[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69965CE51BD0YBNY263CMA5":3,"skill-same:01M69965CE51BD0YBNY263CMA5":102},{"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":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M69965CE51BD0YBNY263CMA5","google-cloud-solution-agentic-ai-data-science-workflow",null,"Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices. Use when architecting multi-product solutions for agent-based data analytics or ML workloads. Don't use for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",23908,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow\u002FSKILL.md",[18,23,28],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",{"categoryNo":29,"categoryName":30,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师",[9,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"agentic","agentic ai","google cloud","google cloud solution agentic ai data science workflow","workflow","data science","cloud","data","science","when","writing","for","reviews","general","use","best practices","code","ml","architecture","2026-11-10 10:12:30",false,"---\nname: google-cloud-solution-agentic-ai-data-science-workflow\nmetadata:\n  version: \"1.0.3\"\n  category: MultiProductSolutions\ndescription: >-\n  Designs a tailored multi-product agentic data science\n  architecture on Google Cloud that incorporates opinionated best practices. Use\n  when architecting multi-product solutions for agent-based data analytics or ML\n  workloads. Don't use for simple queries, non-agentic pipelines, general cloud\n  reviews, or writing agent code.\n---\n\n# Data science workflow with AI agents solution\n\nThis skill guides agents through the workflow to design and implement a\ntailored multi-product solution in the cloud for a given workload, use case, or\nrequirement.\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## Workflow\n\nThe solution design and implementation workflow consists of the following\nphases:\n\n- **Phase 1: Requirements discovery and analysis**: Analyze the workload's\n  requirements, constraints, dependencies, and current state.\n- **Phase 2: Solution design**: Build a technology stack, architecture, and\n  deployment configuration for the workload based on Google Cloud design best\n  practices and recommendations.\n- **Phase 3: Implementation plan**: Generate automation and instructions to\n  deploy the solution.\n- **Phase 4: Solution validation**: Validate that the deployment meets the\n  requirements of the workload.\n\n## Product Renaming & Terminology\n\nWhen generating solution designs, architecture diagrams, and documentation,\ncheck the latest Google Cloud documentation for the most up-to-date product\nnames. The table below provides examples of name mappings to be aware of. Note\nthat underlying APIs, Terraform resources, and IAM roles may retain their legacy\nidentifiers.\n\n| Legacy Name | Updated Name |\n| :--- | :--- |\n| Vertex AI | Gemini Enterprise Agent Platform |\n| Vertex AI Agent Engine | Agent Runtime |\n\n### Phase 1: Requirements discovery and analysis\n\n- [ ] **Step 1: Discover requirements**: Understand the functional and\n  non-functional requirements, business goals, and current state (if any) of the\n  workload by asking clarifying questions. You must halt and wait for the user\n  to answer these questions before proceeding to the **Identify components**\n  step. Use the following questions to guide this requirements discovery\n  process:\n   - What data sources and data types do you need to access and analyze?\n   - Who are the target end users, and what network access model do you require?\n   - What types of user queries or analytical requests do you expect end users\n     to submit to the system?\n   - What performance, security, or governance constraints apply?\n\n- [ ] **Step 2: Identify components**: Only after the user has responded to the\n  clarifying questions in the **Discover requirements** step, analyze their\n  responses to identify the components of the workload and their relationships.\n  Also identify any cross-cloud, hybrid, or on-premises components that the\n  solution needs to integrate with.\n\n- [ ] **Step 3: Generate component decomposition**: Generate a technical\n  decomposition outlining the technical components of the workload and their\n  relationships.\n\n- [ ] **Step 4: Ask for confirmation**: Present the technical decomposition and\n  ask the user to confirm if it matches their workload requirements. Do not\n  proceed to Phase 2 until this is confirmed.\n\n- [ ] **Step 5: Iterate**: If the user requests changes, generate an updated\n   technical decomposition and ask for confirmation again. Continue iterating\n   until the user explicitly confirms the decomposition.