQuery.
ricardoluibigquery-conversational-agent-builder
Architects and validates BigQuery Conversational Analytics Data Agents with property graph grounding and A2A federation.
ricardoluibigquery-graph
Generates GQL queries and property graph DDL for BigQuery graph analytics.
ricardoluiflink-udf
Build and deploy Java user-defined functions for Apache Flink stream processing over Kafka.
ricardoluigcp-dataform-deployment
Deploy and orchestrate Google Cloud Dataform pipelines via REST API with IAM configuration.
ricardoluifederate-lakehouse-catalog
Configures Google Cloud Lakehouse federated catalogs connecting to Databricks Unity and AWS Glue.
ricardoluibq-augmented-analytics
Build and validate BigQuery Augmented Analytics TVF queries and Conversational Analytics Data Agents.
ricardoluikafka-streams-programming
Architect, build, and debug Kafka Streams applications across Kafka, Confluent, and WarpStream environments.
Frequently Asked Questions About Ricardo Lui Geh
FAQPage SchemaWhat tasks can I accomplish with Ricardo Lui Geh's skill collection?▼
You can optimize BigQuery SQL, build BigFrames and BigQuery ML pipelines, ingest Kafka topics into BigQuery and Iceberg, migrate MSK/Event Hubs/Spark workloads to Google Cloud, model Looker PoP explores, provision Dataform repositories, and audit GCS security posture.
Who are these skills designed for?▼
Data engineers, analytics engineers, and cloud architects working on Google Cloud and Confluent platforms. They suit practitioners handling BigQuery analytics, Kafka streaming, lakehouse federation, Looker modeling, and cross-cloud migrations such as Databricks-to-BigQuery parity checks.
What runtimes and dependencies do the skills require?▼
Requirements vary per skill. The Confluent skill creator needs Python 3.9+, confluent-kafka with avro/json/protobuf extras, requests, jsonschema, and python-dotenv, plus access to a Confluent environment. Flink UDF and Kafka client skills target Java with Maven or Gradle.
Are these skills open source and what licenses apply?▼
Most Google-published skills carry the Apache-2.0 license, including bigquery-sql, bigquery-graph, bigquery-bigframes, and gcs-security-assessment. Confluent-authored skills list version metadata without explicit licenses. No paid licensing is indicated in the manifest.
Do the skills cover streaming migration scenarios?▼
Yes. Dedicated skills handle AWS MSK-to-Confluent Cloud cutovers, Azure Event Hubs to Pub/Sub Import Topics, PySpark Delta Lake to Apache Beam on Dataflow, and Composer/Dataform streams to Confluent direct Iceberg ingestion with shadow A/B parity validation.