### Install Kubernetes Client Library (Go)

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/client-library-usage.md

Install the Go Kubernetes client library using go get.

```bash
go get k8s.io/client-go@latest
```

--------------------------------

### Install BigQuery Client Library (Go)

Source: https://github.com/google/skills/blob/main/skills/cloud/bigquery-basics/references/client-library-usage.md

Install the BigQuery client library for Go using the go get command. This prepares your Go environment for BigQuery interactions.

```bash
go get cloud.google.com/go/bigquery
```

--------------------------------

### Install AlloyDB Go Client Library

Source: https://github.com/google/skills/blob/main/skills/cloud/alloydb-basics/references/client-library-usage.md

Install the AlloyDB Go client library using the go get command.

```bash
go get cloud.google.com/go/alloydbconn
```

--------------------------------

### Start Antigravity CLI

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-migrate-from-ai-studio/SKILL.md

Run this command to start the Antigravity CLI after installation.

```bash
agy
```

--------------------------------

### Install Go Client Library

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-run-basics/references/client-library-usage.md

Install the Cloud Run API v2 client library for Go using the go get command. This command fetches and installs the specified package.

```bash
go get cloud.google.com/go/run/apiv2
```

--------------------------------

### Example: Firebase CLI Deploy Command Help

Source: https://github.com/google/skills/blob/main/skills/cloud/firebase-basics/references/cli-usage.md

Shows how to get help for the `deploy` command in the Firebase CLI. Always use `npx` to ensure the latest version.

```bash
npx -y firebase-tools@latest deploy --help
```

--------------------------------

### Enable GKE API, Create and Configure Cluster, Deploy Application

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/SKILL.md

This snippet demonstrates the essential steps to get started with GKE: enabling the container API, creating an Autopilot cluster, configuring kubectl credentials, and deploying a sample application.

```bash
gcloud services enable container.googleapis.com --quiet
gcloud container clusters create-auto my-cluster --region=us-central1 --quiet
gcloud container clusters get-credentials my-cluster --region=us-central1 --quiet
kubectl create deployment hello-server \
  --image=us-docker.pkg.dev/google-samples/containers/gke/hello-app:1.0
```

--------------------------------

### Query Data with BigQuery Client Library (Go)

Source: https://github.com/google/skills/blob/main/skills/cloud/bigquery-basics/references/client-library-usage.md

Use the BigQuery client library in Go to create a client, construct a query, and initiate a read operation. This example shows basic setup and query execution.

```go
ctx := context.Background()
client, _ := bigquery.NewClient(ctx, "project-id")
q := client.Query("SELECT * FROM dataset.table")
it, _ := q.Read(ctx)
```

--------------------------------

### Example: Firebase CLI Firestore Indexes Command Help

Source: https://github.com/google/skills/blob/main/skills/cloud/firebase-basics/references/cli-usage.md

Demonstrates how to get help for the `firestore:indexes` command in the Firebase CLI. Always use `npx` to ensure the latest version.

```bash
npx -y firebase-tools@latest firestore:indexes --help
```

--------------------------------

### Install Cloud SQL Go Connector

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-sql-basics/references/client-library-usage.md

Install the Cloud SQL Go connector package using go get. This package provides the necessary functionality for Go applications.

```bash
go get cloud.google.com/go/cloudsqlconn
```

--------------------------------

### Install Python Client Library

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-run-basics/references/client-library-usage.md

Install the Google Cloud Run client library for Python using pip. Ensure you have pip installed and are using a virtual environment.

```bash
pip install --upgrade google-cloud-run
```

--------------------------------

### Install Kubernetes Client Library (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/client-library-usage.md

Install the Python Kubernetes client library using pip.

```bash
pip install kubernetes
```

--------------------------------

### Install Kubernetes Client Library (Node.js)

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/client-library-usage.md

Install the Node.js Kubernetes client library using npm.

```bash
npm install @kubernetes/client-node
```

--------------------------------

### Install Node.js Client Library

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-run-basics/references/client-library-usage.md

Install the Google Cloud Run client library for Node.js using npm. This command installs the package and its dependencies.

```bash
npm install @google-cloud/run
```

--------------------------------

### Install Required Libraries and Authenticate

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-skill-registry/SKILL.md

Install the necessary Python libraries and authenticate with Google Cloud using application default login.

```bash
# Install required libraries
pip install google-auth requests

# Authenticate with Google Cloud
gcloud auth application-default login
```

