Index of every page on this site: llms.txt
Avatar for Google

Google

Google ❤️ Open Source

200 skills10 repos 24k United States of America

google/skills

Agent Skills for Google products and technologies

110 skills 24k
npx skilld add google/skills --all
  • Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard infrastructure monitoring unrelated to AI agents, or when the agent is not instrumented with OpenTelemetry (for Reliability, Cost, Safety, Security alerts). NOTE: Reliability, Cost, Safety, and Security alerts use generic OTel metrics and work across runtimes (such as Cloud Run, Vertex AI). Quality alerts rely on Vertex AI Online Monitors and are strictly bound to Vertex AI deployments.

  • Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a specific model is deployable (`gcloud ai model-garden models list-deployment-config`), query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for pure listing/discovery questions of the form "is X deployed?", "list my endpoints", or "which regions have models running?" — for those use `agent-platform-endpoint-management`. Don't use for running model evaluations (use `agent-platform-eval-flywheel` skill).

  • Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations.

  • Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic user scenarios, evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy.

  • Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.

  • 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 moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry).

  • Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

  • Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.

  • Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google Workspace RAG, or other RAG products like gRAG.

  • Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.

  • Troubleshoots Google Cloud Gemini Enterprise Agent Platform issues across Agent Gateway, Agent Connectivity Templates (ACT), Agent Registry, Agent Identity, Identity-Aware Proxy (IAP), Unified Access Policies (UAP), Model Armor, Semantic Governance Policies (SGP), Cloud DNS peering, Private CA TrustConfig, Next-Hop Secure Web Proxy (SWP), Explicit HTTPS Proxy (L4 AuthzPolicy), and Cloud Trace. Use when agent requests fail with 401/403/404/498/500/503 or Code 13, Egress request is not authorized, HTTP CONNECT fails with 404, Agent Runtime crashes on startup, or gateway/ACT/IAP/Model Armor/SGP configs fail validation. Don't use for general Google Cloud Identity and Access Management (IAM) debugging or networking issues unrelated to the Agent Platform stack.

  • 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 outside Agent Platform, model deployment to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).

  • Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use `agent-platform-tuning`), deploying models to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).

  • Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.

  • Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment failures. Boundaries: - Only use for GCP-specific cloud infrastructure. - Only use for Terraform coding within the ADC context.

  • Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, generate descriptive statistics and table distribution profiles, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.

  • Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables, views), or perform basic data ingestion and analysis.

  • Generates Python code using BigQuery DataFrames (BigFrames). Use by default for any Python data task involving BigQuery, including data processing, analysis, and machine learning. Don't use for SQL-first workflows or the google-cloud-bigquery client library — use bigquery-basics.

  • Assists in provisioning instances/tables, designing performant schemas, and querying data in Bigtable. Use when designing Bigtable row keys, configuring column families, writing SQL queries or client library code (Java, Go, Python) for Bigtable, or diagnosing performance/hotspotting issues. Also use when provisioning Bigtable clusters using gcloud or cbt CLIs. Don't use for generic Cloud SQL administration.

  • Configure single-project Cloud Logging on Google Cloud: regional log buckets, log sinks, log views, restricting or hiding sensitive logs in the default view (_Default) filter, IAM permissions for views (Logs View Accessor, IAM conditions), logs-based metrics, log exclusions, and sampling. Don't use for cross-project logging or multi-project setups.

  • Configure and troubleshoot Google Cloud cross-project centralized logging and read-time aggregation. Use when: - Setting up log routing from multiple projects/folders/organizations to a central log bucket. - Creating cross-project log sinks and configuring central log buckets. - Troubleshooting cross-project routing. Don't use for single-project basic configurations.

  • Generates Logging Query Language (LQL) queries for Cloud Logging on Google Cloud from natural language. Use this skill when you need to query log data or when you are debugging issues. You can filter log data by Google Cloud service. Don't use this skill to query other databases, such as SQL or Cloud Spanner.

  • Generates Cloud Monitoring Server-Driven UI (SDUI) Widget and XyChart Protocol Buffer textprotos on Google Cloud from resolved PromQL or ListTimeSeries queries. Use when: - Generating valid google.monitoring.dashboard.v1.Widget textprotos, containing PrometheusQuery or TimeSeriesFilter datasets, for use with the Cloud Monitoring Dashboards API, gcloud CLI, or declarative dashboard definitions. - Synthesizing Server-Driven UI (SDUI) widget titles, axis labels, and plot types for Prometheus or ListTimeSeries queries. Don't use for: - Metric discovery or PromQL query generation. For those tasks, use the cloud-monitoring-metric-selection or cloud-monitoring-promql-query skills.

  • Generates valid Cloud Monitoring ListTimeSeries requests and aggregation specifications from metric descriptors and resource parameters. Use when asked to create, generate, format, or build ListTimeSeries requests, JSON payloads, filter expressions, or aligner/reducer aggregations for Cloud Monitoring metrics and charts. Don't use for metric discovery or metric selection.

  • Retrieve, query, and identify relevant Cloud Monitoring metric descriptors on Google Cloud for a service or resource (such as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub/Sub, Cloud Storage, etc.). Use when asked to find, list, search, or discover GCP metric types, names, kind/value schemas, or descriptors.

  • Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).

  • 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 Server. Cloud SQL manages third-party MySQL, PostgreSQL, and SQL Server instances as resources in Cloud SQL. For example, when Cloud SQL creates an open-source MySQL instance, the resulting resource is a Cloud SQL for MySQL instance that Google Cloud manages. Cloud SQL handles backups, high availability, and secure connectivity for relational database workloads.

  • Guides developers through managing (adding, removing, and clearing) audience members for Google products using the Data Manager API and its associated client libraries. Use this skill when the user wants to upload audience members, remove specific users, or clear/replace an entire audience for Customer Match, mobile device ID audiences, or any other audience use case supported by the Data Manager API. Don't use for uploading events or conversions (use the data-manager-api-event-ingestion skill), or for debugging errors, checking request status, or investigating low match rates (use the data-manager-api-troubleshooting skill).

  • Guides developers through implementing event and conversion ingestion to Google products using the Data Manager API /v1/events/ingest endpoint and its associated client libraries. Use this skill when the user wants to upload offline conversions, enhanced conversions for leads, click conversions, call conversions, Google Analytics web or app events, or any other event ingestion use case supported by the Data Manager API. Don't use for uploading audience members (use the data-manager-api-audience-ingestion skill), or for debugging errors, checking request status, or investigating missing conversions (use the data-manager-api-troubleshooting skill).

  • Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience or event ingestion logic (use the data-manager-api-audience-ingestion or data-manager-api-event-ingestion skills instead), or for debugging UNAUTHENTICATED, PERMISSION_DENIED, or other errors from requests after setup (use the data-manager-api-troubleshooting skill).

  • Analyzes the downstream impact (blast radius) using data lineage on Google Cloud when a BigQuery table or view is broken, stale, or modified. Identifies all downstream tables, dashboards, and processes that will be affected. Use when: - Performing a blast radius or impact analysis for a BigQuery table or view. - Assessing the consequences of modifying, deleting, or pausing updates to a BigQuery asset. - Identifying downstream dependencies (tables, dashboards, processes) of a BigQuery asset. Don't use for: - General BigQuery querying or data analysis (use BigQuery-related tools instead). - Non-BigQuery assets (e.g., Cloud Storage files) unless they are part of the BigQuery lineage. - Creating or modifying lineage links directly.

  • Summarizes data lineage graphs on Google Cloud to help users debug data quality issues and understand data provenance for BigQuery and Cloud Storage. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage relationships, or downstream deprecation. Don't use for downstream blast-radius impact analysis (use datalineage-bigquery-asset-impact-analysis skill instead).

