Jordan Totten
Community@tottenjordan
ML @ Google | MS Data Science @ Northwestern University
Agent Skills by Jordan Totten
Showing 77 vetted skills indexed across 1 GitHub repositories.
tottenjordanplaywright-skill
Automates browser testing and web interaction tasks using Playwright scripts.
tottenjordangcp-data-pipelines
Routes data pipeline requests to the appropriate Google Cloud tool and skill.
tottenjordanlicense-header-adder
Prepends Apache 2.0 license headers to new source files with language-appropriate comment syntax.
tottenjordandiscovering-gcp-data-assets
Discovers and inspects Google Cloud data assets using Dataplex search and context lookup.
tottenjordangcp-spark
Generates and executes PySpark code on Google Cloud Dataproc clusters and Serverless.
tottenjordantest-driven-development
Enforces red-green-refactor test-driven development workflow before writing implementation code.
tottenjordantesting-anti-patterns
Detects and corrects common testing anti-patterns involving mocks, test-only methods, and incomplete test coverage.
tottenjordanmanaging-python-dependencies
Detects the project's Python dependency manager and installs packages with the correct tool.
tottenjordandata-autocleaning
Profiles and cleans BigQuery and GCS data using Dataplex scans and SQL transformations.
tottenjordana2a
Build multi-tier ADK agent systems communicating via the A2A protocol on Agent Engine.
tottenjordangcp-dataflow
Guides authoring, packaging, launching, and diagnosing Apache Beam pipelines on Google Cloud Dataflow.
tottenjordanbigquery-data-transfer-service
Discovers and inspects BigQuery Data Transfer Service configurations for ingestion pipelines.
tottenjordanenforcing-resource-attribution
Adds attribution labels to bq and gcloud CLI commands for resource tracking.
tottenjordanbigquery-bigframes
Generates Python code using BigQuery DataFrames for pandas-style analysis and ML on BigQuery.
tottenjordandbt-bigquery
Generates, modifies, and optimizes dbt models and pipelines targeting Google BigQuery.
tottenjordangcp-composer-troubleshooting
Diagnoses Cloud Composer and Airflow DAG failures using gcloud logs and remote code for root cause analysis.
tottenjordanbigquery-graph
Generates GQL queries and property graph DDL for BigQuery graph analytics.
tottenjordangemini-md-improver
Audit and improve GEMINI.md files with quality scoring and targeted updates.
tottenjordanexecuting-plans
Executes written implementation plans in batches with review checkpoints between batches.
tottenjordangit-commit-formatter
Formats git commit messages according to the Conventional Commits specification.
tottenjordanfinishing-a-development-branch
Guides branch completion by verifying tests and executing merge, PR, keep, or discard options.
tottenjordanfederate-lakehouse-catalog
Configures Google Cloud Lakehouse federated catalogs connecting BigQuery to Databricks Unity and AWS Glue.
tottenjordanagent-engine
Deploy and manage ADK agents on Vertex AI Agent Engine with sessions, memory, and A2A support.
tottenjordanaccidental-data-loss-prevention
Requires explicit user consent before executing irreversible data deletion commands.
Frequently Asked Questions About Jordan Totten
FAQPage SchemaWhat tasks can I accomplish with tottenjordan's skill registry?▼
You can build and troubleshoot GCP data pipelines (dbt, Dataform, Dataflow, Spark on Dataproc, Composer Airflow), optimize BigQuery SQL and run BigQuery ML, discover and govern GCP data assets, fuzz code across multiple languages, enforce test-driven development, and automate browser testing with Playwright.
Who is the target audience for these skills?▼
Data engineers and analytics engineers working on Google Cloud, ML practitioners using BigQuery or Vertex AI pipelines, and security engineers running fuzzing campaigns or static analysis with Semgrep and CodeQL. Skills assume familiarity with GCP services, SQL, and standard software testing practices.
How do the GCP pipeline skills work together in practice?▼
Start with gcp-data-pipelines as the entry point, which routes to dbt-bigquery, dataform-bigquery, gcp-dataflow, gcp-spark, or bigquery-data-transfer-service based on requirements. Provision resources via gcp-pipeline-resource-provisioning, orchestrate with Cloud Composer DAGs, and troubleshoot failures with gcp-composer-troubleshooting RCA reports.
Are these skills open source and what do they cost?▼
The Google-published skills carry Apache-2.0 licenses and are free to use. However, executing them incurs normal Google Cloud usage costs for BigQuery, Dataflow, Dataproc, Composer, and Cloud Storage. The fuzzing and testing skills reference open-source projects like AFL++, libFuzzer, and OSS-Fuzz at no license cost.
What prerequisites are required before using these skills?▼
GCP skills require authenticated gcloud CLI access with Application Default Credentials, enforced by gcloud-auth-verification, plus appropriate IAM permissions. Python-based skills require project-managed virtual environments rather than global pip installs. Fuzzing skills require language-specific toolchains such as Clang, Cargo, or Ruby.