Data & AI skills

Design Google Cloud systems where multiple AI agents process live audio, video, or text and respond in real time. Guides requirements discovery, architecture diagrams, infrastructure code, deployment instructions, and validation for technical guidance or safety monitoring workloads.

• Design real-time technical guidance using live audio and video
• Plan hazard detection and visual inspection from video streams
• Create cloud architecture diagrams and deployment instructions

Convert Snowflake dbt SQL models to BigQuery through a bulk migration workflow. Preserve Jinja template logic while adapting configuration, explicit type conversions, JSON access, and deduplication patterns, with translated files saved in their directory structure.

• Migrating Snowflake dbt models to BigQuery in bulk
• Preserving dbt references and incremental processing logic
• Adapting JSON, array, and STRUCT access during migration

Build AI applications in Python with Genkit, including conversational agents, generation workflows, streaming responses, and tool use. The skill also guides setup and debugging through traces, recorded details of model inputs, outputs, and actions.

• Build a chatbot that keeps conversation history
• Implement streaming responses and tool calls
• Investigate Genkit import and API errors

Build conversations and workflows with the Gemini Interactions API on Gemini Enterprise Agent Platform. Follow Python or JavaScript examples for server-stored conversation history, streaming responses, structured JSON output, function calls, and background agent tasks.

• Building chats that retain conversation context
• Displaying responses as they stream
• Returning JSON in a specified format

Build AI applications with Genkit in Node.js and TypeScript, including conversational agents, generation workflows, and tools. Use documentation, type checks, and execution traces—records of model inputs and tool calls—to verify behavior and troubleshoot errors.

• Set up a new Genkit project
• Build a conversational agent with persistent sessions
• Manage prompts in separate .prompt files

Create and manage custom Agent resources on Gemini Enterprise Agent Platform before running conversations. Prepare REST requests to configure instructions, attach files and skills, connect tools, track creation progress, and retrieve, update, or delete agents.

• Create an Agent with task-specific instructions
• Attach files and skills from Cloud Storage or Skill Registry
• Configure connections to external MCP tools

Trace where BigQuery and Cloud Storage data comes from and where it goes. The skill summarizes table or column lineage, meaning data origins and movement, in a readable Markdown report to support data quality investigations.

• Investigating data origins during a quality issue
• Summarizing data sources and destinations
• Tracing the flow of a specific column

Assess how changes, failures, or paused updates to a BigQuery table or view affect downstream assets. Trace data lineage, the relationships showing where data flows, and summarize dependent tables, dashboards, and processes with direct and indirect impacts.

• Assess downstream effects of a table failure
• Check dependencies before changing or deleting a view
• Evaluate the impact of pausing data updates

Build Gemini API integrations on Google Cloud’s Agent Platform using the Google Gen AI SDK. Get guidance on authentication, text and media processing, structured JSON responses, function calls, caching, batch processing, and real-time voice or video interactions.

• Adding Gemini to enterprise applications
• Processing images, audio, and documents
• Generating JSON in a specified format

Generate a client in your chosen language for live, two-way communication with Gemini Enterprise LiveAPI. Includes token renewal, session recovery, tests, and a demo interface for trying text, audio, video, and transcription.

• Build a client for live conversations with Gemini
• Add token renewal and session recovery
• Test audio and video input through a demo interface

Helps build AI features in Go with Genkit, including text generation, structured data output, streaming, tool calls, and conversational agents. Guides HTTP serving and trace inspection to check model responses and tool execution.

• Adding text generation or structured output to a Go app
• Building a chatbot that retains conversation state
• Connecting model responses to tool calls

Manage machine learning models and their versions in the Agent Platform Model Registry. List registered models, inspect details, upload new versions, update names or descriptions, and delete models through workflows that require confirmation for changes.

• List registered models and inspect their details
• Register a new model or model version
• Update a model's display name or description

Create custom Google Analytics reports with user counts, page views, and breakdowns by city or date. The skill covers API setup, authentication, and checking whether selected measurements and grouping fields can be used together.

• Report active users by city and date
• Automate recurring analytics reports
• Check which report fields work together

Review BigQuery capacity, table layouts, storage retention, and SQL to improve cost efficiency. Compare billing options, plan partitioned tables, and evaluate search indexes, stored aggregation results, and BI Engine for suitable workloads.

• Compare On-Demand pricing with Editions
• Review storage billing models and retention periods
• Design table partitioning and clustering

Manage BigQuery datasets, tables, views, and jobs, and run SQL queries for basic data analysis. Provides setup examples and references for data ingestion, command-line operations, client libraries, access permissions, and infrastructure configuration.

• Create BigQuery datasets and tables
• Search and aggregate data with SQL
• Load data and manage processing jobs

Manages Agent Platform endpoints, the stable URLs used to serve online model predictions. It supports listing, inspecting, creating, updating, and deleting endpoints, plus troubleshooting permission errors, quota limits, and resources that are busy.

• Listing endpoints and checking their configuration
• Creating an endpoint before model deployment
• Updating endpoint display names or labels

Manage saved prompts in Agent Platform with Python, including creation, listing, retrieval, version tracking, and deletion. Retrieve a specific version and fill template variables to reuse a prompt with its associated model.

• Create a managed prompt template
• List saved prompts and inspect their contents
• Retrieve a specific version and fill template variables

Write SQL that uses BigQuery’s built-in machine learning and generative AI for forecasting, anomaly detection, identifying drivers of change, searching by meaning, and classifying or summarizing text stored in your data.

• Forecasting future values from time-series data
• Detecting anomalies and investigating drivers of change
• Searching documents by meaning

Prepare to fine-tune open models or Gemini models on Agent Platform. Check the environment, convert and validate training data, choose supported models and settings, and estimate tuning costs for open models.

• Checking whether an Agent Platform tuning environment is ready
• Converting and validating training datasets
• Choosing models and training settings for a task

Generate Python code to clean, transform, analyze, visualize, and model BigQuery data with BigQuery DataFrames. The skill keeps processing in the cloud and uses familiar table operations, with guidance for previews, schema checks, and machine learning.

• Clean and transform BigQuery data with Python
• Preview data and check column types
• Visualize aggregated or sampled data

Explore document collections in Agent Platform RAG Engine, list their files, and retrieve relevant passages with source references. Use retrieved material to generate answers grounded in the collection through Python SDKs.

• Listing available document collections and files
• Inspecting a specific RAG corpus
• Finding relevant passages and their sources

Inspect and manage model tuning jobs, which adapt models through additional training, in Agent Platform. List jobs, check their status and details, and cancel running jobs after reviewing the target and explicitly confirming the action.

• List running model tuning jobs
• Check the status and details of a specific job
• Cancel a long-running job after confirmation

Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.

• Build evaluation datasets from conversation logs
• Generate simulated user scenarios
• Choose scoring criteria for responses and tool use

Find and manage agent skills in the Gemini Enterprise Agent Platform Skill Registry, a catalog of available capabilities. The skill supports searching, uploading, updating, deleting, inspecting revision histories, checking operation status, and creating local starter files.

• Search for skills that provide a needed capability
• Upload or update skills in the registry
• Inspect skill details and revision histories