--------------------------------

### Manual ADC Setup

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-migrate-from-ai-studio/SKILL.md

Manually set up Application Default Credentials by logging in and configuring them.

```bash
gcloud auth login
gcloud auth application-default login
```

--------------------------------

### Install OpenAI and Google Auth Libraries

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-inference/SKILL.md

Install the necessary Python libraries for using the OpenAI SDK with Google Cloud authentication.

```bash
pip install openai google-auth
```

--------------------------------

### Verify Environment Setup

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-inference/SKILL.md

Runs all sample scripts in the scripts/ directory to verify that the environment is correctly set up and all dependencies are working as expected.

```bash
./scripts/verify_all.sh
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-inference/SKILL.md

Installs all required Python SDKs and libraries listed in the requirements.txt file. Ensure the virtual environment is activated before running this command.

```bash
pip install -r scripts/requirements.txt
```

--------------------------------

### Check NPM Installation

Source: https://github.com/google/skills/blob/main/skills/cloud/firebase-basics/SKILL.md

Verify if Node Package Manager (NPM) is installed on the system. If not, guide the user to install Node.js LTS.

```bash
## Check if NPM is installed
npm --version
```

--------------------------------

### Agent Configuration Response Example

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-agents-api/SKILL.md

This JSON shows a typical response when retrieving an agent's configuration. It includes details like name, base agent, description, system instruction, tools, and base environment setup.

```json
{
  "name": "projects/your-project-id/locations/global/agents/my-custom-agent",
  "base_agent": "antigravity-preview-05-2026",
  "description": "A professional agent configured with remote tools and mounted Cloud Storage directories.",
  "system_instruction": "You are a helpful, domain-expert assistant.",
  "tools": [
    {"type": "code_execution"},
    {"type": "filesystem"},
    {"type": "google_search"},
    {"type": "url_context"}
  ],
  "base_environment": {
    "type": "remote",
    "sources": [
      {
        "type": "gcs",
        "source": "gs://your-agent-bucket-name/skills",
        "target": "/.agent/skills"
      }
    ],
    "network": {
      "allowlist": [
        { "domain": "*" }
      ]
    }
  }
}
```

--------------------------------

### Example: Generate Manifest for Gemma 2 9B on L4 GPU

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-inference.md

An example of generating a Kubernetes manifest for the Gemma 2 9B model using the vLLM server on an NVIDIA L4 GPU, targeting a specific latency.

```bash
gcloud container ai profiles manifests create \
  --model=gemma-2-9b-it \
  --model-server=vllm \
  --accelerator-type=nvidia-l4 \
  --target-ntpot-milliseconds=50 --quiet > inference.yaml
```

--------------------------------

### Deploy Model with Traffic Split (Example)

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-endpoint-management/SKILL.md

This is an example command for deploying a model with a specific traffic split, typically done via 'gcloud ai endpoints deploy-model'. Refer to the 'agent-platform-deploy' skill for detailed deployment instructions.

```bash
# Example: Deploying a model with a specific traffic split is usually done
# via 'gcloud ai endpoints deploy-model'.
```

--------------------------------

### List Supported Models

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-inference.md

Use this command to list all available AI/ML models supported by the GKE Inference Quickstart.

```bash
gcloud container ai profiles models list --quiet
```

--------------------------------

### Install GenAI SDK

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-inference/SKILL.md

Installs the Google GenAI SDK, which is the preferred method for interacting with Gemini models on Google Cloud Agent Platform.

```bash
pip install google-genai
```

--------------------------------

### Install Agent Skills

Source: https://github.com/google/skills/blob/main/README.md

Use this command to install Agent Skills from the Google repository. You can then select specific skills to add to your project.

```bash
npx skills add google/skills
```

--------------------------------

### Verify Workload Identity Federation Setup

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-security.md

This command verifies the Workload Identity Federation setup by running a test pod and listing its authentication status.

```bash
kubectl run workload-identity-test \
  --image=gcr.io/google.com/cloudsdktool/cloud-sdk:slim \
  --serviceaccount=<KSA_NAME> --namespace=<NAMESPACE> \
  --rm -it -- gcloud auth list --quiet
```

--------------------------------

### Install Kueue

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-batch-hpc.md

Install Kueue using kubectl to manage job scheduling and resource allocation for batch workloads.