\n\n### Phase 2: Solution design\n\n- [ ] **Step 1: Retrieve relevant Google Cloud documentation**: Use available\n  search or fetch tools to read the content of the following Google Cloud\n  documentation to ground the guidance that you generate in the remaining steps\n  of this phase before proceeding.\n   - [Data science workflow with AI agents](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fagentic-ai-data-science.md.txt)\n   - [Multi-agent AI system in Google Cloud](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fmultiagent-ai-system.md.txt)\n   - [Choose your agentic AI architecture components](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fchoose-agentic-ai-architecture-components.md.txt)\n   - [Choose a design pattern for your agentic AI system](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fchoose-design-pattern-agentic-ai-system.md.txt)\n\n- [ ] **Step 2: Define agentic AI design pattern**: Select the appropriate agent\n  design pattern and agent breakdown based on the workload requirements:\n   - **Recommended primary pattern**: Coordinator pattern.\n   - **Alternative patterns**:\n     - *Single-agent pattern*: For simpler workloads scoped to a single data\n       source and direct tool use without multi-agent orchestration overhead.\n     - *Sequential or parallel pattern*: For deterministic data processing\n       pipelines with predefined, non-adaptive execution steps or concurrent\n       data gathering.\n     - *Review and critique pattern*: For complex or high-stakes data science\n       tasks that require dedicated critic loops.\n\n- [ ] **Step 3: Map components to Google Cloud products**: For each component in\n  the confirmed technical decomposition and agentic design pattern, identify the\n  appropriate Google Cloud products and features, based on the guidelines in\n  \u002Freferences\u002Fproduct-mapping.md.\n\n- [ ] **Step 4: Create architecture diagram**: Create an architecture diagram\n  that shows the components, their relationships, and data\u002Fcontrol flows.\n   - The diagram must be in the Mermaid format:\n     https:\u002F\u002Fgithub.com\u002Fmermaid-js\u002Fmermaid.\n   - The diagram must use component labels and groupings consistent with the\n     official Google Cloud architecture icons.\n\n- [ ] **Step 5: Generate design recommendations**: Generate design guidance\n  based on the guidelines in \u002Freferences\u002Fdesign-recommendations.md.\n\n- [ ] **Step 6: Draft solution architecture**: Compile the requirements,\n  technical decomposition, product mapping, architecture diagram, and design\n   recommendations into a single Markdown file named\n   `solution-architecture-guide.md`, based on the template in\n   `\u002Fassets\u002Foutput-template.md`.\n\n- [ ] **Step 7: Request review**: Present the generated solution architecture to\n  the user and request their feedback or approval. You must halt and wait for\n  the user's explicit approval before proceeding to Phase 3.\n\n- [ ] **Step 8: Iterate**: If the user requests changes, then generate an\n  updated solution architecture and repeat steps 2-7 in this phase until the\n  user explicitly approves the solution architecture.\n\n### Phase 3: Implementation plan\n\n- [ ] **Step 1: Retrieve relevant implementation resources**:\n   - [Stateful Data Science Agent on Agent Engine](https:\u002F\u002Fcodelabs.developers.google.com\u002Fnext26\u002Fadk-deploy-scale)\n   - [Build and deploy an AI agent to Cloud Run using ADK](https:\u002F\u002Fdocs.cloud.google.com\u002Frun\u002Fdocs\u002Fai\u002Fbuild-and-deploy-ai-agents\u002Fdeploy-adk-agent.md.txt)\n   - [Use AlloyDB with agents](https:\u002F\u002Fdocs.cloud.google.com\u002Falloydb\u002Fdocs\u002Fconnect-ide-using-mcp-toolbox.md.txt)\n   - [MCP Toolbox for Databases Configuration](https:\u002F\u002Fmcp-toolbox.dev\u002Fdocumentation\u002Fconfiguration\u002F)\n   - [Agents CLI reference](https:\u002F\u002Fgoogle.github.io\u002Fagents-cli\u002Fcli\u002F)\n\n   _Important_: Use these resources as the technical foundation for the IaC and\n   deployment instructions you generate in the remaining steps of this phase.\n\n- [ ] **Step 2: Identify deployment prerequisites**: Document prerequisites for\n  the deployment, including the following:\n   - Projects and billing associations\n   - Required Google Cloud APIs\n   - Required IAM permissions\n   - Any other prerequisites\n\n- [ ] **Step 3: Generate Infrastructure as Code (IaC)**: Generate code, such as\n  Terraform, and deployment scripts to automate the provisioning of the proposed\n  Google Cloud resources.