GoogleCloudPlatform
- 312 skills
- 0 followers
- 1.1k repo stars
- yesterday last updated
- ▌ Pkb Cl Reviewer · googlecloudplatformReviews PerfKitBenchmarker (PKB) codebase diffs against strict methodological guidelines. Use this skill when analyzing a PKB CL to enforce coding standards, provide inline feedback, and decide on approval vs not.
- ▌ Git Sandbox · googlecloudplatformGit workflow protocol for agents in sandbox/worktree environments. Covers local-only operations, worktree-aware branch management, and non-interactive conflict resolution. Injected only for git-associated workspaces.
- ▌ Git Operations · googlecloudplatformGit safety and operational guidance for Scion agents. Covers working tree resets, shallow clones, rebase pitfalls, and general git behavior that agents should know regardless of workspace mode. For workspace-mode-specific git rules, see the git-sandbox skill.
- ▌ Scion Artifacts · googlecloudplatformUse when publishing a document, report, folder or small HTML site for others to read or review, adding a version, reviewing an artifact with CriticMarkup, fetching or listing artifacts, or sending a scion://artifact reference in a message. Covers scion artifact publish, get, versions, comments, list and view, scion message --artifact, and what agents cannot do.
- ▌ Scion Messaging · googlecloudplatform bundleUse when sending messages to users or agents with scion message, choosing conversations and mentions, or interpreting incoming messages. Covers user-facing formatting, agent delivery, and reading conversation history.
- ▌ Scion Scheduler · googlecloudplatformSchedule one-shot and recurring events for agents using the Scion CLI. Covers self-callbacks, recurring cron schedules and time zones, which schedules an agent can see, lifecycle management, and the blocked-wait pairing rule.
- ▌ Scion Web Serving · googlecloudplatform bundleHow to serve a web page, app, API or other HTTP service from inside your agent so a person or program can reach it through the Hub's port proxy: scion expose and unexpose, the URL to hand over, what the proxy carries, and scion tunnel for full apps. The link serves web protocols only; for a non-HTTP port, point the person to scion tunnel. Use before running scion expose. For web pages and apps, also read references/web-apps.md.
- ▌ Scion Agent Manage · googlecloudplatform bundleManage concurrent LLM-based code agents with scion - orchestrate parallel agents with isolated workspaces, troubleshoot and recover stuck agents
- ▌ Scion Conversation · googlecloudplatformHow to use the scion conversation command for managing conversations. Covers listing, creating, viewing, participant management, and message retrieval. Complements the scion-messaging skill.
- ▌ Scion CLI Operations · googlecloudplatformOperational constraints for Scion agents running in containerized sandboxes. Covers prohibited commands and hub-only API access. Complements the scion CLI reference and messaging skills.
- ▌ Bigquery Graph Author · googlecloudplatform bundleProvides an end-to-end journey for authoring a BigQuery property graph from your tables or from a model document/diagram (an ER diagram, an ontology, a semantic model): dataset discovery, candidate relationships verified against the data, a readable plan, and `CREATE PROPERTY GRAPH` DDL with schema best practices and semantic measures/dimensions, plus an opt-in verification suite for the landed graph. Use when creating or replacing a property graph, authoring a graph from a dataset or a document, or verifying relationships or suspicious edge counts. Don't use for querying an existing graph, for non-BigQuery graph databases, or for drawing/rendering diagrams.
- ▌ GCP Spark Observability · googlecloudplatform bundleMonitors, 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 regions. Use when listing active or historical Spark workloads, discovering failed batches or jobs, auditing multi-region fleet inventory, calculating Serverless compute (DCU-Hours) and shuffle storage consumption, detecting idle or zombie clusters, inspecting scheduled pipeline cadence health, investigating failed cluster operations or stockouts, checking quotas and alerting coverage, or querying Cloud Monitoring and Cloud Logging telemetry. Don't use for deep root-cause analysis or performance optimization of a specific job or batch (use gcp-spark-troubleshooting), authoring new PySpark code (use gcp-spark), or upgrading Spark versions (use gcp-managed-spark-upgrades).