```bash
kubectl apply --server-side -f https://github.com/kubernetes-sigs/kueue/releases/latest/download/manifests.yaml
```

--------------------------------

### Install Helm Chart

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/cli-reference.md

Installs a Helm chart for a release in a specified namespace. This is a kubectl-only operation.

```bash
helm install <RELEASE> <CHART> -n <NAMESPACE>
```

--------------------------------

### GPU Configuration Example

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-compute-classes.md

Specifies GPU requirements within a PriorityRule, including type, count, and optional driver version.

```yaml
gpu:
  type: "nvidia-l4"        # nvidia-l4, nvidia-h100-80gb, etc.
  count: 1                 # GPUs per node
  driverVersion: "latest"  # Optional
```

--------------------------------

### Install Agent Platform Evaluation SDK

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-eval-flywheel/SKILL.md

Install the necessary SDKs for agent platform evaluation. Ensure you have version 1.154.0 or higher for aiplatform and version 1.0.0 or higher for google-genai.

```bash
pip install google-cloud-aiplatform[evaluation]>=1.154.0 google-genai>=1.0.0
```

--------------------------------

### Automated ADC Setup Script

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-migrate-from-ai-studio/SKILL.md

Use this script for automated Application Default Credentials setup for local debugging or script execution.

```bash
bash <(curl -sSL https://storage.googleapis.com/cloud-samples-data/adc/setup_adc.sh)
```

--------------------------------

### Install BigQuery Client Library (Node.js)

Source: https://github.com/google/skills/blob/main/skills/cloud/bigquery-basics/references/client-library-usage.md

Install the BigQuery client library for Node.js using npm. This is necessary for integrating BigQuery into your JavaScript applications.

```bash
npm install @google-cloud/bigquery
```

--------------------------------

### Install BigQuery Client Library (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/bigquery-basics/references/client-library-usage.md

Install the BigQuery client library for Python using pip. This is required before using the library in your Python projects.

```bash
pip install --upgrade google-cloud-bigquery
```

--------------------------------

### Python Example for OpenMaaS Completions API

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-inference/SKILL.md

Example of using the OpenAI SDK's Completions API with OpenMaaS models. This is suitable for models like 'zai-org/glm-5-maas' and others listed.

```python
response = client.completions.create(
    model="deepseek-ai/deepseek-v3.2-maas",
    prompt="Once upon a time",
    max_tokens=100
)
print(response.choices[0].text)
```

--------------------------------

### List Artifacts Locations

Source: https://github.com/google/skills/blob/main/skills/cloud/gcloud/SKILL.md

Example command to list locations for the Artifact Registry service. Ensure to specify the project ID.

```bash
gcloud artifacts locations list
```

--------------------------------

### Location Configuration Example

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-compute-classes.md

Specifies zone targeting for nodes within a PriorityRule, either by listing specific zones or allowing GKE to pick any zone.

```yaml
location:
  zones:
    - "us-central1-a"
    - "us-central1-b"
  # OR
  type: "Any"              # Let GKE pick from cluster zones
```

--------------------------------

### TPU Configuration Example

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-compute-classes.md

Defines TPU configuration within a PriorityRule, specifying type, count, and topology.

```yaml
tpu:
  type: "v5p-slice"
  count: 8
  topology: "2x2x1"
```

--------------------------------

### Get Global Firebase CLI Help

Source: https://github.com/google/skills/blob/main/skills/cloud/firebase-basics/references/cli-usage.md

Lists all available commands and categories for the Firebase CLI. Always use `npx` to ensure the latest version.

```bash
npx -y firebase-tools@latest --help
```

--------------------------------

### Create and Activate Virtual Environment

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-tuning/SKILL.md

Creates a Python virtual environment named 'tuning_agent_venv' and installs dependencies from 'requirements.txt'. Remember to activate this environment before running any Python commands.

```bash
python3 -m venv ~/tuning_agent_venv
source ~/tuning_agent_venv/bin/activate
pip install -r references/requirements.txt
```

--------------------------------

### List KMS Locations

Source: https://github.com/google/skills/blob/main/skills/cloud/gcloud/SKILL.md

Example command to list locations for the Key Management Service (KMS). Ensure to specify the project ID.

