googlecloudplatform

Diagnoses workspace drift across Modules 1 to 4 of the Pitch Generator lab, delivers progressive 3-tier hints, and restores reference step implementations when hints are exhausted. Use when a learner asks for a hint, gets stuck on a lab step, wants to verify…

Manages local server ports and starts the Pitch Generator web server (port 8080) and optional standalone Visual Director A2A service (port 8801) as background daemon processes. Use when asked to run, start, restart, or test the Pitch Generator app or Visual…

Defines the house brand rules for campaign key visuals covering color palette, lighting, composition, subject treatment, and forbidden visual elements. Use when writing art direction, reviewing visual concepts, or rendering a campaign key visual image so the…

Generate an interactive codebase architecture graph website and optional voice-narrated MP4 walkthrough video for any local, public GitHub, or private GitHub repository. Use when the user asks to visualize a codebase, build an interactive repo walkthrough…

Use when auditing local database inventory using the local-db-server MCP server.

The house brand rules for a key visual — palette, light, composition, subject treatment, and what never appears. Load this before writing art direction or rendering an image, so the visual looks like it came from this brand rather than from a generic image…

Orchestrates parallel worker subagents with real-time telemetry reporting and automated hard circuit-breaking via manage_subagents upon fatal worker errors.

Orchestrates parallel worker subagents executing a 4-step workflow, streaming mid-flight milestone progress reports back to the parent orchestrator via send_message. Use when running multi-step pipeline tasks with live progress reporting.

Comprehensive interpretation framework for AlphaGenome Variant Impact (AVI) scores across 18 modalities, Phred scale tiers, and Atlas links.

ACMG/AMP clinical variant interpretation and triage workflow integrating ClinVar assertions and gnomAD v4 population frequency thresholds.

Methodology for prioritizing non-coding GWAS variants, interpreting trait associations, linkage disequilibrium, and causal regulatory mechanisms.

Pharmacogenomic star-allele curation, CPIC dosing guidelines, and PharmGKB clinical evidence level evaluation for therapeutic response.

Management, monitoring, quota checks, and safe deletion of FoldRun prediction jobs

Submission of protein, RNA, ligand, and multimer predictions via AlphaFold2, AlphaFold3, OpenFold3, and Boltz-2

Quality assessment, confidence scoring (pLDDT, PAE, ipTM), and parallel evaluation of predicted protein structures

Standard report format, headings, and linking conventions for all OASE project artifacts.

Classification decision tree and remediation strategies for diagnosing Terraform acceptance test failures across all workflows.

Executes acceptance tests (testacc) for a specific resource or suite in the GA or beta provider and outputs verbose debug logs.

Creates IAM resources for an existing MMv1 resource that does not yet have IAM resources.

Run fast static checks that don't require generating downstreams, including git submodule verification, gofmt formatting, YAML linting, template validation (version-guard and unused-tmpl), mmv1 core unit tests, internal tool unit tests, and .ci/magician unit…

Skill to automatically triage failing tests by reading test-metadata status files, matching GitHub issues, and generating a multi-section failure report.

Update or add Go module dependencies for the downstream Terraform providers (terraform-provider-google and terraform-provider-google-beta) and sync go.mod and go.sum back to mmv1/third_party/terraform/.

Process raw failure info (GitHub issue URL, direct prompt text, GCS debug log links, or local logs) and normalize it into a clean failure payload for test fixing.

Workflow for diagnosing, fixing, and verifying failing Terraform acceptance tests from GitHub issue URLs (detecting test-failure labels), direct prompts, or log files using Failure Scenario Decision Trees.

Upgrades Spark workloads on Google Cloud Managed Service for Apache Spark (formerly known as Dataproc) clusters and Serverless to a newer image or runtime version. Supports static compatibility analysis, code upgrade, build checks against the target version,…

Configures (or reconfigures) the Google Cloud Data Agent Kit (DAK) plugin by checking gcloud and ADC credentials, collecting the GCP project ID, region, and services, and running its bundled `dak-setup` script. Use this proactively and without waiting to be…

Expertise in generating clean, correct, and efficient Dataform pipeline code for BigQuery ELT. Use this when creating or modifying Dataform pipelines, actions, or source declarations, when Dataform, SQLX, or BigQuery are mentioned in a transformation, when…

Expert guidance for creating, modifying, and optimizing dbt pipelines for BigQuery. Use this skill whenever user asks for generating or modifying a dbt model or project. Activate this skill when the user - Creates, modifies, or troubleshoots **dbt models or…

