[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69967Q0WYWG4G2PRRK30B75":3,"skill-same:01M69967Q0WYWG4G2PRRK30B75":107},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M69967Q0WYWG4G2PRRK30B75","google-cloud-solution-agentic-analytics-spark-knowledge-catalog",null,"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).","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",23830,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[32,33,34,9,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"google cloud solution agentic analytics spark knowledge catalog","google cloud","agentic","knowledge","analytics","catalog","spark","cloud","across","code","when","workflows","kit","managed","end","iceberg","types","agent kit","Managed Service","antigravity","2026-11-10 10:12:30",false,"---\nname: google-cloud-solution-agentic-analytics-spark-knowledge-catalog\nmetadata:\n  version: \"1.0.2\"\n  category: MultiProductSolutions\ndescription: >-\n  Discovers requirements and designs an end-to-end governed agentic analytics\n  solution using Knowledge Catalog and Managed Service for Apache Spark\n  (Lightning Engine). Use when designing data science and analytics workflows\n  across structured and unstructured distributed data (including in S3, Azure\n  Blob, AlloyDB, and Iceberg), establishing metadata governance with Knowledge\n  Catalog aspect types, or grounding agentic IDEs (VS Code, Antigravity) by\n  using the Google Cloud Data Agent Kit. Don't use for provisioning borderless\n  data lakehouse infrastructure (use\n  google-cloud-solution-agentic-ai-borderless-data-lakehouse instead).\n---\n\n# Agentic analytics across cloud providers and data types\n\nThis skill provides a workflow to design and implement a governed, secure\npipeline for agentic analytics solution across structured and unstructured data\nthat's distributed across Google Cloud, on-premises systems, and other cloud\nproviders.\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n## Overview of the workflow\n\nThe workflow consists of the following phases:\n*   **Phase 1: Requirements discovery**. Gather detailed requirements related to\n    the cloud workload or use case that the user needs assistance for.\n*   **Phase 2: Solution architecture**. Use the requirements that were gathered\n    in Phase 1 to generate a detailed solution architecture for the cloud\n    workload or use case.\n*   **Phase 3: Solution validation**. Create a plan to validate the generated\n    solution, generate validation instructions and scripts, and run the\n    validation.\n*   **Phase 4: Solution packing and presentation**. Consolidate the generated\n    content and present the solution.\n\n**Important notes about the workflow**:\n*   **Strict phase separation**: During Phase 1 (Requirements discovery), when\n    you ask the user clarifying questions, DON'T recommend, propose, or outline\n    any architectural designs, technical decompositions, cloud services, or\n    component mappings.\n*   **When you can skip certain phases**: If the user's prompt indicates that a\n    specific phase or task in this workflow is already completed or approved\n    (e.g., \"requirements discovery stage is completed\", \"product selection is\n    approved\", or \"architecture is confirmed\"), DON'T repeat that phase or task.\n    Instead, skip directly to the requested task (such as generating the\n    technical decomposition, recommending products, or compiling the solution\n    guide).\n\n## Phase 1: Requirements discovery and analysis\n\n1.  Request the user to describe the functional requirements (business\n    processes, activities, and use cases) of their workload. Ask the user the\n    following questions, one question at a time:\n    -   What are your primary inventory data sources? Are they unstructured\n        (e.g., PDF flavor recipes, invoices) or structured (e.g., historical\n        sales in Iceberg)?\n    -   Where are these sources hosted? Are they split across AWS S3, Azure\n        Blob, Google Cloud Storage, or databases like AlloyDB?\n    -   How do you manage and federate metadata across your data\n        sources within Google Cloud and in external locations (such as other\n        cloud providers)?\n    -   What are your analytical and computational requirements to join, clean,\n        and run forecast models over large-scale distributed data?\n    -   What types of natural language prompts do your data scientists or\n        operational agents expect to execute in their agentic IDE (VS Code or\n        Antigravity IDE)?\n2.  Request the user to describe the non-functional requirements of their\n    workload.\n\n    The following are examples of questions you can ask to gather non-functional\n    requirements:\n    -   **Security, privacy, and compliance**: What data privacy rules,\n        regulatory compliance (e.g., GDPR, HIPAA), or data governance\n        requirements must the system adhere to?\n    -   **Reliability**: What are your uptime, high-availability,\n        fault-tolerance, and disaster recovery objectives (RTO\u002FRPO)?\n    -   **Performance**: What target query latencies and SLA expectations does\n        your workload require?\n    -   **Operations**: What operational monitoring metrics do your data\n        scientists and engineers need?\n    -   **Cost & Sustainability**: Do you have specific budget constraints and\n        data egress\u002Ftransfer cost requirements?\n3.  Ask the user whether the workload currently runs on other cloud providers or\n    on-premises.\n    *   If the user answers \"yes\", then ask the user to describe the\n        architecture of the current deployment.