- ▌ GCP Spark Troubleshooting · googlecloudplatform bundleProvides expert guidance for troubleshooting Google Cloud Spark and Dataproc workloads (Dataproc Serverless batches, interactive sessions, and standard Dataproc clusters), and inspecting, streaming, searching, tailing, or summarizing Spark driver outputs and event logs in Cloud Storage. Use when debugging, diagnosing, or performing Root Cause Analysis (RCA) on failed or slow Spark jobs, PySpark scripts (.py), JVM archives (.jar), compressed event logs (.zst), or IAM, VPC, and classpath errors such as OutOfMemoryError, 403 PERMISSION_DENIED, NoSuchMethodError, and ClassNotFoundException. Do NOT use for authoring new Spark jobs (use gcp-spark), planning or performing runtime version upgrades (use gcp-managed-spark-upgrades), or non-Spark engines such as Dataflow or BigQuery Data Transfer Service.
- ▌ Cloud Databases Onboarding · googlecloudplatform bundleGuides users through discovering their database requirements, recommends a Google Cloud database product or migration destination based on a recommendation matrix, and assists in database creation. Use when a user asks 'What database service should I use?', 'Help me pick a database', asks which Google Cloud database to migrate or onboard a workload to, or wants to create a new database on Google Cloud. Don't use for general Google Cloud maintenance, managing existing databases, or troubleshooting active Database Migration Service (DMS) jobs.
- ▌ GCP Managed Spark Upgrades · googlecloudplatform bundleUpgrades 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, and optional verification runs. Use when: - Upgrading Managed Spark versions (major, minor, or sub-minor) or assessing upgrade readiness. Example prompt: "Upgrade Managed Spark job [job_id] in project [project_id], region [region] to target version [target_version]. Code location: [local path or GCS path]. Target GCS path: [gcs_target_path]" Don't use when: - Writing new Spark code. - Migrating non-Spark workloads (e.g., Hive/Flink to Spark). - Troubleshooting a failed Spark job that is not part of an upgrade. Limitation: This skill does not support data/result validation currently.
- ▌ Resolving MCP Region Configs · googlecloudplatformMandatory Step 0 pre-flight check for regional Google Cloud MCP servers (Composer dak-composer, Dataform dak-dataform, and Dataflow dak-dataflow) before using regional MCP tools or falling back to gcloud/bq CLI. Use whenever a task involves Cloud Composer / Managed Airflow environments, DAGs, or tasks; Dataform repositories, workspaces, compilations, or workflow invocations; or Dataflow jobs, pipelines, or templates, and the expected mcp__*__composer__*, mcp__*__dataform__*, or mcp__*__dataflow__* tools are missing (ToolSearch/deferred tools) or fail on a malformed host. Inspects the live Data Agent Kit plugin MCP config (mcp.json, .claude-plugin/mcp.json, mcp_config.json) across Claude Code, Codex CLI, and Antigravity CLI for unreplaced $GCP_REGION, ${region}, or ${REGION} placeholders, and delegates configuration to @skill:dak-setup instead of editing by hand. Do NOT use when regional MCP endpoints already have a valid region, when regional MCP tools work, or for non-regional services.
- ▌ Dak Setup · googlecloudplatform bundleConfigures (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 asked whenever a SessionStart hook or any other system/context message reports that the Data Agent Kit plugin is not configured, is missing configuration, or needs to be reconfigured. Also use it whenever the user mentions setting up, configuring, reconfiguring, or changing the project, region, or service integrations for the Data Agent Kit or DAK plugin — even if they phrase it casually, like "dak isn't working" or "I want to enable more GCP service integrations".
- ▌ GCP Spark · googlecloudplatform bundleAuthors, 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 Spark / Remote Kernel, ManagedSparkSession, Spark Connect). - Querying, transforming, or writing data with PySpark or Spark SQL, including Apache / BigLake Iceberg, BigQuery, GCS, Spanner, Cloud SQL, AlloyDB, Amazon S3, or Azure Blob Storage / ADLS Gen2. - Building PySpark ETL pipelines, machine learning workloads, or batch jobs. - Managing Dataproc clusters, serverless batches, or interactive sessions. - Optimizing PySpark or Spark SQL queries for performance, memory, and OOM prevention. Do NOT use when: - Auditing multi-region fleet inventory, DCU/cost consumption, idle/zombie clusters, or workload observability (use @skill:gcp-spark-observability). - Troubleshooting failed Spark jobs or Dataproc batches (use @skill:gcp-spark-troubleshooting).
