mirror of
https://github.com/google/skills.git
synced 2026-09-14 20:00:20 +08:00
Cloud IX Team
7faf00e6fe
An agent that needs one of the skills in this repository has no way to find out which one applies without reading every SKILL.md. This adds a small router skill that resolves the lookup at runtime instead. skills/developers/finding-google-skills/SKILL.md is the router. It fetches the catalog, matches a request against the entry descriptions, and then retrieves only the skills that matched. It carries no copy of the catalog, so having it loaded costs little more than its frontmatter. The skill is named for the capability it provides rather than for a product surface, so a reader who does not already know the catalog can still tell what it is for. Retrieval has to be byte-exact, because the agent uses each entry point URL verbatim and a paraphrased catalog yields invented links. The skill asks for a raw shell fetch first and names the alternatives that also return bytes, including Node where no shell fetch tool exists. On Windows it calls for curl.exe rather than curl, since bare curl resolves to an Invoke-WebRequest alias in Windows PowerShell that returns a formatted object. Where only a summarizing fetch tool is available, the skill phrases the request as extraction rather than transcription. Requesting the document verbatim returns nothing usable; requesting a list of the entry point fields returns all of them. A failed retrieval has to be reported rather than papered over. The skill retries, then falls back to listing the repository tree, and if it still has no catalog it says so instead of answering from memory. The catalog may be fetched once and reused within a session, since skills land infrequently enough that a second fetch between two lookups buys nothing. It is not carried beyond the session. If a lookup finds no match, the skill refetches once before concluding that none exists. index.json is the catalog: a "skills" array holding one entry per published skill, with the skill name, its description, and the raw URL of its SKILL.md. A "generator" note sits above the array, so the first thing anyone opening the file reads is that it is generated rather than maintained by hand. Entries are sorted by name and the formatting is fixed, so regenerating an unchanged tree reproduces the file byte for byte. It currently lists 126 skills. The note carries no timestamp and no content hash. Either one would make an unchanged tree regenerate to a different file, which would cost the staleness check its determinism. Fetching the catalog on demand rather than carrying it in context means a session that never needs a lookup pays nothing for it. PiperOrigin-RevId: 972667621
Agent Skills
This repository contains Agent Skills for Google products and technologies, including Google Cloud.
Note
This repository is under active development.
Installation
npx skills add google/skills
From the npx install command, you can select the specific skills from this
repo to install.
Available Skills
- Getting started with Google Cloud
- Multi-product solution skills
- Google Cloud solution-architecture workflow
- Agent Gateway multi-agent security
- Agentic analytics across cloud providers and data types
- Borderless open data lakehouse agentic AI system
- Build and deploy AI agents on Google Cloud
- Data science workflow with AI agents solution
- Google Skill Finder
- Live bidirectional multimodal streaming agentic AI solution
- Migrate AI Workloads to GKE Inference
- RAG for enterprise search using GKE and AlloyDB
- Secure n-tier serverless web application with strict private application tiers
- AI/ML
- Agent Platform Alert Configuration
- Agent Platform Endpoint Management
- Agent Platform Eval Flywheel Skill
- Agent Platform GenAI Inference Skill
- Agent Platform Model Garden Deploy Skill
- Agent Platform Model Registry Management
- Agent Platform Model Tuning
- Agent Platform Prompt Management
- Agent Platform RAG Engine Management
- Agent Platform Troubleshooting
- Agent Platform Tuning Management
- BigQuery AI & ML
- Gemini API in Agent Platform
- Gemini Enterprise Agent Platform - Managed Agents API Skill
- Gemini Interactions API Skill
- Genkit Dart
- Genkit Go
- Genkit JS
- Genkit Python
- LiveAPI Service Skill
- Migrating from Gemini API in AI Studio to Agent Platform
- Skill Registry