\n    *   If the user answer \"no\", then proceed to the next step.\n4.  Request the user to describe dependencies, if any, on other workloads,\n    products, or tools. The following are examples of questions that you can\n    ask to get information about the dependencies:\n    *   Do you have any upstream or downstream dependencies on external systems\n        (e.g., identity providers, data curation platforms, CI\u002FCD pipelines, or\n        active data catalogs)?\n    *   Are there any requirements for your general data-engineering software\n        delivery lifecycle (e.g., version control, testing, data quality\n        assurance)? Provide the path to a directory or examples of these\n        artifacts.\n5.  Review the input that the user has provided so far, and check whether there\n    are any ambiguities or contradictions.\n\n    If you identify any ambiguities or contradictions in the requirements that\n    the user has provided (e.g., zero-copy vs copying data to a repository), then\n    do the following for each ambiguity or contradiction that you identify:\n    *   Describe the ambiguity or contradiction (e.g., explain why copying data\n        contradicts the zero-copy requirement and also incurs data-transfer\n        costs).\n    *   Ask the user how they wish to resolve the ambiguity or contradiction.\n        *   If the user delegates the choice to you (e.g., the user replies with\n            \"do what you think is best\" or \"you decide\"), then provide a clear\n            suggestion to resolve the ambiguity or contradiction (e.g., suggest\n            prioritizing zero-copy remote queries), explain your reasoning\n            (e.g., to eliminate multi-cloud fees and data duplication), and ask\n            the user to approve your suggestion.\n\n    **Critical**: Until all the ambiguities and contradictions that you identify\n    are resolved according to the preceding guidance, you must NOT recommend or\n    generate any architecture design, technical decomposition, or Google Cloud\n    product recommendations.\n\n6.  **Important**: DON'T start this step if there are unresolved contradictions\n    or ambiguities from Step 5.\n\n    Generate a technical decomposition of the components of the workload.\n    *   The technical decomposition must break down the solution into logical\n        components.\n    *   The decomposition MUST address role-based security and credentials\n        within the relevant layers.\n    *   The decomposition MUST be organized under the following four layers,\n        which represent a standard architectural pattern for agentic analytics\n        solutions, flowing from user interaction through data context and\n        governance to core data processing:\n        *   **User-interaction layer (IDE)**: e.g., agentic development\n            environment.\n        *   **Grounding and trusted data**: e.g., foundation model, MCP servers,\n            and data warehouse in the cloud.\n        *   **Metadata curation**: e.g., metadata scanning.\n        *   **Data processing and analytics**: e.g., analytics workflows, Spark\n            data processing, and external data stores.\n7.  Request the user to approve the generated technical decomposition.\n8.  If the user requests changes, then generate an updated technical\n    decomposition.\n9.  Repeat steps 5 through 8 until the user approves the generated technical\n    decomposition.\n10. After the user approves the technical decomposition, proceed to Phase 2.\n    **Important**: Don't proceed to the next phase until the user approves the\n    generated technical decomposition of the workload.\n\n## Phase 2: Solution architecture\n\n### Ground all generated content\n\nFor each task in this phase, to ensure that the generated content aligns with\nthe latest and official Google Cloud guidance, ground the generated content by\nusing the following resources:\n*   Google Developer Knowledge MCP server\n    *   Instructions to connect to the MCP Server:\n        https:\u002F\u002Fdevelopers.google.com\u002Fknowledge\u002Fmcp.md.txt\n    *   Server: https:\u002F\u002Fdeveloperknowledge.googleapis.com\u002Fmcp\n        *   Tools:\n            *   `developerknowledge:search_documents`\n            *   `developerknowledge:get_documents`\n            *   `developerknowledge:answer_query`\n*   Relevant skills from https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\n*   Official Google Cloud documentation, including the following:\n    *   Reference architecture for agentic cross-cloud analytics workflows\n        across multi-cloud data lakes, structured data warehouses, and\n        unstructured data stores:\n        https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fagentic-ai-cross-cloud-analytics.md.txt\n    *   Decision-making guides for the products and topics that are relevant to\n        the workload:\n        https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-architecture\u002Freferences\u002Fdecision-making-guides.md\n    *   Best-practices guides for the products and topics that are relevant to\n        the workload:\n        https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-architecture\u002Freferences\u002Fbest-practices-guides.md\n\n### Task 2.1: Identify Google Cloud products and features required for the workload.\n\n1.  For each component in the confirmed technical decomposition, identify the\n    appropriate Google Cloud products and features, based on the guidance in the\n    following resources and adjusted suitably based on the approved technical\n    decomposition:\n    -   `references\u002Fproduct-selection-guidance.md`\n    -   `https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-architecture\u002Freferences\u002Fdecision-making-guides.md`\n2.  