```bash
gcloud kms locations list
```

--------------------------------

### Get Agent

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-agents-api/SKILL.md

Retrieve the configuration metadata, tools, and environment setup of an existing custom agent.

```APIDOC
## GET /v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents/{AGENT_ID}

### Description
Retrieve the configuration metadata, tools, and environment setup of an existing custom agent.

### Method
GET

### Endpoint
`https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents/{AGENT_ID}`

### Response Example
Returns the complete configured state of the custom Agent resource:
```json
{
  "name": "projects/your-project-id/locations/global/agents/my-custom-agent",
  "base_agent": "antigravity-preview-05-2026",
  "description": "A professional agent configured with remote tools and mounted Cloud Storage directories.",
  "system_instruction": "You are a helpful, domain-expert assistant.",
  "tools": [
    {"type": "code_execution"},
    {"type": "filesystem"},
    {"type": "google_search"},
    {"type": "url_context"}
  ],
  "base_environment": {
    "type": "remote",
    "sources": [
      {
        "type": "gcs",
        "source": "gs://your-agent-bucket-name/skills",
        "target": "/.agent/skills"
      }
    ],
    "network": {
      "allowlist": [
        { "domain": "*" }
      ]
    }
  }
}
```
```

--------------------------------

### List Cloud Run Services in Go

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-run-basics/references/client-library-usage.md

Use the Go client library to list Cloud Run services. This example initializes the client, creates a request, and iterates through the services, printing their names. Ensure the necessary packages are imported and the client is properly closed.

```go
package main

import (
	"context"
	"fmt"
	"log"

	run "cloud.google.com/go/run/apiv2"
	runpb "cloud.google.com/go/run/apiv2/runpb"
	"google.golang.org/api/iterator"
)

func main() {
	ctx := context.Background()
	client, err := run.NewServicesClient(ctx)
	if err != nil {
		// Log the error and exit if the client can't be created
		log.Fatalf("Failed to create Cloud Run Services client: %v", err)
	}
	defer client.Close()

	req := &runpb.ListServicesRequest{
		Parent: "projects/my-project/locations/us-central1", // Remember to replace my-project
	}
	it := client.ListServices(ctx, req)

	fmt.Println("Cloud Run Services:")
	for {
		resp, err := it.Next()
		if err == iterator.Done {
			break // Finished iterating successfully
		}
		if err != nil {
			// Log the error and exit if iteration fails
			log.Fatalf("Error iterating services: %v", err)
		}
		fmt.Println(resp.GetName())
	}
}
```

--------------------------------

### Python Cloud SQL Connector Usage

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-sql-basics/references/client-library-usage.md

Example of using the Python Cloud SQL Connector to establish a database connection. This requires the connector to be installed and configured with your instance details.

```python
from google.cloud.sql.connector import Connector
connector = Connector()
def getconn():
  conn = connector.connect(
      "project:region:instance",
      "pg8000",
      user="my-user",
      password="my-password",
      db="my-db"
  )
  return conn
```

--------------------------------

### Storage Configuration Example

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-compute-classes.md

Configures boot disk and local SSD storage within a PriorityRule, including disk type, size, CMEK, and local SSD interface.

```yaml
storage:
  bootDisk:
    type: "pd-balanced"     # pd-balanced (golden path), pd-ssd, hyperdisk-balanced
    sizeGb: 100
    kmsKey: "projects/.../cryptoKeys/..."  # Optional CMEK
  localSsd:
    count: 1
    interface: "NVME"
```

--------------------------------

### Create Vertical Pod Autoscaler (VPA) in Recommendation Mode

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-scaling.md

Create a VPA configured to only provide resource recommendations without applying them automatically. This is the safest mode to start with.

```yaml
apiVersion: autoscaling.k8s.io/v1
kind: VerticalPodAutoscaler
metadata:
  name: <DEPLOYMENT>-vpa
spec:
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: <DEPLOYMENT>
  updatePolicy:
    updateMode: "Off"
```

--------------------------------

### Get Agent Configuration

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-agents-api/SKILL.md

Use this curl command to retrieve the configuration metadata, tools, and environment setup of an existing custom agent. Replace placeholders with your project, location, and agent IDs.

