gcsfuse-cve-patchingEnd-to-end runbook for patching CVEs across GCSFuse release branches (<version>_release) and master, including next-release branch creation, dependency and Go toolchain upgrades, target-toolchain govulncheck binary verification, and labeled PR creation.gcsfuse-minor-release-branchEnd-to-end runbook for cutting and pushing a new GCSFuse minor release branch (v<major>.<minor>.0_release) from master after pre-cut govulncheck and unit test gating (raising master fix PRs first if any vulnerabilities or unit test failures exist).gcsfuse-dep-upgradeStep-by-step workflow to identify, upgrade, and verify external Go module dependencies and Go toolchain versions in the GCSFuse repository, including CVE and security vulnerability remediation.gcsfuse-buildStreamlined workflow to compile the GCSFuse codebase, verify layout formats, resolve imports, and perform static analysis checks using make build.gcsfuse-pull-requestAutomated step-by-step workflow to construct, format, push, and create pull requests in the GCSFuse repository following Conventional Commits and repository PR templates.ssh-connection-managementGuides on establishing persistent master SSH multiplexing sockets at ~/.ssh/sockets/<TARGET_NAME>.sock using ssh -f -N -M -S, testing connection liveness, gracefully terminating via -O exit, removing stale control sockets, and recreating sockets when remote…gcsfuse-integration-testingStep-by-step runbook for creating, extending, and verifying integration tests in the GCSFuse repository.
Repository-Explorer
GoogleCloudPlatform · Repositories und repräsentative Skills - Seite 3
Repository-Ansicht von 553 gesammelten Skills in 61 GitHub-Repositories.
context-engineering-bootstrapGenerate a baseline ContextSet (Templates, Facets, Value Searches) from a target database's schema (and optional design docs / application code) and save to a caller-specified path. Optionally upload to the Context Set server. Don't use when a user asks to…context-engineering-evaluateGuides the agent to execute an evaluation of a ContextSet against a golden NLQ+SQL dataset using the Evalbench framework, either standalone or as one iteration of the hill-climbing loop.context-engineering-hillclimbAutonomously improve a ContextSet by iterating evaluate → analyze → mutate → re-upload until convergence, given a golden dataset and (optionally) a base context. The user supplies inputs once; no per-iteration approval needed.context-engineering-initConfigures the workspace and environment for database context engineering — manages Toolbox `tools.yaml` database connections, verifies runtime and GCP readiness (uv, Evalbench, ADC, Dataplex/GDA APIs, IAM), records workspace defaults once in…context-engineering-workflowUse this skill when the user is new to context engineering, asks how to get started, or is unsure which peer skill to invoke. Explains the ContextSet concepts (Templates, Facets, Value Searches), the optimization lifecycle, and routes to the right peer skill…context-engineering-dataset-generationGenerate or expand a golden evaluation dataset of SQL/Question (NLQ+SQL) pairs for evaluating NL-to-SQL translation accuracy on a target database. Don't use for generating context items (Templates, Facets, Value Searches) or running Evalbench evaluations.context-engineering-generation-guideGuidelines and best practices for generating context items (Templates, Facets, Value Searches). Use this skill whenever the user asks to create, author, or generate context for database enrichment, or asks for examples and instructions on how to write…
google-cloud-storage-diagnosticTroubleshoots and diagnoses Cloud Storage on Google Cloud (also known colloquially as GCS) errors, 403 Permission Denied or Insufficient Permission denials, and access control conflicts. Use whenever a user encounters or asks to analyze a 403 error on a…gcs-security-assessmentAssesses the security posture of Google Cloud Storage (GCS) buckets and projects. Grounds every finding in gathered telemetry, evaluates buckets against Google security best practices (public access, IAM over-granting, CMEK, VPC Service Controls, audit…google-cloud-storage-bucket-architectCreates Cloud Storage (Google Cloud Storage, or GCS) buckets. Analyzes the workload (sensitive data, media hosting, ingestion, web hosting, archiving, backup, logging, analytics, AI/ML, or general-purpose), validates project-level security settings, and…google-cloud-storage-fuseMounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when you need to interact with gcsfuse — decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute…google-cloud-storage-okfExperimental, generic, and powerful skill for token-efficient search, semantic navigation, and progressive disclosure of unstructured or semi-structured objects (PDFs, logs, JSON/CSV dumps, media, large documents) in Google Cloud Storage (GCS) using the Open…google-cloud-storage-basicsStores, 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,…
liveapi-serviceGenerates a LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a client that connects to the Gemini LiveAPI websocket endpoint (Gemini Enterprise or non-Gemini Enterprise), handles…genai-sdkGuides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API,…quality-flywheelEvaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK. Creates eval datasets (from session traces or synthetic generation), selects and configures metrics (RubricMetric, LLMMetric, CodeExecutionMetric), executes evals via…vertex-aiPrimary Router for Vertex AI skills. Use this skill when the user wants to work with Google Cloud Vertex AI (e.g., deploying models, running inference, or tuning models). This skill routes to vertex-deploy, vertex-inference, or vertex-tuning.vertex-tuningVertex AI Model Tuning. Use when you need to fine-tune models using Vertex AI's infrastructure.