Present the generated product recommendations and ask the user to approve\n    the recommendations.\n3.  If the user requests changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user approves the product recommendations.\n5.  After the user approves the product recommendations, proceed to Task 2.2.\n\n### Task 2.2: Generate an architecture diagram.\n\n1.  Generate an architecture diagram in Mermaid format:\n    https:\u002F\u002Fgithub.com\u002Fmermaid-js\u002Fmermaid.\n2.  Present the generated diagram to the user and ask the user to approve the\n    architecture diagram.\n3.  If the user requests changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user approves the architecture diagram.\n5.  After the user approves the architecture diagram, proceed to Task 2.3.\n\n### Task 2.3: Generate an architecture description.\n\n1.  Generate a description that explains the purpose of each component, the\n    relationships between the components, and the task flow or data flow.\n2.  Present the generated architecture description to the user and ask the user\n    to approve the description.\n3.  If the user requests any changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user approves the architecture description.\n5.  After the user approves the architecture description, proceed to Task 2.4.\n\n### Task 2.4: Generate design recommendations.\n\n1.  Generate design recommendations and best practices to optimally configure\n    each component in the architecture based on the workload's requirements.\n\n    **Important**:\n    *   When you generate design recommendations, consider the following:\n        *   Functional requirements that were gathered in Phase 1.\n        *   Non-functional requirements that were gathered in Phase 1.\n    *   Align the generated design recommendations with the recommendations in\n        `references\u002Fdesign-recommendations.md`.\n    *   To generate design recommendations for Knowledge Catalog, use the\n        resources that are listed in\n        `references\u002Fknowledge-catalog-documentation.md`\n    *   To generate guidance for the non-functional requirements, use the\n        following skills:\n        -   `google-cloud-waf-security`\n        -   `google-cloud-waf-reliability`\n        -   `google-cloud-waf-cost-optimization`\n        -   `google-cloud-waf-operational-excellence`\n        -   `google-cloud-waf-performance-optimization`\n        -   `google-cloud-waf-sustainability`\n2.  Present the generated recommendations to the user and ask whether the user\n    needs any changes.\n3.  If the user needs changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user confirms that the generated design\n    recommendations meet their requirements.\n5.  Proceed to Task 2.5.\n\n### Task 2.5: Generate deployment guidance.\n\n1.  Generate deployment guidance, including code and instructions to enable the\n    user to deploy the solution.\n\n    **Important**:\n    *   The guidance must provide steps for deployment prerequisites, including\n        setting up the Google Cloud project, enabling billing, enabling the\n        required APIs, and setting up the required roles and permissions.\n    *   Use the following resources as the technical foundation for the\n        deployment guidance that you generate:\n        -   https:\u002F\u002Fgithub.com\u002Fgemini-cli-extensions\u002Fdata-agent-kit-starter-pack\u002Ftree\u002Fmain\u002Fskills:\n            A plugin that provides a specialized suite of skills and MCP tools\n            to let you use your preferred coding agent to architect complex data\n            pipelines, transform data with dbt, write Spark and BigQuery SQL\n            notebooks, create and troubleshoot Dataflow pipelines, and\n            orchestrate end-to-end workflows across the Google Cloud data\n            ecosystem.\n        -   https:\u002F\u002Fcodelabs.developers.google.com\u002Fnext26\u002Fgen-keynote\u002Fraw-data-forecasting#0:\n            A codelab that provides instructions to use the Data Agent Kit\n            extension to efficiently analyze a cross-cloud data topology from\n            within your preferred agentic development environment.\n        -   https:\u002F\u002Fcodelabs.developers.google.com\u002Fgovernance-context-part1#0: A\n            codelab that provides instructions to build a data foundation in\n            BigQuery, apply rigid metadata tags (Knowledge Catalog Aspects) to\n            differentiate valid data from noise, and use the Gemini CLI to\n            locally test if the LLM strictly follows your governance rules.\n        -   https:\u002F\u002Fdocs.cloud.google.com\u002Fdataplex\u002Fdocs\u002Festablish-foundational-data-context.md.txt:\n            A tutorial that shows how to establish data context in Knowledge\n            Catalog.\n        -   https:\u002F\u002Fdocs.cloud.google.com\u002Fdataplex\u002Fdocs\u002Fingest-custom-sources.md.txt:\n            A guide that explains how to bring information about your unique,\n            custom data sources into Knowledge Catalog.\n2.  Present the generated deployment guidance to the user and ask whether the\n    user needs any changes.\n3.  If the user requests changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user confirms that the generated deployment\n    guidance meets their requirements.\n5.  Proceed to Phase 3.\n\n## Phase 3: Solution validation\n\n1.  Create a plan to validate the generated solution. The plan must outline the\n    steps to verify that the generated solution meets the workload's\n    requirements.