\n  -   Use Agents CLI commands (`agents-cli scaffold\n  create` or `agents-cli scaffold enhance`) to set up the agent application\n  structure, and deploy the agent to Cloud Run.\n\n- [ ] **Step 4: Write deployment instructions**: Draft sequential, step-by-step\n  deployment instructions to execute the IaC and initialize the workload\n  components. Update deployment instructions in\n  `solution-architecture-guide.md`, based on the template in\n  `assets\u002Foutput-template.md`.\n  -   Use the Agents CLI `agents-cli deploy` command (alongside or instead of\n      raw infrastructure\u002Fdeployment scripts) to run the agent deployment.\n\n- [ ] **Step 5: Request review**: Present the generated deployment instructions\n  to the user for feedback and confirmation. You must halt and wait for the\n  user's explicit approval before proceeding to Phase 4.\n\n- [ ] **Step 6: Iterate**: If the user requests changes, then repeat steps 2-5\n  to generate an updated implementation plan that the user requested.\n\n- [ ] **Step 7: Proceed to the next phase**: After the user approves the\n  implementation plan, proceed to Phase 4.\n\n### Phase 4: Solution validation\n\n- [ ] **Step 1: Retrieve relevant verification resources (optional)**: If the\n  resources from Phase 3 are not already in your context, retrieve the same\n  implementation resources as the starting point for the\n  validation checks and verification scripts that you generate in this phase.\n\n- [ ] **Step 2: Define validation checks**: Outline validation steps to verify\n  that the deployed infrastructure meets the workload's requirements:\n  -   **Deployment dry-run**: Commands like `terraform plan` to preview\n    changes. Include instructions to run agent deployment in dry-run mode\n    (e.g., using `agents-cli deploy --dry-run` or `-n`) to preview steps and\n    Terraform executions before pushing to production.\n  -   **Local testing and quality verification**: Recommend using the Agents\n      CLI to run and test agent logic locally (`agents-cli run`) and conduct\n      systematic evaluations (`agents-cli eval run`) to verify agent quality\n      and performance before deploying.\n  -   **Connectivity and routing**: Verification of network paths, load\n      balancer routing, and service endpoints.\n  -   **Security policies**: Verification of restricted access, firewall\n      rules, and IAM enforcement.\n\n- [ ] **Step 3: Generate verification scripts**: Draft lightweight scripts or\n  command-line instructions (e.g. using `curl`, `gcloud`, or `agents-cli`)\n  that the user can run to perform these validation checks.\n\n  -   The validation plan MUST include instructions using the Agents CLI for\n      local runs, evaluations, and post-deployment validation checks (e.g.,\n      `agents-cli run --url \u003Cservice-url>` to test the deployed service\n      endpoint).\n\n- [ ] **Step 4: Compile validation report**: Document the validation steps,\n  verification scripts, and expected outcomes in a single Markdown file.\n\n- [ ] **Step 5: Conduct validation and finalize**: Assist the user in executing\n  the validation checks and troubleshooting any deployment issues. After you\n  validate the solution successfully, request final approval from the user.\n\n- [ ] **Step 6: Iterate**: If the user requests changes, then generate an\n  updated validation plan and repeat the validation drafting and script\n  generation steps in this phase until the user approves the validation plan.\n","# Data science workflow with AI agents solution\n\nThis skill guides agents through the workflow to design and implement a\ntailored multi-product solution in the cloud for a given workload, use case, or\nrequirement.\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## Workflow\n\nThe solution design and implementation workflow consists of the following\nphases:\n\n- **Phase 1: Requirements discovery and analysis**: Analyze the workload's\n  requirements, constraints, dependencies, and current state.\n- **Phase 2: Solution design**: Build a technology stack, architecture, and\n  deployment configuration for the workload based on Google Cloud design best\n  practices and recommendations.\n- **Phase 3: Implementation plan**: Generate automation and instructions to\n  deploy the solution.\n- **Phase 4: Solution validation**: Validate that the deployment meets the\n  requirements of the workload.\n\n## Product Renaming & Terminology\n\nWhen generating solution designs, architecture diagrams, and documentation,\ncheck the latest Google Cloud documentation for the most up-to-date product\nnames. The table below provides examples of name mappings to be aware of. Note\nthat underlying APIs, Terraform resources, and IAM roles may retain their legacy\nidentifiers.