Jerry Lin
Community@jerrylin96 · Boston, MA
Postdoctoral Associate at Boston University
Agent Skills by Jerry Lin
Showing 42 vetted skills indexed across 1 GitHub repositories.
jerrylin96gcp-data-pipelines
Routes data pipeline requests to the appropriate Google Cloud tool skill.
jerrylin96debugging-and-error-recovery
Diagnose test failures, build errors, and runtime bugs through structured root-cause triage.
jerrylin96timeline-postmortem
Diagnoses missed deadlines via 5 Whys interviews and reschedules Google Workspace tasks with buffered timelines.
jerrylin96discovering-gcp-data-assets
Searches Dataplex catalog and retrieves schema metadata for Google Cloud data assets.
jerrylin96gcp-spark
Generates and executes PySpark code on Google Cloud Dataproc clusters and Serverless.
jerrylin96test-driven-development
Guides writing failing tests before implementation using the RED-GREEN-REFACTOR cycle.
jerrylin96planning-and-task-breakdown
Decompose specifications into atomic TDD tasks with acceptance criteria and dependency ordering.
jerrylin96managing-python-dependencies
Detects project dependency managers and installs Python packages with the correct tooling.
jerrylin96incremental-implementation
Implements multi-file code changes in thin vertical slices with test and commit cycles.
jerrylin96math-proof-audit
Verify mathematical code implementations against LaTeX derivations via adversarial subagent audits.
jerrylin96data-autocleaning
Profiles and cleans BigQuery and GCS data using Dataplex scans and SQL transformations.
jerrylin96gcp-dataflow
Guides authoring, packaging, launching, and diagnosing Apache Beam pipelines on Google Cloud Dataflow.
jerrylin96bigquery-data-transfer-service
Discovers and inspects BigQuery Data Transfer Service configurations for data ingestion pipelines.
jerrylin96signoff
Verifies human comprehension of branch diffs via Socratic interview and records Git attestation trailers.
jerrylin96dbt-bigquery
Generates, modifies, and validates dbt models and pipelines targeting Google BigQuery.
jerrylin96gcp-composer-troubleshooting
Diagnoses Cloud Composer and Airflow DAG failures using gcloud logs and remote code retrieval.
jerrylin96ponytail
Enforces minimal code solutions by applying YAGNI, reuse, and stdlib-first principles.
jerrylin96bigquery
Generates optimized BigQuery SQL, BigFrames code, and BQML AI function queries.
jerrylin96session-sync
Synchronizes Antigravity CLI conversation sessions across machines using Git remote refs.
jerrylin96federate-lakehouse-catalog
Configures Google Cloud Lakehouse federated catalogs connecting BigQuery to Databricks Unity or AWS Glue.
jerrylin96catchmeup
Summarizes git repository activity over preset time windows with signoff attestation audits.
jerrylin96adversarial-review
Reviews specs, plans, tests, and code diffs across four adversarial lifecycle gates.
jerrylin96accidental-data-loss-prevention
Blocks irreversible deletion commands until explicit user consent is obtained.
jerrylin96building-data-apps
Build data dashboards and interactive reports with React, Vite, or Streamlit on GCP data sources.
Frequently Asked Questions About Jerry Lin
FAQPage SchemaWhat tasks can I accomplish with jerrylin96's skill registry?▼
You can build, deploy, and troubleshoot Google Cloud data pipelines: BigQuery SQL and BQML, dbt and Dataform ELT models, Apache Beam Dataflow jobs, Spark on Dataproc Serverless, Cloud Composer orchestration, DTS ingestion configs, lakehouse federation, plus GCS security audits and data-loss prevention guardrails.
Who is the target audience for these skills?▼
Data engineers, analytics engineers, and ML practitioners working on Google Cloud, plus software developers wanting disciplined workflows. Skills like test-driven-development, adversarial-review, spec-driven-development, and codebase-audit serve engineers enforcing quality gates before merging branch diffs.
How do the GCP pipeline skills work together in practice?▼
Start with gcp-data-pipelines as the entry router, then use specialized skills: discovering-gcp-data-assets to locate tables, dbt-bigquery or dataform-bigquery for transformations, gcp-dataflow or gcp-spark for processing, gcp-pipeline-orchestration for Composer DAGs, and gcp-pipeline-resource-provisioning for deployment.yaml-based provisioning.
Are these skills open source and what do they cost?▼
Most Google-published skills carry the Apache-2.0 license, permitting free use and modification; the ponytail skill uses MIT. Skills without explicit license metadata should be reviewed individually. There is no registry fee; costs derive only from underlying Google Cloud resource consumption.
What prerequisites are required to run these skills?▼
GCP skills require authenticated gcloud CLI with Application Default Credentials (gcloud-auth-verification resolves auth errors), appropriate IAM permissions, and project access to BigQuery, Dataflow, Dataproc, or Composer. Python-based work requires project-scoped virtual environments per managing-python-dependencies rather than global pip installs.