```bash
curl -X GET "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/agents/my-custom-agent" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json"
```

--------------------------------

### List Cloud Run Services in Node.js (TypeScript)

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-run-basics/references/client-library-usage.md

Use the Node.js client library to list Cloud Run services. This example demonstrates asynchronous fetching of services. Ensure the @google-cloud/run package is installed.

```typescript
import {ServicesClient} from '@google-cloud/run';
const client = new ServicesClient();
const [services] = await client.listServices({
  parent: 'projects/my-project/locations/us-central1',
});
```

--------------------------------

### List Pods using Kubernetes Client Library (Go)

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/client-library-usage.md

Builds Kubernetes client configuration and lists pods in all namespaces. Requires `kubeconfig` to be set.

```go
import (
    "k8s.io/client-go/kubernetes"
    "k8s.io/client-go/tools/clientcmd"
)
config, _ := clientcmd.BuildConfigFromFlags("", kubeconfig)
clientset, _ := kubernetes.NewForConfig(config)
pods, _ := clientset.CoreV1().Pods("").List(
    context.TODO, metav1.ListOptions{})
```

--------------------------------

### Install Cloud SQL Python Connector for PostgreSQL

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-sql-basics/references/client-library-usage.md

Install the Python connector for PostgreSQL instances using pip. Ensure you have the necessary database driver installed.

```bash
pip install "cloud-sql-python-connector[pg8000]"
```

--------------------------------

### Install Firebase Agent Skills

Source: https://github.com/google/skills/blob/main/skills/cloud/firebase-basics/SKILL.md

Ensure the full set of Firebase agent skills is installed or updated to avoid using outdated patterns. This command also updates existing installations.

```bash
npx -y skills add firebase/agent-skills -y
```

--------------------------------

### Create Agent with Cloud Storage Mounted Resources

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-agents-api/SKILL.md

Use a POST request to create a new agent. This example demonstrates mounting files and skills from a Google Cloud Storage bucket and configuring tools and system instructions. Creating an agent is a Long-Running Operation.

```bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/agents" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json; charset=utf-8" \
  -d '{
    "id": "my-custom-agent",
    "base_agent": "antigravity-preview-05-2026",
    "description": "A professional agent configured with remote tools and mounted Cloud Storage directories.",
    "system_instruction": "You are a helpful, domain-expert assistant.",
    "tools": [
      {"type": "code_execution"},
      {"type": "filesystem"},
      {"type": "google_search"},
      {"type": "url_context"}
    ],
    "base_environment": {
      "type": "remote",
      "sources": [
        {
          "type": "gcs",
          "source": "gs://your-agent-bucket-name/skills",
          "target": "/.agent/skills"
        }
      ],
      "network": {
        "allowlist": [
          { "domain": "*" }
        ]
      }
    }
  }'
```

--------------------------------

### Check gcloud CLI Installation

Source: https://github.com/google/skills/blob/main/skills/cloud/google-cloud-recipe-onboarding/SKILL.md

Verifies if the gcloud CLI binary is installed and accessible on the host system.

```bash
which gcloud
```

--------------------------------

### Install MPI Operator

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-batch-hpc.md

Install the MPI Operator using kubectl to manage MPI-based HPC applications on Kubernetes.

```bash
kubectl apply -f https://raw.githubusercontent.com/kubeflow/mpi-operator/master/deploy/v2beta1/mpi-operator.yaml
```

--------------------------------

### List All Skills

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-skill-registry/references/query-skills.md

Execute this command to list all skills available in the registry for the configured project and location. No specific flags are required.

```bash
python3 scripts/skill_registry_ops.py list
```

--------------------------------

### List Pods using Kubernetes Client Library (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/client-library-usage.md

Loads Kubernetes configuration and lists pods with their IPs across all namespaces. Requires `~/.kube/config` to be set up.

```python
from kubernetes import client, config
config.load_kube_config() # Loads from ~/.kube/config
v1 = client.CoreV1Api()
print("Listing pods with their IPs:")
ret = v1.list_pod_for_all_namespaces(watch=False)
for i in ret.items:
    print("%s\t%s\t%s" % (i.status.pod_ip, i.metadata.namespace, i.metadata.name))
```

--------------------------------

### Install AlloyDB Python Connector and SQLAlchemy

Source: https://github.com/google/skills/blob/main/skills/cloud/alloydb-basics/references/client-library-usage.md

Install the necessary Python packages for the AlloyDB connector and SQLAlchemy for database interaction.