\n2.  Present the validation plan to the user and request feedback or approval.\n3.  If the user requests changes, update the plan as required.\n4.  Repeat steps 2 and 3 until the user approves the validation plan.\n5.  Generate scripts or commands using tools like `curl` or `gcloud` to perform\n    the steps in the approved validation plan.\n6.  Request permission from the user to perform the validation checks.\n7.  If the user gives permission, run the validation checks and troubleshoot any\n    deployment issues.\n8.  When all the validation checks pass, proceed to Phase 4.\n\n## Phase 4: Solution packaging and presentation\n\n1.  Consolidate the text artifacts that were generated in Phase 2 and Phase 3\n    into a single Markdown file named `solution-architecture-guide.md`, based on\n    the template in `assets\u002Foutput-template.md`.\n2.  Present the consolidated solution-architecture-guide.md to the user.\n3.  Request the user's permission to write the code files in the user's\n    workspace.\n4.  After the user gives permission, write the code files in the user's\n    workspace.\n\n## Supporting resources\n\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fdata-cloud-extension\u002Fantigravity\u002Ftransform-data.md.txt:\n    Guide to how the Data Agent Kit extension lets you use notebooks for data\n    transformation and analysis.\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fdataplex\u002Fdocs\u002Fuse-cases.md.txt: Use cases for\n    Knowledge Catalog.\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fmanaged-spark\u002Fdocs\u002Fguides\u002Flightning-engine-serverless.md.txt:\n    Guide to accelerating Apache Spark workloads by using Lightning Engine.\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fbigquery\u002Fdocs\u002Fuse-knowledge-catalog.md.txt:\n    Guide to use Knowledge Catalog as a governance and agentic layer for\n    BigQuery.\n","# Agentic analytics across cloud providers and data types\n\nThis skill provides a workflow to design and implement a governed, secure\npipeline for agentic analytics solution across structured and unstructured data\nthat's distributed across Google Cloud, on-premises systems, and other cloud\nproviders.\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read and follow the instructions in\n[Usage Attribution](references\u002Fattribution.md).\n\n## Overview of the workflow\n\nThe workflow consists of the following phases:\n*   **Phase 1: Requirements discovery**. Gather detailed requirements related to\n    the cloud workload or use case that the user needs assistance for.\n*   **Phase 2: Solution architecture**. Use the requirements that were gathered\n    in Phase 1 to generate a detailed solution architecture for the cloud\n    workload or use case.\n*   **Phase 3: Solution validation**. Create a plan to validate the generated\n    solution, generate validation instructions and scripts, and run the\n    validation.\n*   **Phase 4: Solution packing and presentation**. Consolidate the generated\n    content and present the solution.\n\n**Important notes about the workflow**:\n*   **Strict phase separation**: During Phase 1 (Requirements discovery), when\n    you ask the user clarifying questions, DON'T recommend, propose, or outline\n    any architectural designs, technical decompositions, cloud services, or\n    component mappings.\n*   **When you can skip certain phases**: If the user's prompt indicates that a\n    specific phase or task in this workflow is already completed or approved\n    (e.g., \"requirements discovery stage is completed\", \"product selection is\n    approved\", or \"architecture is confirmed\"), DON'T repeat that phase or task.\n    Instead, skip directly to the requested task (such as generating the\n    technical decomposition, recommending products, or compiling the solution\n    guide).\n\n## Phase 1: Requirements discovery and analysis\n\n1.  Request the user to describe the functional requirements (business\n    processes, activities, and use cases) of their workload. Ask the user the\n    following questions, one question at a time:\n    -   What are your primary inventory data sources? Are they unstructured\n        (e.g., PDF flavor recipes, invoices) or structured (e.g., historical\n        sales in Iceberg)?\n    -   Where are these sources hosted? Are they split across AWS S3, Azure\n        Blob, Google Cloud Storage, or databases like AlloyDB?\n    -   How do you manage and federate metadata across your data\n        sources within Google Cloud and in external locations (such as other\n        cloud providers)?\n    -   What are your analytical and computational requirements to join, clean,\n        and run forecast models over large-scale distributed data?\n    -   What types of natural language prompts do your data scientists or\n        operational agents expect to execute in their agentic IDE (VS Code or\n        Antigravity IDE)?\n2.  Request the user to describe the non-functional requirements of their\n    workload.\n\n    The following are examples of questions you can ask to gather non-functional\n    requirements:\n    -   **Security, privacy, and compliance**: What data privacy rules,\n        regulatory compliance (e.g., GDPR, HIPAA), or data governance\n        requirements must the system adhere to?\n    -   **Reliability**: What are your uptime, high-availability,\n        fault-tolerance, and disaster recovery objectives (RTO\u002FRPO)?\n    -   **Performance**: What target query latencies and SLA expectations does\n        your workload require?