  • Automates the end-to-end detection engineering workflow in Google SecOps using MCP tools. Use when fetching threat intelligence from blogs, generating Threat Detection Opportunities (TDOs), simulating attacker behavior with synthetic UDM events, evaluating rule coverage, and deploying gap-closing rules. Don't use for standalone YARA-L 2.0 rule authoring/tuning (use secops-detection-engineering), threat hunting, or SOC investigation.

  • Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.

  • Provides foundational Firebase CLI setup, CLI installation, version checks (`firebase-tools@latest --version`), CLI login (including --no-localhost), project creation, project selection (`firebase use`), and app config file downloads (`google-services.json`, `GoogleService-Info.plist`). Use ONLY for CLI login, project creation/switching, or downloading app config files. Don't use for Firebase Hosting deploy, Firestore, Auth, App Hosting, Data Connect, Crashlytics, or Remote Config.

  • Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructing, proposing, describing, or executing any gcloud CLI commands - including when answering questions about gcloud syntax, or formatting flags. Don't use when writing Google Cloud client library code or raw REST/gRPC API requests.

  • Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.

  • Integrates Gemini models on Gemini platform (formerly Gemini Enterprise Agent Platform and Vertex AI) using the unified Google Gen AI SDK across Python, TypeScript/JavaScript, Go, Java, and C#. Use for Google Cloud AI workloads: text/multimodal generation, structured JSON, function calling, Search grounding, code execution, URL context, Nano Banana images, Gemini Omni and Veo video, TTS, Lyria music, embeddings, caching, batch, thinking, safety, Live API, or model tuning. Don't use for server-managed stateful agent sessions (gemini-interactions-api), Managed Agent CRUD (gemini-agents-api), raw BidiGenerateContent WebSocket scaffolding/audio debugging (gemini-live-api), open-model SFT or tuning job management (agent-platform-tuning, agent-platform-tuning-management), or OpenMaaS, OpenAI SDK, numeric endpoints, and 429 DSQ debugging (agent-platform-inference).

  • Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.

  • Builds, integrates, and troubleshoots Gemini Enterprise Agent Platform Live API (BidiGenerateContent) WebSocket clients and sessions. Use when scaffolding a LiveAPI client or demo UI/backend (GA v1 WebSockets, isolated Python venv, ADC bearer token refresh, transparent session resumption, ClientMessage and ServerMessage JSON protos, tool responses, context_update, interrupt and transcription handling) or debugging Live API issues such as silent or empty turns, audio amplitude collapse, tonal humming, voice gender or accent drift, premature turn completion, barge-in failures, output_transcription leaks, malformed or looping tool calls, WebSocket 1008/1011/goAway drops, or latency spikes. Don't use for non-live, non-bidirectional Gemini API calls such as unary generateContent, embeddings, image/video generation, or fine-tuning — use the gemini-api skill for those.

  • Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing node taints, or configuring workload protection strategies (graceful termination, opportunistic maintenance, PodDisruptionBudgets). Don't use for general GKE cluster creation, network policy configuration, or non-disruption workload deployment.

  • Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or non-JobSet application issues.

  • Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbar_control_agent crashes, memory cgroup OOMs in serial console logs, tpu-device-plugin metrics checksum corruption errors, or custom TPU metrics collection conflicts on GKE TPU v6e nodes. Don't use for general non-TPU container OOM troubleshooting or standard GKE node lifecycle operations.

  • Manages GKE application onboarding, covering containerization, deployment manifests, and migration. Use when onboarding or deploying an application to GKE for the first time, or containerizing an app for GKE. Don't use for general GKE cluster administration or upgrades (use gke-basics or gke-upgrades instead).

  • Configures Backup for GKE: the BackupRestore cluster addon, BackupPlan and RestorePlan resources, restore workflows, and CMEK-encrypted backups. Use for backup policies, disaster recovery, or GKE cluster restores. Don't use for database backups.

  • Manages core GKE cluster provisioning, credentials, Autopilot vs Standard selection, and workload deployment. Use when creating GKE clusters, fetching kubectl credentials, or deciding between Autopilot and Standard modes. Don't use for Workload Identity (use gke-workload-identity), GKE networking (use gke-networking), security hardening (use gke-platform-security or gke-workload-security), or cluster upgrades (use gke-upgrades).

  • Runs batch and HPC workloads on GKE, utilizing job queues and parallel processing. Use when running GKE batch jobs, configuring GKE HPC, or setting up GKE job queues. Don't use for standard web application deployments (use gke-app-onboarding instead).

  • Trigger on mention of GKE cluster autoscaler, node autoscaling, node pool auto-creation / node auto-provisioning. Provides guidance on enabling and optimizing cluster autoscaler, best practices, and troubleshooting issues such as nodes not scaling up or down, zonal stockouts, or capacity buffers. Do not use for ComputeClass-specific YAML generation or priority configuration (defer to gke-compute-classes skill).

  • Plans and executes GKE cluster creation, provisioning, and production readiness audits using pre-defined templates (Autopilot, Standard Regional, GPU/AI Inference, AI Hypercompute). Use when creating GKE clusters, provisioning GKE environments, selecting cluster modes, or auditing GKE clusters. Don't use for application onboarding or deployment configuration (use gke-app-onboarding instead).

  • Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto Provisioning configuration or general GKE cluster creation.

  • Answer natural language questions and perform analysis on GKE cluster and workload costs using BigQuery billing exports, cost allocation data, and live cluster monitoring metrics. Use when querying GKE costs across projects, namespaces, or workloads, analyzing billing reports in BigQuery (`bq`), checking cluster cost budgets (`gcloud billing`), or diagnosing cost drivers like pod requests vs. actual utilization (`kubectl top`). Don't use for applying cost optimization changes, creating rightsizing manifests (VPA/MPA), or selecting ComputeClasses (use gke-cost-optimization instead).

  • Optimizes GKE costs, rightsizes workloads, and configures Spot VMs, CUDs, cost allocation, and resource quotas. Use when optimizing GKE cluster or workload costs, configuring GKE cost allocation or quotas, rightsizing CPU/memory requests, or selecting Spot VMs and machine types. Don't use for general compute class provisioning or GPU Selection (use gke-compute-classes instead).

  • Provides GKE golden path configuration defaults, production readiness checklists, and cluster default patterns. Use when designing GKE clusters, verifying GKE production readiness, or checking configurations against GKE defaults. Don't use for setting up workload autoscaling specifically (use gke-workload-scaling instead).

  • Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for migrating existing AI workloads to GKE (use google-cloud-solution-guided-gke-ai-migration), GKE RAG with Cloud SQL/AlloyDB (use google-cloud-solution-rag-enterprise-search-gke-sqldb), or batch/HPC (use gke-batch-hpc).

  • Generates and updates secure, production-ready Kubernetes YAML manifests optimized for GKE Autopilot and GKE Standard clusters. Use when creating or modifying GKE deployment manifests, configuring container security contexts, setting CPU/memory resource limits, defining readiness/liveness/startup probes, mounting secrets and volumes, configuring GKE Gateway API routes, targeting Spot VMs, or deploying AI model inference workloads (vLLM, TGI, Gemma). Don't use for live cluster operations, pod troubleshooting (use gke-workload-troubleshooting), or cluster infrastructure provisioning (use gke-cluster-creation).

  • Plans and configures multi-tenancy on GKE. Covers namespace isolation, RBAC planning for teams, resource quotas, LimitRanges, network isolation, and cost allocation. Use when designing GKE multi-tenancy, configuring GKE namespaces, setting up resource quotas, or isolating GKE teams. Don't use for single-tenant cluster configuration or general deployment instructions (use gke-basics or gke-app-onboarding instead).

  • Plans, configures, and manages core GKE cluster networking. Covers private clusters, VPC-native configurations, DNS, node egress, Dataplane V2, and IP planning. Use when designing GKE networking layouts, configuring private clusters, setting up Dataplane V2, planning GKE IP ranges, or managing VPC- native cluster modes. Don't use for application ingress, load balancing, or service networking (use gke-service-networking instead).