- ▌ Curate Context · googlecloudplatform bundleCreates, imports, pulls, edits, repairs, or publishes a Knowledge Catalog (KC) context set as Open Knowledge Format (OKF v0.2) markdown under `bundle/` with `kcmd`, for BigQuery, Spanner, BigLake, Cloud SQL, AlloyDB, or Hive Metastore. Load FIRST whenever creating, importing, pulling, editing, repairing, or publishing a context set or OKF bundle/folder, or using `kcmd`, before running `kcmd` (never unscoped `kcmd` from pip/npx or unconfirmed `./kcmd`) or editing files: e.g. "build a context set from our sales tables and metric doc", "update churn in our context set and publish". Plans first, validates, and publishes only after user approval at both gates, even when told to work autonomously. Keeps the user's OKF folder/structure. If also asked for OSI-G semantic models, ontology canvases, new glossary terms, access changes, or certification, still use it: builds the context set and declines those parts. Never for read-only catalog search or data questions.
- ▌ Bigtable Basics · googlecloudplatform bundleProvisions instances and tables, designs performant schemas, and queries 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.
- ▌ Discover Assets · googlecloudplatformFinds and inspects data assets within Google Cloud. Use for any question that needs to discover data sources or find/inspect schemas, metadata, or domain rules for tables. Relevant when: (1) finding, exploring, or inspecting GCP data assets; (2) retrieving schemas, metadata, or governance policies for a GCP data asset (including a named table); (3) you have a keyword or topic (e.g., "sales data") without a table or resource ID; (4) the user asks for enterprise data, metrics, tables, datasets, analytics, business terms, financial reports, or industry statistics (e.g., banking, e-commerce, transit, SEC filings, solar, healthcare) without full table schemas. Don't use for general knowledge questions unrelated to data, or when both explicit table schemas and full SQL are already provided.
- ▌ Bigquery Graph Query · googlecloudplatform bundleProvides guidelines and best practices for querying BigQuery property graphs and semantic graphs: native GQL (Graph Query Language) pattern matching, multi-hop and variable-length paths, aggregation, top-N, path extraction, output formatting (graph visualization with TO_JSON vs tabular), GRAPH_TABLE relational SQL integration, and semantic graph querying via the GRAPH_EXPAND TVF with starting-node view selection and AGG() measures. Also covers hybrid semantic search, combining `VECTOR_SEARCH` candidate generation with graph traversal when a node carries an embedding-backed property. Use when querying graph topology, node/edge connections, paths, or semantic measures over an existing BigQuery graph. Don't use for Cypher or non-BigQuery graph databases, or for creating/modifying a graph schema.
- ▌ Gke Kueue Debugging · googlecloudplatform bundleDebug 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.
- ▌ Xpk To Clustertoolkit · googlecloudplatform bundleMigrate 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.
- ▌ Cluster Blueprint Assistant · googlecloudplatform bundleCreate, 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 fix gcluster expand/create/deploy errors.
- ▌ Genai Factory Cloud Run RAG Cloudsql · googlecloudplatform bundleUse 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 BigQuery-to-Cloud-SQL embedding pipeline, or troubleshooting Cloud SQL Auth Proxy PSC connectivity and pgvector 3072-dimension indexing limits.
- ▌ Genai Factory Cloud Run RAG Search · googlecloudplatform bundleUse 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 vector_search_config or ScaNN ANN indexes, or troubleshooting europe-west1 tenant creation and COLLECTION_HAS_DATA_OBJECTS errors on destroy.
- ▌ Genai Factory Serve Private Models · googlecloudplatform bundleUse 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), configuring model_garden_config (publisher or Hugging Face models on NVIDIA L4 GPUs), or troubleshooting provider region, EULA consent, and GPU quota errors.
