查找技能

Turn plain-language requests into Cloud Logging queries for Google Cloud. Generate service-specific filters to find errors, investigate issues, or review audit logs using LQL, the language used to search these logs.

中文简介正在准备中。当前显示英语简介。

• Finding recent error logs
• Filtering logs for a specific Google Cloud service
• Investigating who changed or accessed a resource

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.

中文简介正在准备中。当前显示英语简介。

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

Add Google Mobile Ads banners to Android, iOS, or Unity apps. Guides implementation from defining the ad view and choosing its size to handling load events, loading the banner, and checking the completed integration.

中文简介正在准备中。当前显示英语简介。

• Add a banner ad to an Android app
• Place an adaptive banner at the top or bottom of an iOS app
• Integrate a banner ad into a Unity app

Configure Cloud Logging within one Google Cloud project. Set storage locations, retention periods, routing rules, and viewing permissions; create metrics from logs; and adjust stored volume through exclusions or sampling, which retains only a portion of entries.

中文简介正在准备中。当前显示英语简介。

• Set regional log storage and retention periods
• Restrict access to sensitive logs
• Count specific errors with logs-based metrics

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Guides migration from Google AI Studio’s Gemini API to Gemini Enterprise Agent Platform on Google Cloud, covering billing, access permissions, authentication, and connection settings for SDKs and supported agent tools.

中文简介正在准备中。当前显示英语简介。

• Moving a Gemini application to Google Cloud
• Using Google Cloud credits for Gemini API calls
• Unifying agent authentication and billing

Investigate 403 and 500 errors in Google Cloud Gemini Enterprise Agent Platform. Examine logs, registered destinations, agent identities, and authorization policies to produce a diagnostic report with evidence, recommended fixes, and verification steps.

中文简介正在准备中。当前显示英语简介。

• Investigating 403 errors when an agent calls an external API
• Diagnosing Agent Runtime 500 errors involving Model Armor
• Checking registration and permissions for failing MCP connections

Set up the official Google Ads MCP Server, a connector that lets AI assistants retrieve campaign data and reporting metrics through natural language. The guide covers installation, credentials, client configuration, and connection checks.

中文简介正在准备中。当前显示英语简介。

• Connecting Claude Code or Cursor to Google Ads
• Configuring API credentials and environment variables
• Testing campaign queries in natural language

Investigate failing or slow BigQuery jobs and unexpected cost increases. Compare execution details and resource usage with a normal baseline to isolate bottlenecks, identify likely causes, and determine practical remediation steps.

中文简介正在准备中。当前显示英语简介。

• Investigate failed or slow BigQuery jobs
• Locate bottlenecks in execution stages
• Diagnose sudden increases in query or capacity costs

Integrate video and audio ads into websites, apps, and TV platforms with Google IMA SDK. Follow platform-specific guidance for client-side ad requests, playback coordination, error handling, and cleanup after ads finish.

中文简介正在准备中。当前显示英语简介。

• Adding video ads to a website
• Integrating ads into mobile and TV apps
• Coordinating ad playback with main content

Turn Cloud Monitoring metric definitions and resource filters into validated PromQL queries, a language for querying monitoring data. Choose suitable aggregation functions, preserve supplied resource names, and format queries for use in Cloud Monitoring.

中文简介正在准备中。当前显示英语简介。

• Convert Cloud Monitoring metric definitions into PromQL
• Filter monitoring queries to specific resources
• Choose aggregations that match metric types

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.

中文简介正在准备中。当前显示英语简介。

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

Implement rewarded ads with the Google Mobile Ads SDK on Android, iOS, or Unity. Add a user interface for choosing to view an ad for a reward, and follow steps for loading, event handling, display, and verification.

中文简介正在准备中。当前显示英语简介。

• Add ads users choose to view for in-app rewards
• Implement rewarded ads on Android or iOS
• Integrate rewarded ads into a Unity app

Guides implementation of audience uploads, individual removals, and full replacements through the Data Manager API. It covers formatting and hashing identifiers, validating requests, and checking processing results for Customer Match and supported device ID audiences.

中文简介正在准备中。当前显示英语简介。

• Upload Customer Match audience members
• Remove selected users from an audience
• Clear or replace an entire audience

Create Terraform files that define alerts for AI agent latency, errors, token use, safety, security, and response quality. Check telemetry and existing policies first, then validate the generated configuration. Quality alerts require Vertex AI.

中文简介正在准备中。当前显示英语简介。

• Configure alerts for agent latency and error rates
• Monitor rapid increases in token usage
• Monitor safety triggers and permission denials

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.

中文简介正在准备中。当前显示英语简介。

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

Helps developers send conversion and event data to Google Ads, Google Analytics, and Floodlight through the Data Manager API. It covers destination setup, data formatting, validation, migration from other APIs, and checking processing results.

中文简介正在准备中。当前显示英语简介。

• Implement offline conversion uploads to Google Ads
• Send recommended or custom GA4 events
• Migrate event ingestion from another Google API

Configure Google Cloud logs across multiple projects, either by storing them centrally or querying them together where they already reside. The skill guides routing, access permissions, and log views, and helps diagnose missing logs and permission failures.

中文简介正在准备中。当前显示英语简介。

• Collect logs from multiple projects in one central bucket
• Query distributed logs without copying their data
• Set log access boundaries by project or log type

Prepare a local development environment for the Data Manager API with authentication and library installation guidance. It covers five programming languages and companion utilities for formatting, hashing, and encrypting user identifiers before ingestion.

中文简介正在准备中。当前显示英语简介。

• Preparing a local environment for the Data Manager API
• Installing client and identifier utility libraries
• Configuring local credentials and access scopes

Turn Stitch designs into reusable React components for Vite projects, or update existing components to match revised designs. Organize interface elements, logic, and data separately while aligning styles and connecting navigation between pages.

中文简介正在准备中。当前显示英语简介。

• Build React screens from Stitch designs
• Update existing screens after design changes
• Split repeated interface elements into reusable components

Convert an existing frontend into a Stitch design by extracting a standalone HTML file and shared design rules, then uploading both to a project so you can revise the interface in Stitch.

中文简介正在准备中。当前显示英语简介。

• Move an existing web app into Stitch
• Review React or Vue component designs in Stitch
• Extract design rules alongside screen HTML

Turn Stitch designs into React and Vite dashboards with reusable components and asynchronous data fetching. It applies shared design settings from DESIGN.md, includes accessibility checks, and supports optional blockchain data reads.

中文简介正在准备中。当前显示英语简介。

• Build a React dashboard from a Stitch screen
• Apply shared design settings from DESIGN.md
• Add data fetching and loading states

Create and update shared design rules in Stitch, including colors, fonts, and corner shapes, then apply them to existing screens. Keep a DESIGN.md file and project metadata alongside the design system.

中文简介正在准备中。当前显示英语简介。

• Apply shared design rules across existing screens
• Turn a theme description into concrete design values
• Create or update a design system in Stitch