  • Configures GKE observability, including Cloud Logging, Cloud Monitoring, and managed Prometheus. Use when configuring GKE monitoring, setting up GKE logging, or configuring Prometheus metrics collection, to diagnose GKE control plane, API server, admission webhook, etcd storage, node registration or label, and pod eviction, preemption, or scheduling issues using GKE metrics, Kubernetes events, and Cloud Logging, and to troubleshoot Managed Service for Prometheus (GMP) issues such as missing metrics, unhealthy scrape targets, PodMonitoring misconfiguration, rule/alert evaluation failures, and monitoring permission errors. Don't use to configure local application logging frameworks or external APMs outside GKE.

  • Plans, configures, and hardens platform-level Google Kubernetes Engine (GKE) cluster security. Covers cluster add-ons (Secret Manager enablement), RBAC hardening (disabling insecure bindings, audit tools), Binary Authorization, Secrets Encryption (--database-encryption-key), Security Posture (--security-posture), enabling Shielded Nodes, GKE Sandbox cluster enablement, GKE IAM roles, and cross-service authentication IAM patterns. Use when securing cluster control planes, hardening GKE RBAC, enabling Shielded Nodes, enabling GKE Sandbox runtime, enabling cluster-wide security add-ons, or managing GKE IAM roles. Don't use for Workload Identity (use gke-workload-identity) or workload-level security (SecretProviderClass, PSS, NetPol, gVisor pod runtimeClassName; use gke-workload-security).

  • Orchestrates comprehensive production readiness reviews and assessments for GKE clusters and workloads across scalability, security, reliability, observability, backup/DR, and cost optimization. Use when asked to productionize, prepare, assess, audit, or review a GKE cluster or workload before going live to production. Don't use for deep-dive single-domain implementation (use specific domain skills like gke-workload-scaling, gke-platform-security, gke-workload-security, gke-service-networking, gke-reliability instead).

  • Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery and cluster backups (use gke-backup-dr).

  • Configures GKE edge networking, traffic routing, load balancing, and private service endpoints. Use when configuring Gateway API manifests, standard Ingress, Cloud Armor WAF security policies, Container-Native Load Balancing (NEGs), Private Service Connect (PSC), or Google-managed SSL certificates on GKE, and to troubleshoot Ingress and load-balancer 502/5xx errors, backend health-check failures, connection draining, and TLS/SSL policy enforcement. Don't use for core cluster IP planning, Dataplane V2 network policies, or node NAT egress (use gke-networking instead).

  • Manages GKE storage, including PVCs, PersistentVolumes, and Filestore. Use when configuring GKE storage or creating PVCs. For GCS FUSE mounts, use google-cloud-storage-fuse. For diagnosing storage failures (volume attach/mount errors, disk performance/node storage pressure, or Cloud Storage FUSE OOM), use gke-storage-troubleshooting. Don't use for database administration or replication strategies outside volume provisioning context.

  • Plans, executes, and validates Google Kubernetes Engine (GKE) cluster upgrades and maintenance operations for both Standard and Autopilot clusters. Produces upgrade plans, pre/post-upgrade checklists, maintenance runbooks with gcloud commands, release channel strategy, and troubleshooting guides. Handles node pool upgrade strategies (surge, blue-green), version compatibility, PDB management, and workload-specific concerns (stateful, GPU, operators). Use this skill whenever the user mentions GKE upgrades, Kubernetes version bumps, node pool maintenance, GKE patching, cluster version management, release channel selection, maintenance windows, surge upgrades, stuck upgrades, or any GKE lifecycle management task — even casual mentions like "we need to upgrade our clusters" or "plan our next GKE maintenance" or "our upgrade is stuck." Don't use for GKE cluster creation, application onboarding, general networking/routing setup, or security policy configurations (use gke-basics or relevant GKE skills instead).

  • Manages scaling for GKE workloads using HPA and VPA. Use when configuring Horizontal Pod Autoscaler (HPA), configuring Vertical Pod Autoscaler (VPA), or applying best practices for GKE workload autoscaling. Do not use for cluster-level autoscaling (Cluster Autoscaler), static cluster sizing, or configuring node-level machine styles directly.

  • Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (`audit_cluster.sh`), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (`gVisor`), enforcing Pod Security Standards (`restricted` labeling) and pod securityContext, and mounting Secret Manager secrets via CSI (`SecretProviderClass`). Use when auditing workload security posture, isolating namespaces, applying pod security standards, or configuring network policies and secret volume mounts. Don't use for Workload Identity (use gke-workload-identity), cluster-wide control plane security, RBAC hardening, Binary Authorization, Shielded Nodes, or enabling platform-level GKE add-ons (use gke-platform-security instead).

  • Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.

  • Diagnoses Google Ads account performance issues such as conversion loss (value or volume), low lead flow/volume, and lost impression share (opportunities) due to ad rank, bids, or budgets. Use when troubleshooting sudden performance drops, analyzing campaign impression share metrics, investigating low lead flow, or searching for bidding and budget constraints. Don't use for setting up new campaigns, uploading conversion events directly, or general Google Mobile Ads SDK integration issues (use gma-android-integrate instead).

  • Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server. Use this skill when a user wants to connect their AI assistant (such as Gemini, Claude Code, or Cursor) to their Google Ads account to query campaigns or retrieve reporting metrics using natural language.

  • Guides developers through Google Ads API quickstart: credential setup, choosing from 6 client libraries/REST, configuring environments, and running a "retrieve campaigns" script. Troubleshoots common setup errors: USER_PERMISSION_DENIED, login_customer_id issues, and CLOUD_PROJECT_NOT_APPROVED_FOR_PRODUCTION (a Google Cloud project with Test access calling a production account). Use this skill when: - The user asks how to get started with the Google Ads API. - The user needs to set up Google Ads API access in a Google Cloud project or OAuth credentials. - The user wants to write a quickstart/example script for Google Ads. - The user encounters errors like USER_PERMISSION_DENIED, CLOUD_PROJECT_NOT_APPROVED_FOR_PRODUCTION, or the legacy DEVELOPER_TOKEN_NOT_APPROVED.

  • Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle.

  • Manages Google Analytics account and property settings, enables the Analytics Admin API via the Cloud CLI, lists accounts and properties, and manages data streams, custom dimensions, conversion events, and integrations. Use when you need to programmatically configure Google Analytics accounts, provision properties, manage data retention, configure Measurement Protocol secrets, or manage Firebase and Google Ads links.

  • Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers, screenPageViews) and dimensions (like city, date), check metrics and dimensions compatibility, or verify API enablement. Don't use for Google Analytics Admin API operations (e.g., creating properties, managing users) or for front-end tracking installation.

  • Inspects Filestore capacity and utilization on Google Cloud, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds (custom thresholds apply globally across projects in session memory), or preventing out-of-space outages. Don't use for Cloud Storage (GCS) buckets, Persistent Disk block storage, or NetApp Volumes.

  • Guides agents through a 6-step discovery process to design and deploy Google Cloud global external Application Load Balancers with Cloud CDN, Cloud Armor, and Service Extensions, mapping workload requirements to best-practice configurations. Use when: - Designing, configuring, or deploying a Google Cloud global external Application Load Balancer, Cloud CDN, Cloud Armor WAF, or Service Extensions. - Discovering existing Google Cloud resources (Cloud Storage, MIGs, GKE, Cloud Run) to use as backends. - Generating production-grade Terraform HCL or gcloud CLI scripts for global external Application Load Balancers. - Actuating deployments via Infrastructure Manager or bash scripts, including IAM pre-checks. - Detecting, analyzing, or reconciling configuration drift on deployed global external Application Load Balancers. Don't use for: - Non-Google Cloud load balancing or security configurations. - Purely regional or internal load balancing setups (unless part of a hybrid/failover global design).