use-case-deploymentEnd-to-end orchestration and deployment runner for all solution guides in this repository. Use when deploying, running, ingesting test data into, or validating any of the 10 solution guides: GenAI & ML (Gemma 4 with vLLM on GPU), ETL & Integration (Spanner…terraform-deployManage, validate, plan, apply, and destroy Google Cloud Foundation Fabric Terraform infrastructure across all solution guides in this repository. Use when setting up new GCP environments, modifying IAM configurations, managing Spanner/BigQuery/Bigtable…dataflow-pipeline-devDevelop, format, lint, package, and test Apache Beam Dataflow pipelines in Python and Java within this repository. Use when modifying existing pipeline DoFns, creating new Beam pipelines, configuring pipeline options, running local tests with DirectRunner,…dataflow-troubleshootingDiagnose, debug, and resolve common Apache Beam and Google Cloud Dataflow errors in this repository. Use when Dataflow jobs fail to start, workers crash or fail health checks, IAM permission errors occur, Cloud Build or Docker container images fail, GPU…pr-reviewReview, validate, test, approve, and merge Pull Requests in this repository. Use when asked to review a PR, wait for CI builds/checks to pass, verify compliance with repository policies (AGENTS.md, security guardrails, coding standards), approve safe PRs,…
llm-d-benchmarkingBenchmarks a deployed llm-d well-lit path guide stack on GKE using llm-d-benchmark cli with inference-perf as the harness, the user a will select the appropriate workload profiles from llm-d-benchmark.llm-d-workload-tunerThis is an experimental Skill. It automatically tunes GKE vLLM inference server parameters and resources based on workload profiles specified in the benchmark configs.llm-d-deploy-stackDeploys the llm-d stack on GKE using well-lit paths specification.gke-inference-stack-deployDeploys the GKE base platform and inference-specific terra-services (GPU/TPU) for accelerated workloads.
review-policy-protobufReviews policy protobuf definitions under proto/policy/ in GoogleCloudPlatform/opentelemetry-operations-collector. Focuses on core control-plane design principles: declarative-friendly modeling, matcher orthogonality, normative evaluation semantics, invalid…update-opentelemetry-versionInstructions for updating the OpenTelemetry version for a distribution (like google-built-opentelemetry-collector or otelopscol) in this repository.eventInstructions and semantic convention guidelines for working with the pkg/event package and OpenTelemetry Weaver code generation. Use this skill when adding or modifying events, updating pkg/event/schema/events.yaml, or modifying the Jinja2 templates in…distrogenInstructions for developing and using the distrogen CLI tool. Use this skill when modifying the distrogen codebase or troubleshooting its behavior.
skillsGathers detailed information on a topic using Google Search.skillsTransforms research findings into a formatted course module and verifies structure.agent-platform-debuggerDebug GCP Gemini Enterprise Agent Platform issues: Agent Gateway 403s, Agent Registry failures, Agent Identity/IAM denials, IAP egressor authz, service-extensions delegated authz, Model Armor integration failures (500s/denials), hostname mismatches,…
cluster-blueprint-assistantCreate, customize, validate and troubleshoot Cluster Toolkit blueprints with gcluster. Use when asked to set up or modify a Slurm/GKE cluster blueprint, change node counts, machine types, zones, Spot or reservations, add storage like Lustre or Filestore, or…xpk-to-clustertoolkitMigrate xpk CLI commands, scripts, and documentation to Cluster Toolkit blueprints and gcluster CLI submission commands. Use when migrating AI/ML TPU/GPU workloads from xpk to Cluster Toolkit.gke-kueue-debuggingDebug GKE Kueue batch workload admission, pending jobs, cohort borrowing, queues, flavor matching, AdmissionChecks (DWS / TPU slicing), and TAS topology. Use when AI/ML jobs remain in Pending, Inadmissible, or Admitted: False state.
add-source-e2e-integ-test-smtSkill for independently generating Integration Tests and performing End-to-End QA validation for newly added Spanner Migration Tool database sources.add-source-support-smtThis skill provides comprehensive architectural instructions for agents to safely implement entirely new database source engines into the Spanner Migration Tool (SMT). It depends on user-provided data-type and feature mapping matrices for adding source…source-baseline-matrix-research-skillSkill for helping achieve datatype and feature mapping matrix for any source against spanner. It does research and provide baseline mapping matrix on which user can expand upto.
gitops-interaction-guideStandard interaction, terminal session, and execution mode management for all GitOps workshop skills. Enforces explain-before-execute transparency, handles tmux environment detection, pane creation/selection, autonomous vs guided mode selection, and command…gitops-provision-projectInteractive, beginner-friendly guide for self-service tenant project and microservice workload provisioning in GitLab and ArgoCD App-of-Apps GitOps. Explains GitOps multi-tenancy concepts, conducts interactive parameter interview, provisions…gitops-workshop-guideInteractive end-to-end orchestrator and guide for bootstrapping and operating the GitOps Workshop environment (GCP Project, GKE, ArgoCD, GitLab, and App-of-Apps GitOps). Manages mode selection, tmux pane command staging, .env configuration…
knowledge-catalog-discovery-agentAnalyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.kb-searchAllows listing, searching and extracting information from local knowledge base documents for information about tables