\n    -   **Operations**: What operational monitoring metrics do your data\n        scientists and engineers need?\n    -   **Cost & Sustainability**: Do you have specific budget constraints and\n        data egress\u002Ftransfer cost requirements?\n3.  Ask the user whether the workload currently runs on other cloud providers or\n    on-premises.\n    *   If the user answers \"yes\", then ask the user to describe the\n        architecture of the current deployment.\n    *   If the user answer \"no\", then proceed to the next step.\n4.  Request the user to describe dependencies, if any, on other workloads,\n    products, or tools. The following are examples of questions that you can\n    ask to get information about the dependencies:\n    *   Do you have any upstream or downstream dependencies on external systems\n        (e.g., identity providers, data curation platforms, CI\u002FCD pipelines, or\n        active data catalogs)?\n    *   Are there any requirements for your general data-engineering software\n        delivery lifecycle (e.g., version control, testing, data quality\n        assurance)? Provide the path to a directory or examples of these\n        artifacts.\n5.  Review the input that the user has provided so far, and check whether there\n    are any ambiguities or contradictions.\n\n    If you identify any ambiguities or contradictions in the requirements that\n    the user has provided (e.g., zero-copy vs copying data to a repository), then\n    do the following for each ambiguity or contradiction that you identify:\n    *   Describe the ambiguity or contradiction (e.g., explain why copying data\n        contradicts the zero-copy requirement and also incurs data-transfer\n        costs).\n    *   Ask the user how they wish to resolve the ambiguity or contradiction.\n        *   If the user delegates the choice to you (e.g., the user replies with\n            \"do what you think is best\" or \"you decide\"), then provide a clear\n            suggestion to resolve the ambiguity or contradiction (e.g., suggest\n            prioritizing zero-copy remote queries), explain your reasoning\n            (e.g., to eliminate multi-cloud fees and data duplication), and ask\n            the user to approve your suggestion.\n\n    **Critical**: Until all the ambiguities and contradictions that you identify\n    are resolved according to the preceding guidance, you must NOT recommend or\n    generate any architecture design, technical decomposition, or Google Cloud\n    product recommendations.\n\n6.  **Important**: DON'T start this step if there are unresolved contradictions\n    or ambiguities from Step 5.\n\n    Generate a technical decomposition of the components of the workload.\n    *   The technical decomposition must break down the solution into logical\n        components.\n    *   The decomposition MUST address role-based security and credentials\n        within the relevant layers.\n    *   The decomposition MUST be organized under the following four layers,\n        which represent a standard architectural pattern for agentic analytics\n        solutions, flowing from user interaction through data context and\n        governance to core data processing:\n        *   **User-interaction layer (IDE)**: e.g., agentic development\n            environment.\n        *   **Grounding and trusted data**: e.g., foundation model, MCP servers,\n            and data warehouse in the cloud.\n        *   **Metadata curation**: e.g., metadata scanning.\n        *   **Data processing and analytics**: e.g., analytics workflows, Spark\n            data processing, and external data stores.\n7.  Request the user to approve the generated technical decomposition.\n8.  If the user requests changes, then generate an updated technical\n    decomposition.\n9.  Repeat steps 5 through 8 until the user approves the generated technical\n    decomposition.\n10. After the user approves the technical decomposition, proceed to Phase 2.\n    **Important**: Don't proceed to the next phase until the user approves the\n    generated technical decomposition of the workload.\n\n## Phase 2: Solution architecture\n\n### Ground all generated content\n\nFor each task in this phase, to ensure that the generated content aligns with\nthe latest and official Google Cloud guidance, ground the generated content by\nusing the following resources:\n*   Google Developer Knowledge MCP server\n    *   Instructions to connect to the MCP Server:\n        https:\u002F\u002Fdevelopers.google.com\u002Fknowledge\u002Fmcp.md.txt\n    *   Server: https:\u002F\u002Fdeveloperknowledge.googleapis.com\u002Fmcp\n        *   Tools:\n            *   `developerknowledge:search_documents`\n            *   `developerknowledge:get_documents`\n            *   `developerknowledge:answer_query`\n*   Relevant skills from https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\n*   Official Google Cloud documentation, including the following:\n    *   Reference architecture for agentic cross-cloud analytics workflows\n        across multi-cloud data lakes, structured data warehouses, and\n        unstructured data stores:\n        https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fagentic-ai-cross-cloud-analytics.md.txt\n    *   Decision-making guides for the products and topics that are relevant to\n        the workload:\n        https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-architecture\u002Freferences\u002Fdecision-making-guides.md\n    *   Best-practices guides for the products and topics that are relevant to\n        the workload:\n        https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-architecture\u002Freferences\u002Fbest-practices-guides.md\n\n### Task 2.1: Identify Google Cloud products and features required for the workload.