```bash
pip install "google-cloud-alloydb-connector[pg8000]" sqlalchemy
```

--------------------------------

### Install BigQuery DataFrames (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/bigquery-basics/references/client-library-usage.md

Install the bigframes library for Python using pip. This library provides a pandas-like API for BigQuery.

```bash
pip install --upgrade bigframes
```

--------------------------------

### Describe VPA Recommendations

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-scaling.md

Use this command to view the resource recommendations provided by the Vertical Pod Autoscaler (VPA). This helps in understanding current resource usage and potential optimizations.

```bash
kubectl describe vpa <NAME>
```

--------------------------------

### Go Usage Example with AlloyDB Driver

Source: https://github.com/google/skills/blob/main/skills/cloud/alloydb-basics/references/client-library-usage.md

Connect to an AlloyDB instance using the custom AlloyDB Go driver and execute a simple query. Ensure the driver is registered before opening the database connection.

```go
package main

import (
    "database/sql"
    "fmt"
    "log"

    "cloud.google.com/go/alloydbconn/driver/pgxv5"
)

func main() {
    // Register the AlloyDB driver with the name "alloydb"
    // Uses Private IP by default. See Network Options below for details.
    cleanup, err := pgxv5.RegisterDriver("alloydb")
    if err != nil {
        log.Fatal(err)
    }
    defer cleanup()

    // Instance URI format:
    //   projects/PROJECT/locations/REGION/clusters/CLUSTER/instances/INSTANCE
    db, err := sql.Open("alloydb", fmt.Sprintf(
        "host=%s user=%s password=%s dbname=%s sslmode=disable",
        "projects/my-project/locations/us-central1/clusters/my-cluster/instances/my-instance",
        "my-user",
        "my-password",
        "my-db",
    ))
    if err != nil {
        log.Fatal(err)
    }
    defer db.Close()

    var greeting string
    if err := db.QueryRow("SELECT 'Hello, AlloyDB!'").Scan(&greeting); err != nil {
        log.Fatal(err)
    }
    fmt.Println(greeting)
}
```

--------------------------------

### Initialize Agent Platform Client

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-eval-flywheel/SKILL.md

Initializes the Agent Platform client with project and location. Ensure you replace 'PROJECT_ID' and 'LOCATION' with your actual values.

```python
import agentplatform
from agentplatform import types
from google.genai import types as genai_types
import pandas as pd

# Initialize client
client = agentplatform.Client(project="PROJECT_ID", location="LOCATION")
```

--------------------------------

### Initialize Client with Environment Variables (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-interactions-api/SKILL.md

Initialize the Gemini API client using environment variables for automatic configuration. Ensure GOOGLE_GENAI_USE_ENTERPRISE is set to true.

```bash
export GOOGLE_GENAI_USE_ENTERPRISE=true
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="global"
```

```python
from google import genai

client = genai.Client()
```

--------------------------------

### Structured Output Generation with AI.GENERATE

Source: https://github.com/google/skills/blob/main/skills/cloud/bigquery-basics/references/bigquery_ai_generate.md

This example demonstrates how to extract specific information into a structured format using the `output_schema` argument. The output fields will match the defined schema.

```sql
SELECT
  AI.GENERATE(
    'Extract the date and amount from this invoice: ' || invoice_text,
    output_schema => 'date DATE, amount FLOAT64'
  ) as extracted_data
FROM `dataset.invoices`;
```

--------------------------------

### Upload Skill from Folder

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-skill-registry/references/manage-skills.md

Use this command to upload a new skill by providing the path to its local folder. Ensure all required flags like skill ID, display name, description, and folder path are included.

```bash
python3 scripts/skill_registry_ops.py upload \
  --skill-id "my-sample-skill" \
  --display-name "My Sample Skill" \
  --description "A test skill uploaded via script." \
  --folder "/path/to/skill/folder"
```

--------------------------------

### Generate Video with Veo Model

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-api/references/media_generation.md

Generate video content using the Veo model. This example demonstrates setting up video generation with an optional initial image and polling for the operation's completion. Note that Veo usage can be costly.