- ▌ Genai Factory Cloud Run RAG Alloydb · googlecloudplatform bundleUse 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 running the BigQuery-to-AlloyDB embedding pipeline, or troubleshooting AlloyDB PSC and IAM authentication.
- ▌ Genai Factory Cloud Run Single · googlecloudplatform bundleUse 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 Balancer, Cloud Armor, and Model Armor.
- ▌ Genai Factory Ge Agent Platform · googlecloudplatform bundleUse when deploying or configuring the genai-factory ge-agent-platform blueprint (Gemini Enterprise apps and assistants, SaaS or Custom MCP OAuth 2.0 data connectors, Agent Registry endpoints/A2A agents/MCP servers, Egress Agent Gateway with PSC connectivity template, directional Model Armor templates, and IAM v3 Unified Access Policies).
- ▌ Genai Factory Gecx Agent Studio · googlecloudplatform bundleUse when deploying or configuring the genai-factory gecx-agent-studio blueprint (Gemini Enterprise for Customer Experience / CX Agent Studio google_ces_app with Discovery Engine data stores and private Cloud Run or on-prem OpenAPI toolsets over Service Directory and Internal Regional TCP Proxy Load Balancers), or running agentutil.py to ingest documents, create toolsets, and push CES agents.
- ▌ Genai Factory Cloud Run Nl2sql Bq · googlecloudplatform bundleUse 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 the ADK web interface (SERVE_WEB_INTERFACE), or troubleshooting BigQuery IAM permissions.
- ▌ Genai Factory Agent Runtime · googlecloudplatform bundleUse 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 Agent Gateway, or troubleshooting GOOGLE_CLOUD_LOCATION and Firestore session errors.
- ▌ Genai Factory AI Apps Search · googlecloudplatform bundleUse when deploying or configuring the genai-factory ai-apps-search blueprint (Vertex AI Search / Discovery Engine public website search engine), customizing target website URI patterns (target_sites), querying the servingConfigs/default_search:search API, or troubleshooting empty basic website search results.
- ▌ Genai Factory Gecx Dialogflow · googlecloudplatform bundleUse when deploying or configuring the genai-factory gecx-dialogflow blueprint (Dialogflow CX Conversational Agent with Discovery Engine FAQ and unstructured knowledge base data stores, plus private Cloud Run Function and on-prem webhooks over Service Directory and Internal Regional TCP Proxy Load Balancers), or running agentutil.py to import documents, restore agents, and test detectIntent.
- ▌ Bigquery AI Ml · googlecloudplatform bundleLoad this skill before writing or running any BigQuery SQL that calls AI.* or ML.*. 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.
- ▌ Bigquery Analytic Hints · googlecloudplatformAfter any BigQuery time-series, trend or exploratory analysis, or after running an AI.* function, load this to append up to two next-step suggestions. Recommends and routes to BigQuery AI capabilities for next-step data analysis. Use during exploratory data analysis, time-series or cohort pattern investigation, or text corpus exploration in BigQuery when the user has not requested a specific AI function. Proactively suggests relevant built-in BigQuery AI functions (forecasting, anomaly detection, tabular prediction, change point analysis, key driver attribution, trend/seasonality decomposition, or semantic text classification) as concise follow-up actions. Do not use for writing or looking up exact SQL syntax and function arguments, dataset or table administration, DDL/DML migrations, query performance troubleshooting, or permission checks.
- ▌ Contributing 3 · googlecloudplatformEnd-to-end workflow for contributing to Cloud Foundation Fabric: triaging GitHub issues, proactive feature development, validating with tests and Policy Troubleshooter, and submitting sanitized Pull Requests. Use when addressing a Fabric GitHub issue, developing a module or FAST stage change, or preparing a branch for a pull request.
- ▌
- ▌ Deploying 2 · googlecloudplatformGuides deployment of Race Condition to a GCP project. Use when deploying to the cloud, setting up infrastructure with Terraform, or troubleshooting a deployment. This is for cloud deployment -- for local development, use the getting-started skill instead.
