@google

agent-platform-tuning-management covers listing, inspecting, and canceling genai tuning jobs via the agent platform python sdk, with strict safety confirmation rules for destructive operations.

google-agents-cli-scaffold automates creation and enhancement of google agents projects via CLI, mapping user intent to deployment targets, datastores, and ci/cd runners. covers prototype-first iteration, rag provisioning, and reference scaffolding for non-standard structures.

adk-scaffold provides a structured multi-step workflow for creating and enhancing ADK agent projects, with emphasis on requirements gathering, design specification approval, and incremental deployment scaffolding via CLI.

agent-platform-model-registry covers lifecycle management of ml models including upload, retrieval, metadata mutation, and deletion with tiered safety confirmations enforced at execution boundaries.

agent-platform-rag-engine-management covers corpus discovery, inspection, context retrieval, and grounded generation via the vertexai sdk with explicit safety confirmation tiers for resource-consuming operations.

agent-platform-prompt-management covers crud operations on managed prompts in agent platform via sdk, with tiered safety confirmation gates for mutations and destructive actions.

adk-cheatsheet provides a pointer to the python adk api quick reference covering agents, tools, auth, orchestration, and callbacks. intended for developers modifying existing projects, not scaffolding new ones.

google-agents-cli-deploy covers agent deployment across three targets (Agent Runtime, Cloud Run, GKE) with infrastructure-as-code patterns, CI/CD pipeline setup via WIF authentication, and rollback strategies via git or traffic shifting.

adk-eval-guide documents the evaluation framework and workflow for adk skills, referencing auxiliary guides for metrics, user simulation, and multimodal testing without spelling out the actual methodology.

firebase-basics provides prerequisite validation and cli setup for firebase projects, including npm verification, agent skills installation, and project context configuration.

gemini-interactions-api covers stateful multi-turn conversation and workflow execution on gemini enterprise platform using unified sdk and latest model versions, with mandatory authentication and turn-scoped configuration.

adk-deploy-guide references deployment patterns across cloud run, gke, and ci/cd but delegates procedural detail to external docs, offering navigation rather than actionable steps.

agent-platform-eval-flywheel guides iterative evaluation and improvement of genai models and agents using google cloud's evaluation sdk, covering dataset creation, metric selection, and failure analysis with concrete remediation.

agent-platform-deploy covers deployment and cleanup of open models and custom weights to agent platform endpoints, with safety confirmation tiers specified but procedures incomplete.

quick reference for google agents adk patterns covering agent creation, tool definition, callbacks, and state management with SequentialAgent, ParallelAgent, and LoopAgent orchestration.

gke-basics provides minimal scaffolding for gke cluster creation via gcloud and kubectl commands, assumes user familiarity with kubernetes and google cloud, references a golden path document without inline specification.

agent-platform-skill-registry enables agents to search, upload, update, and delete skills within gemini enterprise agent platform, plus monitor long-running operations and auto-scaffold new skills.

onboarding guidance for individual developers starting with google cloud, covering account setup, billing configuration, and initial resource deployment.

incomplete framework reference for google cloud performance optimization. provides conceptual overview of resource allocation principles but lacks executable guidance, concrete procedures, or decision criteria.

this skill describes google cloud security principles and best practices from the well-architected framework without providing actionable guidance, specific trigger conditions, or implementation procedures.

adk-dev-guide references session continuity and defers to design spec but lacks actionable workflow steps, concrete procedures, or decision logic for adk development.

Guides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when…

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama,…

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent…

Investigates Google Cloud networking issues by analyzing logs, metrics, and diagnostics. Use when investigating VPC Flow Logs, NAT, firewall, or threat logs,…

Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training…

MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK…

Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete…

Interacts with Google Cloud services using the gcloud CLI safely and efficiently. Covers command validation, data reduction, safety guardrails with a denylist,…

Generates sustainability-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Google Cloud Well-Architected…

Generates operations-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Operational Excellence pillar of the…

Investigates Google Cloud networking issues by analyzing logs, metrics, and diagnostics. Use when investigating VPC Flow Logs (including cost estimation), NAT,…

Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database…

Generates reliability-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Google Cloud Well-Architected…

Generates cost optimization guidance for Google Cloud workloads based on the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate a…

This file generates or explains Cloud SQL resources. Use this file when the user asks to create a Cloud SQL instance or database for MySQL, PostgreSQL, or SQL…

Provides expert guidance on authenticating and authorizing to Google Cloud services and APIs, covering human users, service identities, Application Default…

Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables,…

Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the usage of…

Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or…

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini Enterprise", "publish to Gemini…

This skill should be used when the user wants to "set up tracing", "monitor my ADK agent", "configure logging", "add observability", "debug production…

This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval…

This skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent",…