\n\n1.  For each component in the confirmed technical decomposition, identify the\n    appropriate Google Cloud products and features, based on the guidance in the\n    following resources and adjusted suitably based on the approved technical\n    decomposition:\n    -   `references\u002Fproduct-selection-guidance.md`\n    -   `https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-architecture\u002Freferences\u002Fdecision-making-guides.md`\n2.  Present the generated product recommendations and ask the user to approve\n    the recommendations.\n3.  If the user requests changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user approves the product recommendations.\n5.  After the user approves the product recommendations, proceed to Task 2.2.\n\n### Task 2.2: Generate an architecture diagram.\n\n1.  Generate an architecture diagram in Mermaid format:\n    https:\u002F\u002Fgithub.com\u002Fmermaid-js\u002Fmermaid.\n2.  Present the generated diagram to the user and ask the user to approve the\n    architecture diagram.\n3.  If the user requests changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user approves the architecture diagram.\n5.  After the user approves the architecture diagram, proceed to Task 2.3.\n\n### Task 2.3: Generate an architecture description.\n\n1.  Generate a description that explains the purpose of each component, the\n    relationships between the components, and the task flow or data flow.\n2.  Present the generated architecture description to the user and ask the user\n    to approve the description.\n3.  If the user requests any changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user approves the architecture description.\n5.  After the user approves the architecture description, proceed to Task 2.4.\n\n### Task 2.4: Generate design recommendations.\n\n1.  Generate design recommendations and best practices to optimally configure\n    each component in the architecture based on the workload's requirements.\n\n    **Important**:\n    *   When you generate design recommendations, consider the following:\n        *   Functional requirements that were gathered in Phase 1.\n        *   Non-functional requirements that were gathered in Phase 1.\n    *   Align the generated design recommendations with the recommendations in\n        `references\u002Fdesign-recommendations.md`.\n    *   To generate design recommendations for Knowledge Catalog, use the\n        resources that are listed in\n        `references\u002Fknowledge-catalog-documentation.md`\n    *   To generate guidance for the non-functional requirements, use the\n        following skills:\n        -   `google-cloud-waf-security`\n        -   `google-cloud-waf-reliability`\n        -   `google-cloud-waf-cost-optimization`\n        -   `google-cloud-waf-operational-excellence`\n        -   `google-cloud-waf-performance-optimization`\n        -   `google-cloud-waf-sustainability`\n2.  Present the generated recommendations to the user and ask whether the user\n    needs any changes.\n3.  If the user needs changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user confirms that the generated design\n    recommendations meet their requirements.\n5.  Proceed to Task 2.5.\n\n### Task 2.5: Generate deployment guidance.\n\n1.  Generate deployment guidance, including code and instructions to enable the\n    user to deploy the solution.\n\n    **Important**:\n    *   The guidance must provide steps for deployment prerequisites, including\n        setting up the Google Cloud project, enabling billing, enabling the\n        required APIs, and setting up the required roles and permissions.\n    *   Use the following resources as the technical foundation for the\n        deployment guidance that you generate:\n        -   https:\u002F\u002Fgithub.com\u002Fgemini-cli-extensions\u002Fdata-agent-kit-starter-pack\u002Ftree\u002Fmain\u002Fskills:\n            A plugin that provides a specialized suite of skills and MCP tools\n            to let you use your preferred coding agent to architect complex data\n            pipelines, transform data with dbt, write Spark and BigQuery SQL\n            notebooks, create and troubleshoot Dataflow pipelines, and\n            orchestrate end-to-end workflows across the Google Cloud data\n            ecosystem.\n        -   https:\u002F\u002Fcodelabs.developers.google.com\u002Fnext26\u002Fgen-keynote\u002Fraw-data-forecasting#0:\n            A codelab that provides instructions to use the Data Agent Kit\n            extension to efficiently analyze a cross-cloud data topology from\n            within your preferred agentic development environment.\n        -   https:\u002F\u002Fcodelabs.developers.google.com\u002Fgovernance-context-part1#0: A\n            codelab that provides instructions to build a data foundation in\n            BigQuery, apply rigid metadata tags (Knowledge Catalog Aspects) to\n            differentiate valid data from noise, and use the Gemini CLI to\n            locally test if the LLM strictly follows your governance rules.\n        -   https:\u002F\u002Fdocs.cloud.google.com\u002Fdataplex\u002Fdocs\u002Festablish-foundational-data-context.md.txt:\n            A tutorial that shows how to establish data context in Knowledge\n            Catalog.\n        -   https:\u002F\u002Fdocs.cloud.google.com\u002Fdataplex\u002Fdocs\u002Fingest-custom-sources.md.txt:\n            A guide that explains how to bring information about your unique,\n            custom data sources into Knowledge Catalog.