This skill helps the agent generate or update orchestration pipeline definitions for Google Cloud Composer to initialize orchestration pipeline or update the orchestration definition for orchestration of various data pipelines, like dbt pipelines, notebooks,…

Monitors, inventories, and assesses Google Cloud Managed Service for Apache Spark (Dataproc Serverless and Dataproc on Compute Engine) environments, clusters, batches, jobs, sessions, metrics, logs, costs, and configurations across single and multiple…

Authors, optimizes, and runs PySpark and Spark code on Google Cloud Managed Spark (Dataproc Serverless, clusters, and Spark Connect). Use when: - Authoring or running Spark/PySpark notebooks in any kernel (Local Kernel with spark-remote templates, Remote…

Provides data-retrieval best practices, tool selection guidance, and performant SQL query syntax for BigQuery telemetry across INFORMATION_SCHEMA, Cloud Monitoring, and the REST API. Use when the telemetry to fetch is already known, selecting telemetry tools,…

Implement the core reconciliation logic (Adapter) and E2E fixtures for a direct controller migrating from legacy

Provides provides clear review criteria for reviewing PRs that add controllers for KCC Greenfield resources.

Guides the implementation of KRM types and CRD scaffolding for migrating existing resources to "direct" controllers.

Standards and rules for implementing KCC direct controllers for GCP resources that ONLY support service-generated IDs.

Guides the implementation of export support for a direct controller, including implementing AdapterForURL and verifying it through the unified test runner.

Guides the implementation of Phase 2 (direct controller logic, E2E fixtures, and fuzzer) for KCC Greenfield resources, with a focus on real GCP recording and verification.

Implement the core reconciliation logic (Adapter) and E2E fixtures for a direct KCC resource. Use this after Step 1 is complete.

Guides the implementation of Phase 3 (MockGCP and Alignment) for a direct KCC resource, verifying behavioral correctness against simulated GCP services. Use this when you need to implement or align mockgcp for a KCC resource.

Use when deploying or configuring the genai-factory cloud-run-nl2sql-bq blueprint (Natural Language to SQL Google ADK agent on Cloud Run querying BigQuery), pointing the bigquery_agent at a custom BigQuery dataset (BQ_DATA_PROJECT_ID, BQ_DATASET_ID), enabling…

Use when deploying or configuring the genai-factory cloud-run-rag-alloydb blueprint (Cloud Run RAG frontend and scheduled BigQuery ingestion job backed by AlloyDB for PostgreSQL with pgvector and alloydb_scann over Private Service Connect), building and…

Use when deploying or configuring the genai-factory cloud-run-rag-cloudsql blueprint (Cloud Run RAG frontend and scheduled BigQuery ingestion job backed by Cloud SQL for PostgreSQL with pgvector over Private Service Connect), tuning db_configs, running the…

Use when deploying or configuring the genai-factory cloud-run-rag-search blueprint (Cloud Run RAG frontend and scheduled GCS ingestion job backed by Vertex AI Vector Search 2.0 Collections with auto-embeddings and Hybrid Search / RRF), customizing…

Use when deploying or configuring the genai-factory cloud-run-single blueprint for a single Cloud Run GenAI application (chat, Google ADK agent, ADK with A2A server, Gemma 3 on NVIDIA L4 GPU, or FastMCP server) with External/Internal Application Load…

Use when deploying or configuring the genai-factory serve-private-models blueprint (Vertex AI Model Garden open models such as Gemma 3 privately exposed via Private Service Connect to a Cloud Run frontend with Load Balancer, Cloud Armor, and Model Armor),…

Use when deploying or configuring the genai-factory agent-runtime blueprint on Vertex AI Agent Engine (Reasoning Engine), switching between the ADK and ADK + A2A sample agents, configuring PSC-I network attachments or Secure Web Proxy egress, attaching an…

Use when configuring Cloud Run services or scheduled RAG ingestion jobs in genai-factory, setting up External HTTPS or Internal Application Load Balancers (lbs_configs), Cloud Armor IP allowlists, Certificate Authority Service (ca_pool_name_suffix), Direct…

Reviews project source code against workspace development standards covering copyright headers, documentation completeness, PEP 8 style, logging, error handling, and dependency hygiene. Use when performing a local code review or checking code quality. Don't…

Generates and updates project README documentation based on codebase changes. Use when generating or updating application documentation. Don't use for inline code comments or docstring-only refactoring.