- ▌ Contributing 2 · googlecloudplatformGuides the developer workflow for contributing to Race Condition. Use when setting up pre-commit hooks, running tests before a PR, understanding code style requirements, or preparing a contribution.
- ▌ Getting Started 2 · googlecloudplatformGuides setup of the Race Condition project from clone to running simulation. Use when the developer wants to get the project running locally, install dependencies, configure GCP credentials, or troubleshoot startup issues.
- ▌ Exploring The Codebase 2 · googlecloudplatformExplains the Race Condition architecture, the design decisions behind it, and where to read code first. Use when the developer asks how something works, wants a tour, or wants to understand the system before changing it.
- ▌ Ad Copywriting 2 · googlecloudplatform bundleGoogle Ads copywriting expertise. Covers Responsive Search Ad (RSA) best practices, headline formulas, description frameworks, and character limits. Load this skill when generating text ads, headlines, or ad copy.
- ▌ Brand Strategy 2 · googlecloudplatformBrand strategy and campaign positioning expertise. Covers audience segmentation, competitive differentiation, value proposition frameworks, and campaign brief creation. Load this skill when setting up campaigns, selecting audience segments, or defining creative direction.
- ▌ Platform Specs 2 · googlecloudplatformAd platform specifications and best practices. Covers Google Ads, YouTube, Instagram, TikTok, and Meta ad formats, dimensions, character limits, and optimization tips. Load this skill when creating platform-specific content or recommending campaign settings.
- ▌ Trend Analysis 2 · googlecloudplatformMarket trend analysis and product-trend mapping expertise. Covers how to interpret trend data, align products to cultural moments, and create trend-informed campaign angles. Load this skill during the Creative Research Phase when running trend_spotter and product_trend_mapper.
- ▌ Visual Direction 2 · googlecloudplatform bundleVisual art direction expertise for marketing imagery. Covers photography styles, composition rules, color theory, lighting techniques, and product staging. Load this skill when generating image ads, asset sheets, moodboards, or keyframe images.
- ▌ Video Storytelling 2 · googlecloudplatform bundleCinematic video ad storytelling expertise. Covers 3-act narrative structure, emotional arcs, camera motion, scene transitions, and voiceover pacing for 10-second commercial video ads using Gemini Omni. Load this skill when generating video ads or storylines.
- ▌ Genmedia Producer 2 · googlecloudplatformExpert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or using the GenMedia MCP tools (Veo, Lyria, Gemini TTS, NanoBanana).
- ▌ Bigtable · googlecloudplatform bundleManage Google Bigtable instances/tables, design schemas, and query data using SQL or client libraries. Use for provisioning, schema updates, or code generation.
- ▌ Recaptcha Transaction Defense Integrator · googlecloudplatform bundleIntegrates reCAPTCHA Enterprise Transaction Defense and automates ground truth via PSP chargeback webhooks (Stripe, Adyen). Use when a user wants to protect transactions from fraud and close the feedback loop with automated annotations. Don't use for generic reCAPTCHA v2 checkbox integrations or non-transactional bot protection.
- ▌
- ▌ Fabric Builder · googlecloudplatform bundleGenerates idiomatic Cloud Foundation Fabric (CFF) Terraform code using CFF modules. Use when users ask to create GCP resources, use Fabric modules, or generate Terraform code for Google Cloud.
- ▌ Fast Prerequisites · googlecloudplatform bundleGuides the user step-by-step through the prerequisites for the FAST 0-org-setup stage, supporting both Standard GCP and Google Cloud Dedicated (GCD) environments. Use when a user asks to prepare or run prerequisites for 0-org-setup or bootstrap the FAST landing zone.
- ▌ Release Process · googlecloudplatformGuide for cutting a new release of the Cloud Foundation Fabric (CFF) repository. Use this skill when asked to create, prepare, or draft a new release.
- ▌ Context Engineering Init · googlecloudplatform bundleOrchestrates the initialization workflow for context engineering, and provides helper workflow for setting up database connections by creating or updating tools.yaml configurations.