- Infrastructure
- Designing and Deploying GCP Infrastructure with Application Design Center
- GKE AI/ML Inference
- GKE Alert Configuration
- GKE App Onboarding
- GKE Backup & Disaster Recovery
- GKE Basics & Critical Gotchas
- GKE Batch & HPC Workloads
- GKE Cluster Autoscaler
- GKE Cluster Creation
- GKE ComputeClasses
- GKE Golden Base Image Discovery Expert
- GKE Golden Path Configuration
- GKE JobSet Interruption Troubleshooting
- GKE Manifest Generation Skill
- GKE Multi-Tenancy
- GKE Networking
- GKE Productionize Skill
- GKE Reliability
- GKE Service Networking Skill
- GKE Storage
- GKE TPU Dynamic Slices Monitoring & Management
- GKE Upgrades & Maintenance
- GKE Workload Scaling
- GKE Workload Troubleshooting Skill
- Google Cloud Filestore Autoscale
- Google Cloud global external Application Load Balancer Configuration Skill
- Google Cloud Networking Observability Expert
- Google Cloud Storage Basics
- Google Cloud Storage FUSE
- Databases and analytics
- AlloyDB Basics
- BigFrames (BigQuery DataFrame) basics
- BigQuery Asset Impact Analysis
- BigQuery Basics
- Bigtable Basics
- Cloud SQL Basics
- Data Lineage Summary
- Dynamic Hybrid Search using AlloyDB
- GCP Managed Airflow DAG Authoring Guide
- Google Cloud Database Onboarding Skill
- Managed Service for Apache Airflow (formerly Cloud Composer) DAG troubleshooting guide
- Managed Service for Apache Airflow (formerly Cloud Composer) Migration Guide
- Spanner Basics
- Developer tools
- Management tools
- Cloud Monitoring Chart Generation Skill (
cloud-monitoring-chart-generation) - Cloud Monitoring ListTimeSeries Request Generator
- Cloud Monitoring PromQL Generator
- Configuring Cloud Logging
- Configuring Cross-Project Logging
- Generate Logging Query Language queries
- GKE Cost Analysis
- GKE Cost Optimization
- GKE Observability
- GKE TPU Metrics Monitoring Guide
- Handle Disruption on GPUs and TPUs Troubleshooting
- Metric Selection (Service Query & Local Keyword Filtering)
- SLO Alert Configuration Setup Wizard
- TPU Connection Failure and VBAR OOM Troubleshooting
- Workload Manager Basics
- Cloud Monitoring Chart Generation Skill (
- Well-Architected Framework
- Google Cloud Well-Architected Framework skill for the Cost Optimization pillar
- Google Cloud Well-Architected Framework skill for the Operational Excellence pillar
- Google Cloud Well-Architected Framework skill for the Performance Optimization pillar
- Google Cloud Well-Architected Framework skill for the Reliability pillar
- Google Cloud Well-Architected Framework skill for the Security pillar
- Google Cloud Well-Architected Framework skill for the Sustainability pillar
- Security and identity
- Web and app hosting
- Advertising
- AI Migration Agent Instructions for the Google Mobile Ads SDK
- Data Manager API Audience Ingestion
- Data Manager API Event Ingestion
- Data Manager API Setup
- Google Ads API Account Performance Diagnostics Skill
- Google Ads API MCP Server Installation
- Google Ads API Quickstart
- Google Mobile Ads SDK - Banner Ads
- Google Mobile Ads SDK - Install
- Google Mobile Ads SDK - Interstitial Ads
- Google Mobile Ads SDK - Rewarded Ads
- IMA DAI SDK
- IMA SDK client-side
- Others
Additional Google skills
- Advanced Google Cloud Storage Skills
- Agent Development Kit (ADK) Skills
- Android Skills
- Dart Skills
- Firestore Skills
- Flutter Skills
- Google Maps Platform Skills
Plugins
This repo also bundles Google product plugins (Skills + MCP servers) for agent harnesses.
| Agent harness | Install |
|---|---|
| Claude Code | claude plugin marketplace add google/skills, then claude plugin install <plugin>@google-plugins |
| Codex | codex plugin marketplace add google/skills, then install from the /plugins browser |
| Antigravity CLI | agy plugin install https://github.com/google/skills/<plugin-path> |
Support
If you need help or encounter issues with these skills, search for existing issues or open a new one in the GitHub Issue Tracker.
Contributing
We welcome contributions to improve our skills. You can help by:
- Reporting bugs or inaccuracies in the skill Markdown files.
- Suggesting new skills to add to this repository (for example, Google technologies or recipes) by filing a feature request.
License
You are free to copy, modify, and distribute these skills under the terms of the
Apache 2.0 license. See the LICENSE file for details.