  • Investigates Google Cloud networking issues by analyzing GCP logs, metrics, and diagnostics. Use when investigating dropped network traffic, packet drops, drop reasons, VPC Flow Logs (including Private Service Connect / PSC, serverless / App Engine Direct VPC, and cost estimation), Cloud NAT, firewall or threat logs, VPN metrics/tunnels, or Connectivity Tests for path diagnostics. Don't use for generic VM management or non-observability tasks.

  • Provides expert guidance on Identity and Access Management (IAM) and authenticating and authorizing to Google Cloud services and APIs, covering human users, service identities, Application Default Credentials (ADC), and best practices for secure access.

  • Deploys a baseline landing zone foundation for a Google Cloud Organization, establishing security guardrails using Organization Policies, resource hierarchy folders and projects, billing association, and centralized logging and monitoring. Deploys Google Cloud's recommended security controls and architecture. Use when setting up a new Google Cloud Organization or establishing a secure, enterprise-grade landing zone foundation. Don't use for individual project onboarding (use google-cloud-recipe-onboarding or product-specific skills instead).

  • Guides a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resource. Use when a new developer wants to initialize their first Google Cloud project, configure billing, and verify deployment. Don't use for enterprise organization setup (use Google Cloud Setup guided flow for that instead). Don't use for complex multi-project architectures.

  • Configures Cloud Monitoring PromQL-based Service Level Objective (SLO) alerting policies on Google Cloud for resources registered in App Hub or individually specified. Generates Terraform output. Use when the user asks to configure an SLO or Service Level Objective. Don't use for standard alerting policies.

  • Guides agents to interactively discover customer requirements for live, bidirectional multi-agent AI systems that process continuous streams of multimodal data for real-time technical guidance and safety monitoring. Generates a custom Google Cloud solution that uses opinionated best practices and architecture guidance. Use when users need agentic assistance to design and create a multi-product solution in the cloud for live bidirectional multimodal streaming workloads. Don't use for simple text-based chat applications or workloads without real-time streaming requirements.

  • Discovers requirements and designs a borderless open data lakehouse using Lakehouse for Apache Iceberg and BigQuery data agents. Use when architecting multi-cloud storage infrastructure (Cloud Storage, AWS S3, Azure Blob), establishing ingestion and AI serving subsystems, configuring Cross-Cloud Interconnect, or deploying Gemini Enterprise Agent Platform and BigQuery data agents. Don't use for single-cloud data warehouses, or when the focus is on Knowledge Catalog metadata governance and Spark-driven IDE analytics workflows (use google-cloud-solution-agentic-analytics-spark-knowledge-catalog instead).

  • Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices. Use when architecting multi-product solutions for agent-based data analytics or ML workloads. Don't use for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.

  • Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and Iceberg), establishing metadata governance with Knowledge Catalog aspect types, or grounding agentic IDEs (VS Code, Antigravity) by using the Google Cloud Data Agent Kit. Don't use for provisioning borderless data lakehouse infrastructure (use google-cloud-solution-agentic-ai-borderless-data-lakehouse instead).

  • Interactively discovers requirements and designs holistic, multi-product system architectures, solution blueprints, and deployment recommendations for complex workloads on Google Cloud. Use when designing end-to-end cloud solutions, selecting and integrating Google Cloud services, generating architecture diagrams, or conducting requirements discovery for new cloud workloads or migrations. Don't use for single-product tasks (use product-specific skills), initial onboarding or authentication (use google-cloud-recipe-*), Well-Architected Framework reviews or audits (use google-cloud-waf-*), or workloads covered by specialized solution skills.

  • Designs, builds, and deploys AI agents or multi-agent systems on Google Cloud. Provides an interactive workflow to gather requirements, recommend a tailored architecture, and generate deployment instructions. Use when designing or implementing agentic systems on Google Cloud. Don't use for general Google Cloud solution architecture (use google-cloud-solution-architecture instead) or for narrow tasks targeting a single product without agent context.

  • Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to self-hosted inference on GKE, or asks follow-up questions during such a migration (hardware sizing, model staging, manifest generation, validation, traffic cutover). DO NOT use for brand new GKE inference deployments with no existing workload to migrate (use gke-inference instead). DO NOT use if the user intends to automate the migration via the Gemini Cloud Assist MCP server.

  • Assists in designing and implementing secure n-tier serverless web applications and microservices on Google Cloud. Use when users need architecture designs, security checklists, Terraform code, or deployment guidance for multi-tier serverless apps, regional data residency / European sovereignty compliance, zero-trust private VPC networking, or Private Service Connect. Don't use for VM, GKE, or non-Google Cloud architectures.

  • Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. Use when users need a vector-enabled SQL database as the store and index for the embedding vectors, an open model and open-source inferencing framework, and Kubernetes containers to host all the application components. DON'T use this skill for fully-managed RAG, or SaaS search services, or when a non-SQL vector database is required.

  • Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets. Use when you need to interact with Cloud Storage — set up a Storage MCP server (remote or local Toolbox), create or configure buckets, upload, download, stream, or transfer data, organize objects with folders, generate signed URLs, control access (IAM, ACLs, public access prevention), set storage classes (Standard, Nearline, Coldline, Archive), manage lifecycle and cost, protect data (versioning, CMEK, retention, Bucket Lock, holds, soft delete), host static websites, trigger Pub/Sub notifications, mount buckets (gcsfuse), or optimize performance. Covers gcloud storage / gsutil, JSON/XML APIs, client libraries, Terraform, and Cloud Storage MCP servers. Don't use for generic MCP setup that doesn't mention Cloud Storage, other MCP servers, block storage (Persistent Disk), BigQuery, or databases (Cloud SQL, Spanner, Bigtable, Firestore).

  • Mounts Cloud Storage buckets on Google Cloud as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when interacting with gcsfuse or Cloud Storage FUSE mounts: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune mount flags (--implicit-dirs) or config files, apply workload profiles, keep ML checkpointing safe (rename atomicity, hierarchical namespace/HNS, close-time finalization, concurrent writers), or diagnose slow training, low throughput, or bill spikes with gcsfuse metrics. Covers mount semantics, gcsfuse CLI and configs, GKE gcsfuse CSI driver (Workload Identity principal:// bindings, profile StorageClasses, sidecar sizing), and Cloud Run volume mounts. Don't use for bucket administration without a mount (google-cloud-storage-basics) or POSIX shared file systems (Filestore, Managed Lustre; use gke-storage).

  • Evaluates Google Cloud workloads for cost efficiency and FinOps alignment using the Google Cloud Well-Architected Framework Cost Optimization pillar. Use when the user asks to analyze Google Cloud spend, reduce cloud bills, rightsize resources (for example, Compute, GKE, Storage, Databases), evaluate discount options (for example, CUDs, SUDs, Spot VMs), or eliminate idle capacity. Do not use for standalone product pricing lookups or non-cost architecture design.

  • Generates operational guidance for CI/CD deployment pipelines, observability, monitoring, logging, and incident management on Google Cloud based on the design principles and recommendations in the Operational Excellence pillar of the Google Cloud Well-Architected Framework (WAF). Use when the user asks about operations-related topics like capacity management, change management, incident and problem management, configuration management, deployment automation using infrastructure as code (IaC), or operational health checks for Google Cloud workloads.

  • Generates performance-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Performance Optimization pillar of the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate a workload, identify performance requirements, and provide actionable recommendations for resource allocation, modular design, and elasticity.

  • Evaluates, designs, and improves the reliability, resilience, availability, fault tolerance, and disaster recovery (DR) of Google Cloud workloads based on the design principles and recommendations in the Reliability pillar of the Google Cloud Well-Architected Framework. Use when the user asks about reliability-related topics like workload uptime, designing for high availability (HA) or DR, setting and meeting RTO/RPO targets, SRE best practices, backup strategies, multi-region failover, or fault-tolerant architecture on Google Cloud. Don't use for other Well-Architected Framework pillars such as Cost Optimization, Operational Excellence, or Security, or for hands-on resource deployment and live incident troubleshooting.