\n\n| Legacy Name | Updated Name |\n| :--- | :--- |\n| Vertex AI | Gemini Enterprise Agent Platform |\n| Vertex AI Agent Engine | Agent Runtime |\n\n### Phase 1: Requirements discovery and analysis\n\n- [ ] **Step 1: Discover requirements**: Understand the functional and\n  non-functional requirements, business goals, and current state (if any) of the\n  workload by asking clarifying questions. You must halt and wait for the user\n  to answer these questions before proceeding to the **Identify components**\n  step. Use the following questions to guide this requirements discovery\n  process:\n   - What data sources and data types do you need to access and analyze?\n   - Who are the target end users, and what network access model do you require?\n   - What types of user queries or analytical requests do you expect end users\n     to submit to the system?\n   - What performance, security, or governance constraints apply?\n\n- [ ] **Step 2: Identify components**: Only after the user has responded to the\n  clarifying questions in the **Discover requirements** step, analyze their\n  responses to identify the components of the workload and their relationships.\n  Also identify any cross-cloud, hybrid, or on-premises components that the\n  solution needs to integrate with.\n\n- [ ] **Step 3: Generate component decomposition**: Generate a technical\n  decomposition outlining the technical components of the workload and their\n  relationships.\n\n- [ ] **Step 4: Ask for confirmation**: Present the technical decomposition and\n  ask the user to confirm if it matches their workload requirements. Do not\n  proceed to Phase 2 until this is confirmed.\n\n- [ ] **Step 5: Iterate**: If the user requests changes, generate an updated\n   technical decomposition and ask for confirmation again. Continue iterating\n   until the user explicitly confirms the decomposition.\n\n### Phase 2: Solution design\n\n- [ ] **Step 1: Retrieve relevant Google Cloud documentation**: Use available\n  search or fetch tools to read the content of the following Google Cloud\n  documentation to ground the guidance that you generate in the remaining steps\n  of this phase before proceeding.\n   - [Data science workflow with AI agents](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fagentic-ai-data-science.md.txt)\n   - [Multi-agent AI system in Google Cloud](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fmultiagent-ai-system.md.txt)\n   - [Choose your agentic AI architecture components](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fchoose-agentic-ai-architecture-components.md.txt)\n   - [Choose a design pattern for your agentic AI system](https:\u002F\u002Fdocs.cloud.google.com\u002Farchitecture\u002Fchoose-design-pattern-agentic-ai-system.md.txt)\n\n- [ ] **Step 2: Define agentic AI design pattern**: Select the appropriate agent\n  design pattern and agent breakdown based on the workload requirements:\n   - **Recommended primary pattern**: Coordinator pattern.\n   - **Alternative patterns**:\n     - *Single-agent pattern*: For simpler workloads scoped to a single data\n       source and direct tool use without multi-agent orchestration overhead.\n     - *Sequential or parallel pattern*: For deterministic data processing\n       pipelines with predefined, non-adaptive execution steps or concurrent\n       data gathering.\n     - *Review and critique pattern*: For complex or high-stakes data science\n       tasks that require dedicated critic loops.\n\n- [ ] **Step 3: Map components to Google Cloud products**: For each component in\n  the confirmed technical decomposition and agentic design pattern, identify the\n  appropriate Google Cloud products and features, based on the guidelines in\n  \u002Freferences\u002Fproduct-mapping.md.\n\n- [ ] **Step 4: Create architecture diagram**: Create an architecture diagram\n  that shows the components, their relationships, and data\u002Fcontrol flows.\n   - The diagram must be in the Mermaid format:\n     https:\u002F\u002Fgithub.com\u002Fmermaid-js\u002Fmermaid.\n   - The diagram must use component labels and groupings consistent with the\n     official Google Cloud architecture icons.\n\n- [ ] **Step 5: Generate design recommendations**: Generate design guidance\n  based on the guidelines in \u002Freferences\u002Fdesign-recommendations.md.\n\n- [ ] **Step 6: Draft solution architecture**: Compile the requirements,\n  technical decomposition, product mapping, architecture diagram, and design\n   recommendations into a single Markdown file named\n   `solution-architecture-guide.md`, based on the template in\n   `\u002Fassets\u002Foutput-template.md`.