- ▌ Context Generation Guide · googlecloudplatform bundleGuidelines 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 templates, facets, or value searches. It helps bridge the gap between LLMs and structured databases. For running the automated generation, evaluation, and tuning lifecycle, see the context-engineering-workflow skill.
- ▌ Context Engineering Evaluate · googlecloudplatform bundleGuides the agent to execute an evaluation of a ContextSet against a golden NLQ+SQL dataset using the Evalbench framework.
- ▌ Context Engineering Workflow · googlecloudplatformContext engineering for Gemini Data Analytics API's data agent developer platform tools. Generates, evaluates, and iteratively optimizes a ContextSet (Templates, Facets, Value Searches) to maximize Natural-Language-to-SQL translation accuracy. Use this skill to run the automated setup, NL-SQL pair evaluation dataset generation and expansion, bootstrapping, scoring, and optimization pipeline. For manual authoring standards and schema syntax rules, see the context-generation-guide skill.
- ▌ Context Engineering Bootstrap · googlecloudplatformGuides the agent to bootstrap an initial ContextSet (templates, facets, and value searches) by deducing key information from the database schema and generating a ContextSet file.
- ▌ Context Engineering Hillclimb · googlecloudplatformGuides the agent to perform hill-climbing iterations to improve a ContextSet based on Evalbench evaluation results.
- ▌ Context Engineering Dataset Generation · googlecloudplatform bundleGenerate or expand a golden evaluation dataset of SQL/Question (NLQ+SQL) pairs for evaluating NL-to-SQL translation accuracy on a target database.
- ▌ Migration Helper Init · googlecloudplatform bundleInitialize a new YARA-L rule directory structure and YARA-L rule file from the template.
- ▌ Migration Helper Format · googlecloudplatformTake a source SIEM rule and format its content for readability, then insert it into a YARA-L rule template.
- ▌ Migration Helper Extract · googlecloudplatformExtract unstructured legacy rules from a raw text file and structure them into valid JSON.
- ▌ Migration Helper Validate · googlecloudplatformValidate a YARA-L rule's syntax against the Google SecOps MCP server and self-correct any errors.
- ▌ Migration Helper Recommend · googlecloudplatformRun the recommender script to generate recommendations for SecOps curated/community rules based on custom rules.
- ▌ Migration Helper Author Notes · googlecloudplatformAuthor rule notes, parameters, dependencies, tuning, and testing sections for a YARA-L rule.
- ▌ Migration Helper Generate Log · googlecloudplatformGenerate a raw sample log entry in the original source format that will trigger the migrated YARA-L rule.
- ▌ Migration Helper Migrate Rule · googlecloudplatformFull orchestration workflow to migrate a custom SIEM rule to YARA-L, running all sub-steps sequentially.
- ▌ Migration Helper Generate Rule · googlecloudplatformMigrate a source rule section in a YARA-L file into YARA-L 2.0, adhering to precise Google SecOps schemas.
- ▌ Persona UX · googlecloudplatform bundleAdopts the UX Specialist persona. Focuses on the visual impact, layout stability, and accessibility of the workstation's desktop environment and dashboards.
- ▌ Persona Oss · googlecloudplatform bundleAdopts the Open-Source Expert persona. Ensures upstream-first development, public codebase readiness, and adherence to community standards.
- ▌ Persona Sre · googlecloudplatform bundleAdopts the Site-Reliability Engineer (SRE) persona. Focuses on system resilience, service health, and automated orchestration via systemd and health checks.
- ▌ Persona Swe · googlecloudplatform bundleAdopts the Software Engineer persona. Focuses on functional correctness, structural integrity, and architectural hygiene, including Source Code Versioning History Refactoring.
- ▌ Persona Legal · googlecloudplatform bundleAdopts the Legal Expert persona. Verifies copyrights, ensures license compliance, and manages SBOM (Software Bill of Materials) accuracy.
- ▌ Persona Privacy · googlecloudplatform bundleAdopts the Privacy Expert persona. Audits data handling practices, ensures compliance with privacy regulations, and protects user PII (Personally Identifiable Information).