```python
import time
from google import genai
from google.genai import types
from PIL import Image

client = genai.Client()

image = Image.open("image.png")  # Optional initial image

# Video generation is an async operation
operation = client.models.generate_videos(
    model="veo-3.1-fast-generate-001",
    prompt="a cat reading a book",
    image=image,
    config=types.GenerateVideosConfig(
        person_generation="dont_allow",
        aspect_ratio="16:9",
        number_of_videos=1,
        duration_seconds=5,
        output_gcs_uri="gs://your-bucket/your-prefix",
    ),
)

# Poll for completion
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

if operation.response:
    print(operation.result.generated_videos[0].video.uri)
```

--------------------------------

### Install Cloud SQL Node.js Connector

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-sql-basics/references/client-library-usage.md

Install the Cloud SQL Node.js connector package using npm. This is required for Node.js applications to connect to Cloud SQL.

```bash
npm install @google-cloud/cloud-sql-connector
```

--------------------------------

### Set up Application Default Credentials (ADC)

Source: https://github.com/google/skills/blob/main/skills/cloud/gcloud/SKILL.md

Authenticate code calls from local applications or SDK libraries. Use `--no-browser` for headless environments.

```bash
gcloud auth application-default login --no-browser
```

--------------------------------

### Start Cloud SQL Auth Proxy

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-sql-basics/SKILL.md

Starts the Cloud SQL Auth Proxy in a separate terminal. This proxy facilitates secure connections to your Cloud SQL instance.

```bash
./cloud-sql-proxy INSTANCE_CONNECTION_NAME
```

--------------------------------

### Single-Turn Interaction Response Example

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-interactions-api/SKILL.md

Example JSON response from a single-turn Gemini Interactions API call. It includes the interaction ID, conversation steps, and usage statistics.

```json
{
  "id": "your-interaction-id",
  "status": "completed",
  "steps": [
    {
      "role": "model",
      "content": [
        {
          "type": "text",
          "text": "Serverless computing is a cloud execution model where the cloud provider dynamically manages the allocation and provisioning of servers, charging customers based on actual usage rather than pre-purchased capacity."
        }
      ]
    }
  ],
  "usage": {
    "total_tokens": 24751,
    "total_input_tokens": 23894,
    "total_output_tokens": 857
  },
  "created": "2026-05-08T10:44:43Z",
  "updated": "2026-05-08T10:44:43Z",
  "environment_id": "your-environment-id",
  "object": "interaction"
}
```

--------------------------------

### Initializing Gemini Client for Agent Platform

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-migrate-from-ai-studio/SKILL.md

Initialize the Google GenAI client. The client automatically uses the enterprise environment flag.

```python
from google import genai

# The client automatically picks up the GOOGLE_GENAI_USE_ENTERPRISE=TRUE environment flag
client = genai.Client()

response = client.models.generate_content(
    model='gemini-3-flash-preview',
    contents='Hello world!',
)
print(response.text)
```

--------------------------------

### Instruction (Prompt/Completion) JSONL Format

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-tuning/references/data_prep.md

Suitable for base models or simple completion tasks. Provide a 'prompt' and its corresponding 'completion'.

```json
{
  "prompt": "Summarize the following text: [TEXTКак]",
  "completion": "[SUMMARY]"
}
```

--------------------------------

### Python Example for OpenMaaS Embeddings

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-inference/SKILL.md

Example of using the OpenAI SDK to generate embeddings for text using OpenMaaS embedding models. Ensure the Model ID is verified on Model Garden.

```python
# Verify specific Embedding Model ID on Model Garden (e.g., intfloat/multilingual-e5-small)
response = client.embeddings.create(
    model="intfloat/multilingual-e5-large-maas",
    input="The quick brown fox jumps over the lazy dog",
)
print(response.data[0].embedding)
```

--------------------------------

### Create a Cloud SQL Instance

Source: https://github.com/google/skills/blob/main/skills/cloud/cloud-sql-basics/references/cli-usage.md

Use this command to provision a new Cloud SQL instance with specified database version, machine tier, and region. The --quiet flag suppresses interactive prompts.

```bash
gcloud sql instances create my-instance --database-version=MYSQL_8_0 \
    --tier=db-f1-micro --region=us-central1 \
    --quiet
```

--------------------------------

### List Deployment Configuration for a Specific Model

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-deploy/SKILL.md

Check the supported machine types and accelerators for a specific model, such as google/gemma3@gemma-3-27b-it.