  • Evaluates Google Cloud workloads and provides actionable recommendations for identity management, access control, permissions and roles, network and perimeter security, data security and encryption, security logging and threat detection, software supply chain hardening, AI security, data privacy, regulatory compliance, and cloud sovereignty. The recommendations are aligned with the Security, Privacy, and Compliance pillar of the Google Cloud Well-Architected Framework (WAF). Use when the user asks about firewall rules, zero trust, shared responsibility and shared fate, audit logging, security monitoring, threat mitigation, shift-left CI/CD security, Secure AI Framework (SAIF), data residency, or hardening Google Cloud resources. Don't use for other Well-Architected Framework pillars (Cost Optimization, Operational Excellence, Reliability, Performance Optimization, or Sustainability).

  • Provides recommendations for environmental sustainability, carbon footprint reduction, and energy efficiency based on the Sustainability pillar of the Google Cloud Well-Architected Framework (WAF). Use when the user asks to assess, design, or optimize Google Cloud workloads for sustainability—including the shared responsibility model, selecting low-carbon regions (CFE%), reducing resource and AI/ML energy waste, designing efficient software and storage lifecycles, or measuring and tracking emissions using Google Cloud Carbon Footprint. Don't use for financial cost reduction (use google-cloud-waf-cost-optimization), latency and throughput tuning (use google-cloud-waf-performance-optimization), or high availability and disaster recovery (use google-cloud-waf-reliability).

  • Migrates Android applications from the old, legacy Google Mobile Ads (GMA) SDK (com.google.android.gms:play-services-ads) to the new GMA Next-Gen SDK (com.google.android.libraries.ads.mobile.sdk:ads-mobile-sdk). Provides comprehensive mapping tables for imports, classes, and method signatures to help determine migration steps. Use when migrating an existing Android codebase from the old, legacy GMA SDK to GMA Next-Gen SDK.

  • Provides instructions to implement, integrate, or configure Google Mobile Ads (GMA) banner ads in Android, iOS, or Unity mobile applications. Use when the task involves setting up banner ads in a mobile application. Don't use for other ad formats like interstitial or rewarded ads.

  • Provides instructions for integrating the Google Mobile Ads (GMA) SDK. Use this skill when the user wants to get started with, install, integrate, set up, or configure the SDK for AdMob or Ad Manager, GMA Next-Gen SDK or mobile ads framework in an Android, iOS, or Unity application.

  • Provides instructions for implementing, integrating, or configuring Google Mobile Ads (GMA) SDK interstitial ads in Android, iOS, or Unity mobile applications. Use when the task involves setting up interstitial ads. Don't use for "rewarded interstitial" ads.

  • Provides instructions for implementing, integrating, or configuring Google Mobile Ads (GMA) SDK rewarded ads in Android, iOS, or Unity mobile applications. Use when the task involves setting up rewarded ads. Don't use for "rewarded interstitial" ads.

  • Safely simulates and applies Identity and Access Management (IAM) v1 (Allow) policy changes on Google Cloud. Uses the Policy Simulator to replay historical access logs against proposed policies to prevent breaking active workloads before applying the changes. Use when simulating or applying IAM v1 allow policies across Projects, Folders, or Organizations. Don't use for analyzing IAM v2 deny policies, VPC Service Controls, or performing general policy troubleshooting.

  • Manages the end-to-end lifecycle of on-demand, temporary access using Privileged Access Manager (PAM). Use when a user asks to create, read, update, or delete PAM entitlements, request temporary access, or approve/deny pending PAM grants. Do NOT use for permanent IAM policy bindings, troubleshooting IAM permission errors, or general Google Cloud resource provisioning.

  • Integrates the Google Interactive Media Ads (IMA) Dynamic Ad Insertion (DAI) SDK into websites, web apps, mobile apps, or TV apps. Use when: - A video player needs to load and play HLS or DASH streams in web apps, Android apps, iOS apps, tvOS apps, Cast (CAF) receivers, or Roku channels. - The app needs to make use of a Google DAI livestream event asset key, or content source CMS ID, video ID for video on demand. Don't use this skill to load and play a VAST or VMAP URL.

  • Supports Interactive Media Ads (IMA) SDK. Use this skill for client-side ad insertion when you are requesting video ads for websites, apps, TVs or other platforms using VAST or VMAP. Do not use for Dynamic Ad Insertion (DAI), SSAI, or SGAI.

  • Provides guidance for authoring Apache Airflow DAGs in Managed Service for Apache Airflow (MSAA; formerly Cloud Composer). Covers environment context discovery, Airflow 2 vs 3 compatibility, authoring best practices, and local/remote validation processes. Use when creating or extending an Airflow DAG. Don't use when authoring Python code unrelated to Airflow DAGs.

  • Provides guidance for migrating Apache Airflow DAGs in Managed Service for Apache Airflow (MSAA; formerly Cloud Composer). Covers migration to Airflow 2.11.1 (MSAA Gen 2 and 3) and Airflow 3 (MSAA Gen 3), including environment inspection, GCS download/upload and scanning patterns for breaking changes. Use when migrating the DAG code to newer Airflow version. Don't use when checking DAG run failures unrelated to code migration.

  • Assists in provisioning instances and databases, designing performant schemas, and querying data in Cloud Spanner on Google Cloud. Use when designing primary keys, writing SQL queries or client library code, or diagnosing performance issues.

  • Use this skill to manage Google Cloud Workload Manager evaluations, rules, scanned resources, and validation results by using public client libraries and the REST API. Use when you need to inspect workload best-practice rules, create and run evaluations for Google Cloud general best practices, SAP, SQL Server, or custom organizational rules, review violations, export results to BigQuery, or automate Workload Manager through client libraries because no service-specific public CLI or MCP server is available. Don't use for general Google Compute Engine instance management, VPC configuration, or standard IAM auditing.

google/adk-recipes

A collection of agent recipes, reference patterns, and vertical plugins built with Agent Development Kit (ADK)

21 skills 11k
npx skilld add google/adk-recipes --all
  • Work with the Ambient Quality Agent (AQuA) added to this agents-cli project: augment the agents-cli agent with AQuA or attach the agent to an AQuA deployed elsewhere, read the quality insights it finds in production conversations, get AQuA's root-cause diagnosis, read what the developer asked it to remember, and fix the defects in the agent's code. Propose proactively when the user mentions AQuA or AQA, wants to monitor the quality of a deployed agent, mentions traces or observability, asks what is going wrong with their agent in production, wants to fix AQuA insights, or wants to publish code metrics to AQuA. Also propose it when traces from an evaluation run are in the telemetry table AQuA reads. Don't use it for scoring a local agent against a golden dataset (use google-agents-cli-eval) or for deploys without AQuA (google-agents-cli-deploy).

  • Aligns a Python recipe's pyproject.toml with the repo's standards enforced by .github/workflows/python-validate-recipe.yml, plus one critical [build-system] presence check. Scope is pyproject.toml only — standalone ruff.toml / .ruff.toml files (also forbidden in recipes) are caught by the CI workflow instead, not by this skill. Runs in two modes: a read-only --dry-run that reports what needs alignment, and an apply mode that rewrites pyproject.toml (and optionally manifest.yaml) using comment-preserving TOML/YAML editors. Use when the user wants to "align the recipe's pyproject.toml", "fix pyproject to match the repo standard", "check what needs changing in a recipe's pyproject", or clean up a recipe before submitting a PR.

  • Blog post writing skill with structure templates and style guidelines. Guides the agent through writing well-structured, engaging technical blog posts with proper formatting, section flow, and reader engagement techniques.

  • Install/auth CLIs the sandbox lacks - `gws` (Drive, Gmail, Sheets, Calendar), `gcloud`, `agents-cli`, `mcp-cli` (MCP servers). Use on "command not found" or before GCP/Workspace/MCP work.