\n2.  Present the generated deployment guidance to the user and ask whether the\n    user needs any changes.\n3.  If the user requests changes, then make the required changes.\n4.  Repeat steps 2 and 3 until the user confirms that the generated deployment\n    guidance meets their requirements.\n5.  Proceed to Phase 3.\n\n## Phase 3: Solution validation\n\n1.  Create a plan to validate the generated solution. The plan must outline the\n    steps to verify that the generated solution meets the workload's\n    requirements.\n2.  Present the validation plan to the user and request feedback or approval.\n3.  If the user requests changes, update the plan as required.\n4.  Repeat steps 2 and 3 until the user approves the validation plan.\n5.  Generate scripts or commands using tools like `curl` or `gcloud` to perform\n    the steps in the approved validation plan.\n6.  Request permission from the user to perform the validation checks.\n7.  If the user gives permission, run the validation checks and troubleshoot any\n    deployment issues.\n8.  When all the validation checks pass, proceed to Phase 4.\n\n## Phase 4: Solution packaging and presentation\n\n1.  Consolidate the text artifacts that were generated in Phase 2 and Phase 3\n    into a single Markdown file named `solution-architecture-guide.md`, based on\n    the template in `assets\u002Foutput-template.md`.\n2.  Present the consolidated solution-architecture-guide.md to the user.\n3.  Request the user's permission to write the code files in the user's\n    workspace.\n4.  After the user gives permission, write the code files in the user's\n    workspace.\n\n## Supporting resources\n\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fdata-cloud-extension\u002Fantigravity\u002Ftransform-data.md.txt:\n    Guide to how the Data Agent Kit extension lets you use notebooks for data\n    transformation and analysis.\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fdataplex\u002Fdocs\u002Fuse-cases.md.txt: Use cases for\n    Knowledge Catalog.\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fmanaged-spark\u002Fdocs\u002Fguides\u002Flightning-engine-serverless.md.txt:\n    Guide to accelerating Apache Spark workloads by using Lightning Engine.\n*   https:\u002F\u002Fdocs.cloud.google.com\u002Fbigquery\u002Fdocs\u002Fuse-knowledge-catalog.md.txt:\n    Guide to use Knowledge Catalog as a governance and agentic layer for\n    BigQuery.\n",{"name":5,"metadata":57,"description":7},{"version":58,"category":59},"1.0.2","MultiProductSolutions","main","64d010629e61e4a7d59fc21e042362f370b5888b","skills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog",1991,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-11 03:08:50",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add google\u002Fskills --skill google-cloud-solution-agentic-analytics-spark-knowledge-catalog",{"tool":75,"command":76},"bunx","bunx skills add google\u002Fskills --skill google-cloud-solution-agentic-analytics-spark-knowledge-catalog",{"tool":78,"command":79},"pnpm","pnpm dlx skills add google\u002Fskills --skill google-cloud-solution-agentic-analytics-spark-knowledge-catalog","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002FSKILL.md",true,[83,89,95,99,103],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"assets\u002Foutput-template.md","ASSET","资产文件",5290,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002Fassets\u002Foutput-template.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fattribution.md","REFERENCE","参考文档",2037,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002Freferences\u002Fattribution.md",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fdesign-recommendations.md",2401,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002Freferences\u002Fdesign-recommendations.md",{"path":100,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fknowledge-catalog-documentation.md",2266,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002Freferences\u002Fknowledge-catalog-documentation.md",{"path":104,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fproduct-selection-guidance.md",3396,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-analytics-spark-knowledge-catalog\u002Freferences\u002Fproduct-selection-guidance.md",[108,143,171,196,223,247],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":120,"publishedAt":52},"01M6998S2EZKD3GEJ7F943RZTE","sign-in-with-google-web","Implement, configure, and secure Sign In With Google (SiwG) using Google Identity Services (GIS \u002F `https:\u002F\u002Faccounts.google.com\u002Fgsi\u002Fclient`) across web architectures. Use when creating Google sign-in buttons, implementing Google One Tap with FedCM, integrating GIS in React\u002FNext.js\u002FAngular\u002FHTML, verifying ID tokens on backend runtimes (Python\u002FNode.js\u002FGo\u002FJava), enforcing Google Workspace domain restrictions (`hd`), securing client-side ID tokens via WebCrypto nonces or encrypted IndexedDB, embedding in cross-origin iframes via the Intermediate Iframe API (`https:\u002F\u002Faccounts.google.com\u002Fgsi\u002Fintermediate`), configuring Content Security Policy (CSP), COOP, and Permissions Policy (`identity-credentials-get`) headers, or handling sign-out and revocation. Don't use for legacy Google Sign-In (`gapi.auth2`), Google Cloud IAM service accounts, or Android\u002FiOS native Credential Manager.