```bash
gcloud ai model-garden models list-deployment-config \
    --model="google/gemma3@gemma-3-27b-it"
```

--------------------------------

### Initialize Gemini Client with Environment Variables (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-api/SKILL.md

Initialize the Gemini client in Python. It automatically picks up environment variables for authentication and configuration.

```python
from google import genai

client = genai.Client()
```

--------------------------------

### Initializing ADK Agent with Tools

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-migrate-from-ai-studio/SKILL.md

Initialize an Agent Development Kit (ADK) agent, defining its model, name, description, instructions, and available tools.

```python
from google.adk.agents.llm_agent import Agent

def get_current_time(city: str) -> dict:
    """Returns the current time in a specified city."""
    return {"status": "success", "city": city, "time": "10:30 AM"}

root_agent = Agent(
    model='gemini-3-flash-preview',
    name='root_agent',
    description="Tells the current time in a specified city.",
    instruction="You are a helpful assistant that tells the current time in cities. Use the 'get_current_time' tool for this purpose.",
    tools=[get_current_time],
)
```

--------------------------------

### Initialize Gemini Client with Hard-coded Parameters (Python)

Source: https://github.com/google/skills/blob/main/skills/cloud/gemini-api/SKILL.md

Initialize the Gemini client in Python by explicitly providing enterprise, project, and location parameters.

```python
from google import genai

client = genai.Client(
    enterprise=True,
    project="your-project-id",
    location="global",
)
```

--------------------------------

### Get AlloyDB Cluster Info

Source: https://github.com/google/skills/blob/main/skills/cloud/alloydb-basics/references/cli-usage.md

Use this command to retrieve detailed information about a specific AlloyDB cluster.

```bash
gcloud alloydb clusters describe CLUSTER_ID --region=REGION
```

--------------------------------

### Update gcloud CLI

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-tuning/SKILL.md

Updates the gcloud CLI to the latest version quietly. This command is used during environment setup.

```bash
gcloud components update --quiet > /dev/null 2>&1
```

--------------------------------

### Get Node Resource Usage with kubectl

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/cli-reference.md

Displays the CPU and memory usage of nodes in the cluster. This is a kubectl-only operation.

```bash
kubectl top nodes
```

--------------------------------

### Find Compatible Hardware for a Model

Source: https://github.com/google/skills/blob/main/skills/cloud/gke-basics/references/gke-inference.md

Find valid accelerator and server combinations for a specific AI/ML model.

```bash
# Find valid accelerator/server combinations for a model
gcloud container ai profiles list --model=<MODEL_NAME> --quiet

# Example: what can run Gemma 2 9B?
gcloud container ai profiles list --model=gemma-2-9b-it --quiet
```

--------------------------------

### Python Usage Example with SQLAlchemy

Source: https://github.com/google/skills/blob/main/skills/cloud/alloydb-basics/references/client-library-usage.md

Connect to an AlloyDB instance using the Python connector and SQLAlchemy, executing a simple query.

```python
import sqlalchemy
from google.cloud.alloydbconnector import Connector

INSTANCE_URI = "projects/MY_PROJECT/locations/MY_REGION/clusters/MY_CLUSTER/instances/MY_INSTANCE"

with Connector() as connector:
    pool = sqlalchemy.create_engine(
        "postgresql+pg8000://",
        creator=lambda: connector.connect(
            INSTANCE_URI,
            "pg8000",
            user="my-user",
            password="my-password",
            db="my-db",
        ),
    )

    with pool.connect() as conn:
        result = conn.execute(sqlalchemy.text("SELECT NOW()")).fetchone()
        print(result)
```

--------------------------------

### Upload Skill from Zip File

Source: https://github.com/google/skills/blob/main/skills/cloud/agent-platform-skill-registry/references/manage-skills.md

This command uploads a new skill using a .zip file. It requires the skill ID, display name, description, and the path to the .zip file. This is an alternative to uploading from a folder.

```bash
python3 scripts/skill_registry_ops.py upload \
  --skill-id "my-sample-skill" \
  --display-name "My Sample Skill" \
  --description "A test skill uploaded via script." \
  --zip-file "/path/to/skill.zip"
```