- ▌ Persona Security · googlecloudplatform bundleAdopts the Security Expert (SEC) persona. Focuses on system hardening, vulnerability auditing, and the protection of sensitive credentials and data.
- ▌ Deploy Workstations · googlecloudplatformAssists Hackathon Admins and Platform Engineers in customizing the Cloud Workstations blueprint. Generates a terraform.tfvars file based on interactive Q&A and runs terraform plan.
- ▌ Persona Agent Manager · googlecloudplatform bundleAdopts the Agent Manager persona. Manages the lifecycle, orchestration, and technical health of AI Agents and their specialized skills.
- ▌ Validate Image Updates · googlecloudplatform bundleEnforces the mandatory sequential validation workflow when a new workstation image is built or the codebase is modified.
- ▌ Update Preflight · googlecloudplatform bundleManages preflight web app UX/UI constraints, layout stability, and the frontend hot-patching deployment process. Use when modifying HTML, CSS, or JS in the apps/workstations/preflight-web/ directory.
- ▌ Create Skill · googlecloudplatform bundleGuides the design, scaffolding, authoring, validation, and registration of new agentic developer skills following Cortex Framework standards and anatomy rules.
- ▌ Query Sap Ddic · googlecloudplatform bundleInspects and dumps SAP table schemas directly from replicated SAP DDIC tables (DD01L, DD02L, DD02T, DD03L, DD04L, DD04T, DD08L) in BigQuery.
- ▌ Create Data Product · googlecloudplatform bundleInstructions on how to create and scaffold a new data product in Cortex Framework V7.
- ▌ Create Python Tests · googlecloudplatform bundleInstructions on how to write Python unit tests to verify a Cortex data product's transformation logic, filters, and field mappings.
- ▌ Generate Er Diagram · googlecloudplatform bundleGenerates Entity-Relationship (ER) diagrams from Cortex data product(s) in dot notation, mermaid diagrams, or draw.io XML formats.
- ▌ Setup Cortex Config · googlecloudplatform bundleGuides the setup and configuration of the Cortex Framework config.yaml file, validating GCP projects, BigQuery datasets, locations, and Dataform target settings.
- ▌ Update Data Product · googlecloudplatform bundleDetailed steps and quality gates for updating or modifying existing data products in Cortex Framework V7.
- ▌ Using Cortex Skills · googlecloudplatform bundleDiscovers and invokes Cortex external agent skills. Use when starting a session or when you need to discover which skill applies to the current task.
- ▌ Validate Data Product · googlecloudplatform bundleInstructions on how to validate an existing or newly created data product in Cortex Framework V7 with mandatory granular status reporting.
- ▌ Data Modeling Standards · googlecloudplatform bundleReference guide for business rules, naming conventions, and data modeling standards enforced during data product development.
- ▌ Build And Deploy Data Product · googlecloudplatform bundleInstructions on how to build and deploy a data product in Cortex Framework V7.
- ▌ Smt Functional Testing · googlecloudplatform bundleFunctionally 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, datastream-to-spanner, spanner-to-sourcedb. Skip entirely for other templates. Don't use for deploying templates to production or debugging a running production pipeline without testing.
- ▌ Smt E2e Dataflow Debugging · googlecloudplatform bundleDebugs logical errors and data discrepancies in Dataflow templates by launching jobs via Terraform and comparing source (e.g. Cloud SQL) vs destination (e.g. Spanner) data. Use ONLY when the pipeline launches and runs to completion (terminal state) but exhibits data discrepancies or logical issues. Do NOT use for debugging template startup/runtime crashes or staging/building new templates.
- ▌ Meta Test Orchestrator · googlecloudplatformTemplate-agnostic Orchestrator Skill for generating and executing exhaustive testing suites for any migration template. It will generate the functional and datatype related test for the source.
- ▌ Add Integ Tests Gcs Spanner Dv · googlecloudplatformSpecific runner skill that creates integration tests for the gcs-spanner-dv (Data Validation) template.
- ▌ Add Source Datatype Integ Test · googlecloudplatformSkill for adding data type integ tests for new source by provided datatype_mapping_matrix.