Converts raw application ideas into a product manager and software architect technical specification and scaffolds the prototype application. Use when designing and building a new application prototype from a user prompt. Don't use for modifying existing…

Commits local changes to a new Git branch and opens a GitHub pull request through the configured GitHub MCP server. Use when proposing code changes in a new pull request. Don't use for local-only commits without a remote GitHub repository.

Runs pre-commit verification steps including documentation updates, unit test generation and execution, and security code analysis. Use when preparing changes before creating a commit or pull request. Don't use for initial application scaffolding or opening…

Performs a security audit of the project source code and dependencies to identify vulnerabilities and recommend remediations. Use when scanning the codebase for security issues. Don't use for functional unit testing or style-only code formatting.

Generates and executes Python unit tests for methods in the project. Use when creating or updating unit test suites for Python files. Don't use for end-to-end browser testing or security vulnerability scanning.

Modernizes a legacy .NET application to the current .NET Long-Term Support (LTS) release on Cloud Run with Cloud SQL for PostgreSQL. Use when asked to modernize, containerize, or migrate the .NET application in the current working directory to Cloud Run and…

Use when the marathon plan needs non-spatial event parameters defined: theme, hydration-point logistics, crowd zones, start times, or expected participant counts. Triggered when the request describes the feel or operational logistics of the race rather than…

Use when the marathon plan needs a 26.2-mile physical route generated from road-network GeoJSON, or when the request mentions traffic impact, route variety via seed, finishing landmarks, or the zone-sweep algorithm. Triggered by route-planning or…

Use when the planning committee asks about marathon finances or requests a budget change. Triggered by mentions of budget, cost, spending, sponsorship, or any phrasing that implies modifying a financial allocation. Reports in percentages rather than specific…

Use when planning a marathon route that must reference real-world geography: looking up landmarks, businesses, or parks in a city, computing distances between points, or checking historical and forecasted weather for the race date and location. Triggered when…

Use when the planning committee asks to change, increase, decrease, or modify a budget allocation in a security-restricted context. Triggered by any budget-modification phrasing. Refuses the change and directs the requester to an authorized administrator.

Use when a runner agent receives a distance update and must deplete water proportionally, or when the runner enters a hydration station and must decide whether to stop and rehydrate. Triggered by distance events and station events.

Use when a runner agent needs to manage athletic performance during a race tick: accelerating, braking, or reading current vitals (speed, energy, hydration, exhaustion). Triggered every tick the runner is active.

Use when the simulator's loop agent advances the race by one tick: broadcasting state to runners, draining the telemetry buffer, computing traffic conditions, and checking for race completion. Triggered every iteration of the LoopAgent.

Audits, optimizes, and remediates CXAS agent configurations for Gemini Composite v2 voice naturalness directly in local workspaces with cxas-scrapi. Upgrades the model to gemini-composite-v2, clears speaking style instructions and Director's Notes (or keeps…

Converts CXAS golden evaluations to SCRAPI SimulationEvals test cases. Use when generating high-level, goal-oriented test cases from turn-by-turn evaluation JSONs, and when enriching test expectations with inferred tool calls.

End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and iterate to production quality. Use this skill whenever the…

Author, validate, and manage Contact Center AI (CCAI) Insights Autolabeling Rules. Use when users want to translate business labeling logic into CEL condition expressions, maintain declarative autolabel_rules.yaml configurations, or synchronize rules to GCP…

Author, validate, and manage Contact Center AI (CCAI) Insights Configurable Dashboards. Use when users want to define multi-tab analytics dashboards, configure Vega-Lite charts and SQL queries, maintain declarative dashboards.yaml configurations, or…

Automates the ingestion of customer requirement documents such as diagrams, BRDs, code etc., synthesizes high-fidelity natural transcripts, and compiles them into highly interactive, responsive Critical User Journey (CUJ) reports.

Migrate Dialogflow CX (DFCX) agents to CXAS (Customer Experience Agent Studio) agents. Use this skill when the user mentions DFCX migration, migrating agents, converting DFCX to CXAS, porting agents, agent migration, or post-migration…

Enforces 100% task and file ingestion coverage via an asynchronous, supervisor-driven state polling mechanism.

Guide for implementing a database source connector in the v2/cdc-data-generator Dataflow template. Details scope boundaries, prerequisites, connector implementations, factory registrations, unit testing, and smoke testing guidelines.

Specific runner skill that creates integration tests for the gcs-spanner-dv (Data Validation) template.