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fidentity\u002Fsign-in-with-google-web\u002FSKILL.md",[114,117],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[9,121,122,123,124,125,126,127,128,33,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"sign in with google web","sign","with","web","android","go","security","google workspace","implement","policy","python","implementing","react","iam","permissions","buttons","secure","manager","identity","architectures","domain","runtimes",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":156,"publishedAt":52},"01M6998PHPDCAD684VW5WRG83D","dpop-adoption","Implement and debug OAuth 2.0 DPoP (RFC 9449) refresh token sender-constraining for WebCrypto, Node.js ES6, and browser runtimes integrating with Google's OAuth platform. Use when configuring non-extractable asymmetric key pairs (P-256), generating DPoP Proof JWTs for authorization code exchange and token refresh, or handling 400 use_dpop_nonce challenge retry loops at oauth2.googleapis.com\u002Ftoken. Don't use for unconstrained OAuth 2.0 flows (where refresh tokens are not bound to a client key pair), or for Google Cloud IAM \u002F service account authentication.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fidentity\u002Fdpop-adoption\u002FSKILL.md",[149,150,153],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":154,"categoryName":155,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师",[157,158,9,33,159,160,161,162,163,41,134,164,165,166,167,168,169,139,142,170,42],"dpop adoption","adoption","es6","retry","authentication","flows","challenge","browser","loops","at","node","token","pair","platform",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":181,"publishedAt":52},"01M6998M72TC73EEAQH4XC7EXW","retrieving-developer-knowledge","Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI\u002FGemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms. Integrates with the Developer Knowledge MCP server (search_documents, get_documents, answer_query) or the Developer Knowledge REST API fallback. Use when searching for gcloud CLI commands, API syntax, IAM permissions, official documentation, architectural comparisons, or product choice overviews. Don't use for local filesystem lookups or non-Google documentation.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Fretrieving-developer-knowledge\u002FSKILL.md",[177,178,179,180],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":154,"categoryName":155,"taxonomyType":29,"taxonomyTypeDesc":30},[182,35,183,184,33,185,186,187,188,189,190,191,192,42,193,194,40,134,195,135],"retrieving developer knowledge","developer","MCP","mcp server","official","developer documentation","get","search","local","choice","documents","query","api","documentation",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":202,"publishedAt":52},"01M6998J2CZEXS9BES9S3WWFKC","migrate-to-rust","Clones, analyzes, plans, and migrates legacy codebases (C++, Fortran, Java, Python, C, Shell) from a GitHub URL or local directory to a modern, high-performance, deterministic, 100% Safe Rust architecture, tracking live telemetry across every task bucket, test failure\u002Ffix cycle, and Profile-Guided Optimization (PGO) stage, and producing a first-person AI storytelling report and interactive HTML infographic. Use when migrating a GitHub repository or local codebase to Rust, porting legacy C++, Fortran, Python, or Java workloads to memory-safe Rust, designing Struct-of-Arrays (SoA) or SIMD Rust architectures, or optimizing Rust ports with LLVM PGO. Don't use for unrelated non-Rust refactoring or single-line syntax questions.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Fmigrate-to-rust\u002FSKILL.md",[],[203,204,205,206,207,208,209,210,131,211,212,213,214,215,216,190,217,218,219,42,220,221,40,222],"migrate to rust","rust","migrate","github","memory","performance","directory","safe","ports","llvm","soa","cycle","porting","fix","arrays","infographic","high-performance","URL","architecture","unrelated",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":232,"publishedAt":52},"01M6998GCC3K29WZ82KXMB9E02","finding-google-skills","Google platform decision and setup guidance, loaded on demand from Google's skill catalog. Use when a developer is choosing or setting up part of their stack, such as where to run a service, a database, storage, messaging, authentication, analytics, ads, or AI model serving, and a Google product is a reasonable candidate - whether or not a vendor is named - or when a request names a Google product or API. Brings in the matching Google skill so the answer can weigh Google options, their trade-offs, and when they are not the right fit. Skip when the stack is already settled on another provider and no Google product is named, or the task involves no platform choice.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Ffinding-google-skills\u002FSKILL.md",[229,230,231],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":154,"categoryName":155,"taxonomyType":29,"taxonomyTypeDesc":30},[9,233,234,235,236,170,237,238,239,240,241,161,37,242,243,191,244,245,42,246,194],"finding google skills","storage","as","messaging","model","trade-offs","provider","answer","fit","up","decision","use","database","candidate",{"skillNo":248,"name":249,"nameZh":6,"description":250,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":251,"categories":252,"keywords":255,"publishedAt":52},"01M6998DWNHTH0BS6W1CY8ZXMP","workload-manager-basics","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.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fworkload-manager-basics\u002FSKILL.md",[253,254],{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},[256,257,138,258,9,184,259,33,185,260,261,262,263,42,264,194,134,265,266,267,268],"workload manager basics","workload","basics","cli","review","vpc","resources","inspect","you","create","libraries","server","run"]