  • Content research and SEO writing methodology. Guides the agent through topic research, keyword identification, competitive analysis, and writing SEO-optimized content that ranks well and provides genuine value to readers.

  • Run a custom investigation: review a chosen slice of conversations instead of a random sample, by writing a SQL selector over the observed agent's telemetry, and optionally narrow what the reviewer reports. Use when a message asks to investigate only certain conversations -- ones that hit an error, used a particular tool, ran slowly, mention a topic, looped, or were abandoned -- or asks to re-review conversations already seen with a different focus. Covers the telemetry table a selector reads, writing the selector, previewing what it matched, and starting the run.

  • Scans a Python recipe to find every place an environment variable is accessed — including `os.environ.setdefault("V", "d")`, whose "d" would otherwise be a hidden default a user editing .env.example has no way to discover — then ensures all variables are declared in `.env.example`, that `load_dotenv()` is bootstrapped in the package `__init__.py`, and that `python-dotenv>=1.0.0` is listed in `pyproject.toml`. When a new entry is added to `.env.example`, the extracted default from source is written as the value (with a `# extracted-by:extract-env-vars` marker and provenance comment); values that look like stubs (`"my-project-id"`, `"changeme"`, `"<...>"`) are downgraded to the TODO placeholder but the source string is preserved in the marker comment. Also detects hardcoded model-name string literals (e.g. `"gemini-3.5-flash"` in `agent.py`) and rewrites them to an `os.getenv(...)` call. The variable name is derived from the assignment target when it names a model (`DEFAULT_EMBEDDING_MODEL` → `EMBEDDING_MODEL`), else `MODEL_NAME` (single model) or `MODEL_NAME_GENERATED_1` / `MODEL_NAME_GENERATED_2`, … (multiple models). Normally no fallback default is written into the Python source; the one exception is when no `load_dotenv()` bootstrap could be installed (no package `__init__.py`), where the original literal is kept as the fallback so the lookup cannot evaluate to `None` at runtime. The model string is written as the value in `.env.example` with a comment prompting a rename. When re-run against a recipe whose `.env.example` already has entries, the writer classifies each entry (skill-authored vs. user-authored, TODO vs. real value) and only rewrites lines it can prove it authored; user-authored lines are always preserved. A stale TODO (either skill-authored or a bare v1-era `<TODO: update-this-value>` with no inline comment) is upgraded in place when source can supply a real default. IMPORTANT — two hard rules the skill NEVER breaks: (1) USER-EDIT SAFETY. Any `.env.example` line the skill cannot prove it authored is USER_OWNED and is never modified. The rewriter fails closed on any structural ambiguity (quoted values, backslash continuation, duplicate declarations) — a stale TODO left in place is cheap; a clobbered user edit is not. (2) ADDITIVE-ONLY FOR PYTHON FILES. The skill never writes new `os.environ.setdefault(...)` bootstrap lines into any Python file. Pre-existing `os.environ.setdefault(...)` or `os.getenv("VAR", "default")` calls that the recipe author wrote by hand are LEFT UNTOUCHED — the skill's only writes to Python files are (a) the `load_dotenv()` bootstrap; (b) `# noqa: E402` on trailing relative imports that would otherwise trip Ruff; (c) hardcoded model-literal replacement. Use when the user wants to "extract env vars", "update .env.example", "add load_dotenv", "surface setdefault defaults", "upgrade stale TODOs in .env.example", "replace hardcoded model names", or "fix environment variables" in a Python recipe.

  • Discover/install NEW agent skills from external sources (skills.sh). Use for capabilities you lack, e.g. "find a skill for X". Do NOT use to list skills you already have; see `<available_skills>`.

  • Scan an ADK recipe directory and generate a manifest.yaml for it based on the schema at .github/schemas/manifest-schema.json. Use when the user wants to create or generate a manifest.yaml for a recipe under core/, contrib/, or plugins/.

  • Generates a lightweight `tests/test_runnability.py` for a Python recipe. The test just imports the recipe's agent module and asserts that `root_agent is not None` (and `app is not None` if the module defines one). The skill parses agent.py with `ast` to figure out which import-time side effects need mocking (`vertexai.init`, `google.auth.default`) and which env vars need setting (`GOOGLE_CLOUD_PROJECT`, `INTEGRATION_TEST`), and only emits the boilerplate the recipe actually needs. Runs in dry-run (report + preview) and apply (write to disk) modes. Use when the user wants to "add a runnability test", "generate test_runnability.py", "create a smoke test for the recipe", or fix the missing-required-file failure from `python-validate-recipe.yml`.

  • Review a GitHub pull request and leave inline comments in a natural human reviewing voice, indistinguishable from comments typed by hand on the GitHub web UI. Deliberately bounded to defects a reader can settle by looking at the anchored line, rather than a deep audit, so every comment is cheap for the author to check. Scales to 2-20 comments by PR size, parallelises analysis across sub-agents, drafts for approval, then posts individually with human pacing. Use when the user says "review this PR", "review PR 123", pastes a github.com/.../pull/N link, or asks for comments on a pull request. Don't use for reviewing local uncommitted changes or a diff against a branch (use the `review` skill for that).

  • Read/write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the `gws` CLI. Needs an OAuth client or service account configured first. Use for any Google Workspace task.

  • Makes an existing Python recipe deployable: generates the serving files a container needs (Dockerfile, .dockerignore, fast_api_app.py, app_utils/a2a.py, app_utils/services.py, app_utils/reasoning_engine_adapter.py) and configures the recipe to match (required serving dependencies, the App object in agent.py, the hatch wheel package, manifest.deployable). Interactive by design — it asks the recipe owner about runtime data directories and stops for a human decision when a recipe needs an ADK migration or carries a legacy app_utils generation. When docker is available it offers to PROVE the claim: it builds the generated Dockerfile, runs it, probes it, and refuses to flag a recipe deployable if the container does not come up. Does NOT deploy or write terraform. Use when the user wants to "make this recipe deployable", "add a Dockerfile to a recipe", "add the serving files", "containerize a recipe", "verify the container builds", or prepare a recipe for Cloud Build / Artifact Registry.

  • Inspect the per-workspace tool-policy overlay (.lha/policies.jsonl) that gates destructive or sensitive tool calls, and tell the user what to change if they want a rule added or removed.

  • End-to-end orchestration to prepare or update a Python recipe under core/python/, contrib/python/, or plugins/<vertical>/<solution>/ so it passes every check in .github/workflows/python-validate-recipe.yml. Runs eight phases in order on an already-in-place recipe: manifest.yaml generation, environment-variable extraction, pyproject.toml alignment, ruff format+check, per-recipe `uv lock`, runnability-test generation, compile-and-run verification of the generated test file, and a final pass through the repo's own `validate manifest` / `validate structure` validators. Assumes the user has already done the manual prep (deactivated any venv, `git pull` and `uv sync` from the repo root, placed the recipe at its target path, renamed if needed). Delegates to the existing sub-skills (generate-manifest, extract-python-environment-variables, align-recipe-pyproject, generate-python-runnability-test) so the master never duplicates their logic. Pauses at fixed decision points (description mismatch, existing test regeneration) AND is free to interrupt for clarification any time a phase's output looks ambiguous, unexpected, or would benefit from a human judgment call — this is an interactive skill by design. Use when the user wants to "prepare a recipe", "update a recipe end to end", "run all the checks and fixes", "make this recipe PR-ready", or invokes it by name.

  • Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to "build a product search agent", "create an e-commerce search", "make a shopping assistant", "set up semantic catalog discovery", "ingest products into Vector Search", or "deploy a retail RAG agent". Handles the full pipeline: catalog data ingestion to BigQuery, Gemini Enterprise Agent Platform Vector Search collection setup, ADK agent scaffolding, evaluation, and Cloud Run deployment.