Functionally tests local Dataflow pipeline changes against the main branch using ephemeral GCP resources and gated approvals. Use ONLY when functionally testing one of these specific migration templates: gcs-spanner-dv, sourcedb-to-spanner,…

Guide for implementing a database source connector in the v2/datastream-to-spanner forward migration Dataflow template. Details scope boundaries, prerequisites, connector implementations, registry registrations, unit testing, and smoke testing guidelines.

Guide for implementing a database source connector in the v2/sourcedb-to-spanner forward migration Dataflow template. Details scope boundaries, prerequisites, connector implementations, registry registrations, unit testing, and smoke testing guidelines.

Guide for implementing a database source connector in the v2/spanner-to-sourcedb reverse migration Dataflow template. Details scope boundaries, prerequisites, connector implementations, registry registrations, unit testing, and smoke testing guidelines.

Specific runner skill that delegates to the Template-Agnostic Meta-Test Orchestrator for the datastream-to-spanner (CDC) template.

Specific runner skill that delegates to the Template-Agnostic Meta-Test Orchestrator for the sourcedb-to-spanner (Bulk) template.

Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.

Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Veo, Lyria, Gemini TTS, NanoBanana).

Expert in casting, directing, and generating expressive text-to-speech using Gemini TTS (Gemini 3.8 Flash / Flash-Lite TTS and earlier 3.1 / 2.5 models). Use this when the user needs virtual voice actor personas, expressive speech generation, two-speaker…

Expert in generating full multi-scene multimedia storybooks (image, video, voice, and music) with dynamic duration probing, conversational tempo guardrails, a dedicated self-correcting Editor's QC Room, and pipeline flowcharts embedded in interactive reports.

Assess and convert/port a Mesop (Python) app to a FastAPI backend + Lit web components + Web Awesome (default) or Material 3 (Material Web, opt-in) + Vite build. Use when asked to assess, plan, port, migrate, or convert a Mesop app (or a single Mesop…

Builds the mcp-genmedia Go MCP servers (nanobanana, veo, lyria, gemini-multimodal, chirp3-hd, avtool) from source and wires them into settings.json. Use this skill whenever the MCP tools are missing or broken — typically at the start of a new session, after a…

Installs Google's GenMedia MCP servers (Lyria, NanoBanana, Veo, Chirp, AVTool) via curl from pre-compiled release binaries and registers them in mcp_config.json. Use when the required media synthesis tools are missing or inactive.

Generate images from a text prompt (optionally guided by reference images) using the genmedia Nanobanana MCP server's nanobanana_image_generation tool. Use when a task needs a still image produced from a description, with control over aspect ratio,…

Generates and validates Google Cloud Cluster Toolkit (gcluster) YAML blueprints for Slurm-based HPC clusters. Activate this skill whenever the user asks to create, modify, inspect, or validate a Google Cloud HPC Cluster Toolkit blueprint.

Role and workflow rules for evaluating Nextflow pipelines, profiling FASTQ manifests, and compiling GCP Batch optimized nextflow.config files.

Generates and validates Google Cloud Cluster Toolkit (gcluster/ghpc) YAML blueprints for Slurm-based HPC clusters. Activate this skill whenever the user asks to create, modify, inspect, or validate a Google Cloud HPC Cluster Toolkit blueprint.

Inspects and reports GCP Compute capacity, Standard vs. Spot CPU quotas, and storage architecture constraints (Persistent Disk vs. Hyperdisk) for HPC workloads. Use when the user asks about compute quotas, CPU limits, or available capacity across GCP regions.

Monitors and visualizes Google Cloud Batch nodes in use (Spot vs. Standard VMs), who is running Batch jobs and for what duration, and active/completed Batch jobs with their execution durations and 30-day historical statistics, including an interactive GUI…

Monitors and visualizes HPC cluster instances running over time, Slurm environment jobs and per-user workload ownership, and active HPC storage systems (Managed Lustre, Cloud Filestore, Cloud Storage FUSE, Local NVMe) with 30-day historical statistics and an…

Evaluates Nextflow bioinformatics pipelines, profiles input data manifests, and compiles Google Cloud Batch optimized nextflow.config files with hardware tiering and QA auditing. Use when the user asks to configure, optimize, or run Nextflow workflows on…

Analyzes and reports GCP storage quotas, capacity headroom, and performance tiers for Filestore Zonal, Filestore Regional, and Managed Lustre. Use when the user asks about storage quotas, Filestore or Lustre capacity, or shared filesystem limits.