  • Root-cause analysis of one AQuA insight against the observed agent's own source code. Use when a message names an insight and asks what the root cause is, how to fix it, why the agent behaved that way, or to diagnose a failure -- for example `Diagnose insight <id> ("<label>") — what is the root cause, and how would you fix it?`. Reads the source snapshot at the revision the failure ran on, plus the complete conversations behind the insight, and answers with `<path>:<start>-<end>` citations, and records the proposed fix against the insight.

  • Answer questions about how the adk-recipes repo itself is governed — CI and workflow behavior, the limits and thresholds in .github/policy.yml and the reasoning behind them, CODEOWNERS routing, what the bots (stale sweep, Dependabot, recipe canary, AI review) do, how the repo is organised (core vs contrib vs skills verticals), what the repo skills and validators cover, when a rule last changed and which PR changed it, what a label means, and the admin runbooks for changing any of it. Also answers generic contribution-process questions from docs/ — how a recipe is prepared and validated, what a field in manifest.yaml means, what a runnability test is, what a README must contain, what a named CI error means. On explicit request it also traces which files consume a config key, and audits whether the repo still obeys its own policy. STRICTLY READ-ONLY — it never edits, commits, comments, labels, or performs a task on the caller's behalf, even when asked directly; it cites the source file and describes the change for a human to make. A request to do the work is answered rather than obeyed — it says it is read-only, names the skill that does the work, and gives the guidance. Use when someone says "oracle", or asks how/why/who about this repo's own configuration, CI, governance, or layout. Don't use for writing or preparing a recipe (use prepare-python-recipe, generate-manifest, align-recipe-pyproject and friends), for ADK API questions (use the google-agents-cli-* skills), or for anything needing the caller's screen — a failing check on their PR, their working tree, their branch.

  • Use for a recurring unattended task (cron; pull data, open a PR, post a digest), or to test/dry-run a routine first. Explains authoring and testing via the routine tool.

  • This skill should be used when the user wants to "create a new Python ADK recipe", "scaffold a new Python recipe", "generate a new Python recipe in contrib", "add a new Python recipe to the adk-recipes repository", or "create a Python adk recipe". It utilizes an automated script to copy template files and resolve basic placeholders.

  • Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation.

google/mantis

A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

21 skills 2.8k
npx skilld add google/mantis --all
  • Proactive security advisor and architectural remediation assistant for secure code development. Use to query threat models, historical vulnerability lineages, verified patch patterns, triaged false positives, and learned trajectory invariants before code edits or to generate architectural remediation plans for confirmed findings. Don't use for automated multi-pass red-team exploitation or fuzzing.

  • Synthesizes raw learnings and codebase analysis into an interlinked Markdown Knowledge Base (KB). Use at the beginning of a loop to build or update architecture.md, entities, and vulnerabilities. Don't use for generating threat models or formulating execution plans.

  • Calculates the final risk score based on empirical evidence and architectural impact. Use when findings have been fully processed by previous stages and you need to append final risk scores to the finding files. Don't use for discovering new vulnerabilities or writing patches.

  • Analyzes individual security findings to identify and construct complex exploit chains. Use after validation stages to see if multiple low-severity bugs can be combined into a higher impact vulnerability. Don't use for initial codebase auditing or writing patch code.

  • Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests. Don't use for scanning source code or running attack campaigns.

  • Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.

  • Consolidates raw security findings to eliminate redundant reports. Use when raw findings have been generated by the researcher and need consolidation before review. Don't use for initial code auditing or patch generation.

  • Analyzes the repository's version control system (VCS) history to extract past vulnerabilities, security fixes, and vulnerability patterns. Use as an initial pre-processing step to build a historical vulnerabilities database (workspace/historical_learnings.jsonl) that informs subsequent stages about past issues and fixes. Don't use for code reviews, writing test scripts, or patching code.

  • Launches automated vulnerability review campaigns on target files or repositories. Use to initiate Mantis vulnerability review pipelines with automated preflight checks, environment auto-configuration, and runtime overrides (sandboxes, models, endpoints). Don't use for configuring settings without scanning or for manual single-stage reviews.

  • Acts as the persistent supervisor, launching and monitoring the automated review campaign. Use when running a long-running, continuous security review campaign that needs autonomous coordination. Don't use for executing individual review stages directly.

  • Generates minimal security fixes using transactional isolation (shadow directories or file backups), applies patches, and verifies them. Use when security findings are successfully reproduced and need patches applied and verified. Don't use for initial vulnerability research or reproduction payload generation.

  • Interactively guides the design and implementation of custom deterministic orchestrator harnesses. Use when a user wants to build their own pipeline to wrap and run Mantis skills reliably. Don't use for executing the default pipeline directly.

  • Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for executing code reviews, writing test scripts, or patching code.

  • Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to workspace/learnings.jsonl. Don't use for analyzing source code or writing patches.

  • Generates a human-readable security review packet compiled from confirmed findings and exploit chains. Use at the end of a review cycle to produce stakeholder-facing documentation. Don't use for auditing code or verifying patches directly.

  • Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to write and execute a script or payload to verify the crash. Don't use for code auditing or patching.

  • Audits production source code files based on the strategy in workspace/plan.json. Use when a review plan exists and you need to perform static analysis and deep-dive reviews of targeted files. Don't use for planning, deduplicating, or writing patches.

  • Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.

  • Builds a content-addressed semantic-unit index from source code for structural context. Use when a pinned or live codebase is available and structural cross-reference data would improve research quality. Don't use for findings analysis, patching, or reporting.

  • Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching code.

  • Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.

google/adk-python

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

16 skills 22k
npx skilld add google/adk-python --all
  • Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a tool to one, branch or loop between nodes, run steps in parallel, pause for user approval, or test an agent. Don't use for explaining how ADK works internally or designing its core components (use `adk-architecture`), for an agent that already runs but misbehaves (use `adk-debug`), for authoring a sample under `contributing/` (use `adk-sample-creator`), or for naming, typing, and formatting conventions (use `adk-style`).

  • Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering "how does X work" about ADK internals, tracing where an event or a piece of state comes from, deciding where a new capability belongs, reviewing a change to BaseNode, Workflow, Runner, Agent, Event or Context, working out why a node re-ran or stayed waiting after a resume, or judging whether a change breaks the public API. Don't use for assembling an agent from existing pieces (use adk-agent-builder), diagnosing one failing run or test (use adk-debug), or formatting and naming conventions (use adk-style).

  • Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the `adk run` CLI and the `adk web` dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs, loops, emits raw JSON instead of calling tools, is not discovered by `adk web`, when a sub-agent cannot see the parent conversation, or when you need the LLM request/response, token counts, or logs for a run. Don't use for how ADK is designed internally (use `adk-architecture`), for building a new agent or workflow (use `adk-agent-builder`), for environment or dependency setup failures (use `adk-setup`), or for lint and style nits (use `adk-style`).

  • Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and testing-plan sections the PR template requires. Use when writing or rewording a commit message, squashing commits before a pull request, drafting a PR description, or checking that a change is shaped to land. Don't use for generic git mechanics such as rebasing, resolving conflicts, cherry-picking, or branch surgery; those need no skill. Don't use to judge the content of a change (use adk-review) or for code style and naming (use adk-style).

  • Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local changes, wants a self-review before opening a pull request, asks whether a change breaks the public API or needs tests, samples or docs, or asks what is wrong with the current diff. Required for changes to public APIs, core architecture (Runner, Workflow, BaseNode), new features and major refactors. Don't use for a single style nit (use adk-style), for diagnosing a failing test or a misbehaving agent at runtime (use adk-debug), or for wording a commit message or PR description (use adk-git).

  • Creates a new sample agent in the ADK Python repository — the sample directory, its `agent.py`, and its `README.md` — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out/fan-in, a standalone tool-using agent), asks where a new sample belongs under `contributing/samples/`, or wants an existing sample's README brought up to the standard structure. Don't use for building a real working agent for the user's own project (use `adk-agent-builder`), or for checking whether the Python blocks in a Markdown file run (use `adk-verify-snippets`).

  • Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development checkout, install project dependencies, fix a missing or broken .venv, or prepare a machine for contributing a pull request. Don't use for debugging a running agent (use adk-debug), for commit and pull-request mechanics (use adk-git), or for re-running formatters on a checkout that is already set up (pre-commit run --all-files).

  • Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or symbol should be public or private, naming or placing a test file, fixing a formatter, linter, or type-check failure (pyink, isort, ruff, mypy, addlicense, compliance-checks), or asking whether code matches house style. Don't use for reviewing a whole changeset (use adk-review), writing a developer guide or design doc for a code unit (use adk-unit-guide or adk-unit-design), building or configuring agents (use adk-agent-builder), or installing the toolchain (use adk-setup).

  • Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to `docs/design/{topic}/{unit}/index.md`. It describes the code as implemented, not a proposed design, and its reader is a developer about to change or extend that unit. Use when asked to "write a design doc for {file}", "document the architecture of {class}", "document the extension points of {unit}", or after adding a core class, node type, or plugin base. Don't use for documentation aimed at developers who only call the unit from their own application — that is a usage guide with runnable examples under `docs/guides/` (use `adk-unit-guide`). Don't use to answer a framework-wide architecture question (use `adk-architecture`).

  • Writes a hands-on developer guide for one ADK code unit — a minimal runnable example, how it works, a configuration-option table, advanced uses, limitations, and links to related samples — to `docs/guides/{topic}/{unit}/index.md`, then lists it in the index at `docs/guides/README.md`. Its reader is a developer calling the unit from their own application, at more depth than the published adk.dev documentation carries. Use when asked to "write a unit guide for {class}", "document how to use {feature}", "add a guide for {file}", or after shipping a user-facing class, node, or plugin. Don't use for internals documentation aimed at someone changing or extending the unit — that is a design document under `docs/design/` (use `adk-unit-design`). Don't use to write a runnable sample under `contributing/samples/` (use `adk-sample-creator`).

  • Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide, or a documentation page; wants to know which snippets in a Markdown file are broken or out of date; or asks for a snippet verification report. Don't use for running the project's test suite (run pytest directly), for checking code style or formatting (use `adk-style`), or for authoring a new runnable sample agent (use `adk-sample-creator`).

  • Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.

  • Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.

  • A math calculation skill that runs Python scripts to perform arithmetic.

  • A text processing skill that formats strings using shell scripts.

  • A skill that provides weather information based on reference data.

google/adk-kotlin

9 skills 308
npx skilld add google/adk-kotlin --all
  • Casts a fireball at a specified target.

  • A simple skill that echoes provided arguments.

  • Description

  • A simple skill that prints provided arguments using Python.

  • A skill living directly under the assets root.

  • Name field does not match the directory name.

  • Skill that has a directory outside the allow-list.

  • Description 1

  • Description 2

google/agents-cli

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

8 skills 6.4k
npx skilld add google/agents-cli --all
  • Use when working in this project — adding tools, editing the agent, running, evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent, google.adk, adk web, or an ADK runner. This project is LangChain/LangGraph scaffolded by agents-cli, so ADK-specific instructions do not apply.

  • This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

  • This skill should be used when the user wants to "deploy an agent", "deploy my ADK agent", "set up CI/CD", "configure secrets", "troubleshoot a deployment", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an Agent Gateway. Covers deployment workflows, service accounts, rollback, and production infrastructure. Applies to any framework agents-cli deploys (ADK, LangChain, ...). Part of the agents-cli skills suite. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), evaluation (use google-agents-cli-eval), or project scaffolding (use google-agents-cli-scaffold).

  • This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

  • This skill should be used when the user wants to "set up tracing", "monitor my agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations (AgentOps, Phoenix, MLflow, etc.), and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment setup (use google-agents-cli-deploy) or API code patterns (use google-agents-cli-adk-code).

  • This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

  • This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers `agents-cli scaffold create`, `scaffold enhance`, and `scaffold upgrade` commands, template options, deployment targets, and the prototype-first workflow. Do NOT use for writing agent code (ADK projects: use google-agents-cli-adk-code) or deployment operations (use google-agents-cli-deploy).

  • 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", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle and coding guidelines. Entrypoint for building ADK agents. Always active — provides the full workflow (scaffold, build, evaluate, deploy, publish, observe), code preservation rules, model selection guidance, and troubleshooting steps for ADK or any agent development.

google/elephant-goldfish-model

Open-source plugin for designing and reviewing software with agents

7 skills 22k
npx skilld add google/elephant-goldfish-model --all
  • Bootstrap directory README.md files across a repository subtree.

  • Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.

  • Drafts a design document section-by-section using the concepts brief from egm-brainstorm (or user notes). This is the second step in the Elephant-Goldfish (EGM) feature flow. Use when you are ready to write a design doc after aligning on requirements + solution.

  • Runs drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences. Use when the user asks to detect drift or check for consistency across all design documents or READMEs in a directory.

  • The Elephant resolution skill. Ingests flat deficiency reports from concurrent Goldfish reviewers, applies automated fixes for PROPOSE FIX items via UI multiple-choice gates, and presents interactive negotiation/re-sync checkpoints.

  • Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.

  • Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.

google/meridian

Meridian is an MMM framework that enables advertisers to set up and run their own in-house models.

5 skills 1.6k
npx skilld add google/meridian --all
  • Loads a fitted Meridian model and runs budget optimization scenarios. Use when the user wants to load a saved model and find the optimal budget allocation or target ROI spending. Don't use for visualizing model performance (use meridian-result-visualization) or building/fitting the model (use meridian-model-building).

  • Assists users with questions about Meridian Marketing Mix Modeling and Meridian GeoX geo-experiment concepts, parameters, and best practices by finding and consulting the relevant documentation on developers.google.com/meridian. Use when the user asks for explanations or guidance on Meridian MMM or GeoX topics. Don't use for writing code or running models directly.

  • Guides users through building a Meridian Marketing Mix Modeling (MMM) model. Use when a user wants to load data, map columns, configure ModelSpec, run Exploratory Data Analysis (EDA), fit a model, and save the model. Don't use for visualizing results or creating a scenario planner.

  • Loads a fitted Meridian model and generates standard visualization reports: Model Results Summary. Use when the user wants to load a saved model and view results (model performance, fit, health). Don't use for running budget optimization (use meridian-budget-optimization) or building/fitting the model (use meridian-model-building).

  • Generates Scenario Planner data from a fitted Meridian model and exports it for Looker Studio dashboard creation via Colab handoff. Use when the user wants to generate scenario planning data, budget grids, or Looker Studio dashboards from a saved model. Don't use for visualizing model results (use meridian-result-visualization) or running standard budget optimization (use meridian-budget-optimization).

google/ax

Agent Executor (AX) is Google's open agentic orchestration runtime

2 skills 15k
npx skilld add google/ax --all
  • How AX depends on Agent Substrate (modules, address contract, mocks, version bumps, E2E pin). Load when touching internal/substrate, bumping Substrate, or triaging make test-e2e.

  • End-of-change pass that brings AGENTS.md and skills/ back in step with the code. Load after any code change, before declaring done; it is the last step of the Definition of done.

google/agentmesh

Agent Mesh

1 skill 1.2k
npx skilld add google/agentmesh --all
  • Use when local tools cannot provide a needed capability and an Agent Mesh network can: inspect mesh state, discover reachable services/tools, describe and call namespaced remote MCP tools, reach OpenAI-compatible inference models hosted by mesh peers, and hand work to A2A agents on the mesh through the official a2a CLI. Also use to set up, join, or reconnect a agentmesh-node when its MCP tools are not callable yet.

Skills published by Google. Checked GitHub just now