\n\n- [ ] **Step 7: Request review**: Present the generated solution architecture to\n  the user and request their feedback or approval. You must halt and wait for\n  the user's explicit approval before proceeding to Phase 3.\n\n- [ ] **Step 8: Iterate**: If the user requests changes, then generate an\n  updated solution architecture and repeat steps 2-7 in this phase until the\n  user explicitly approves the solution architecture.\n\n### Phase 3: Implementation plan\n\n- [ ] **Step 1: Retrieve relevant implementation resources**:\n   - [Stateful Data Science Agent on Agent Engine](https:\u002F\u002Fcodelabs.developers.google.com\u002Fnext26\u002Fadk-deploy-scale)\n   - [Build and deploy an AI agent to Cloud Run using ADK](https:\u002F\u002Fdocs.cloud.google.com\u002Frun\u002Fdocs\u002Fai\u002Fbuild-and-deploy-ai-agents\u002Fdeploy-adk-agent.md.txt)\n   - [Use AlloyDB with agents](https:\u002F\u002Fdocs.cloud.google.com\u002Falloydb\u002Fdocs\u002Fconnect-ide-using-mcp-toolbox.md.txt)\n   - [MCP Toolbox for Databases Configuration](https:\u002F\u002Fmcp-toolbox.dev\u002Fdocumentation\u002Fconfiguration\u002F)\n   - [Agents CLI reference](https:\u002F\u002Fgoogle.github.io\u002Fagents-cli\u002Fcli\u002F)\n\n   _Important_: Use these resources as the technical foundation for the IaC and\n   deployment instructions you generate in the remaining steps of this phase.\n\n- [ ] **Step 2: Identify deployment prerequisites**: Document prerequisites for\n  the deployment, including the following:\n   - Projects and billing associations\n   - Required Google Cloud APIs\n   - Required IAM permissions\n   - Any other prerequisites\n\n- [ ] **Step 3: Generate Infrastructure as Code (IaC)**: Generate code, such as\n  Terraform, and deployment scripts to automate the provisioning of the proposed\n  Google Cloud resources.\n  -   Use Agents CLI commands (`agents-cli scaffold\n  create` or `agents-cli scaffold enhance`) to set up the agent application\n  structure, and deploy the agent to Cloud Run.\n\n- [ ] **Step 4: Write deployment instructions**: Draft sequential, step-by-step\n  deployment instructions to execute the IaC and initialize the workload\n  components. Update deployment instructions in\n  `solution-architecture-guide.md`, based on the template in\n  `assets\u002Foutput-template.md`.\n  -   Use the Agents CLI `agents-cli deploy` command (alongside or instead of\n      raw infrastructure\u002Fdeployment scripts) to run the agent deployment.\n\n- [ ] **Step 5: Request review**: Present the generated deployment instructions\n  to the user for feedback and confirmation. You must halt and wait for the\n  user's explicit approval before proceeding to Phase 4.\n\n- [ ] **Step 6: Iterate**: If the user requests changes, then repeat steps 2-5\n  to generate an updated implementation plan that the user requested.\n\n- [ ] **Step 7: Proceed to the next phase**: After the user approves the\n  implementation plan, proceed to Phase 4.\n\n### Phase 4: Solution validation\n\n- [ ] **Step 1: Retrieve relevant verification resources (optional)**: If the\n  resources from Phase 3 are not already in your context, retrieve the same\n  implementation resources as the starting point for the\n  validation checks and verification scripts that you generate in this phase.\n\n- [ ] **Step 2: Define validation checks**: Outline validation steps to verify\n  that the deployed infrastructure meets the workload's requirements:\n  -   **Deployment dry-run**: Commands like `terraform plan` to preview\n    changes. Include instructions to run agent deployment in dry-run mode\n    (e.g., using `agents-cli deploy --dry-run` or `-n`) to preview steps and\n    Terraform executions before pushing to production.\n  -   **Local testing and quality verification**: Recommend using the Agents\n      CLI to run and test agent logic locally (`agents-cli run`) and conduct\n      systematic evaluations (`agents-cli eval run`) to verify agent quality\n      and performance before deploying.\n  -   **Connectivity and routing**: Verification of network paths, load\n      balancer routing, and service endpoints.\n  -   **Security policies**: Verification of restricted access, firewall\n      rules, and IAM enforcement.\n\n- [ ] **Step 3: Generate verification scripts**: Draft lightweight scripts or\n  command-line instructions (e.g. using `curl`, `gcloud`, or `agents-cli`)\n  that the user can run to perform these validation checks.\n\n  -   The validation plan MUST include instructions using the Agents CLI for\n      local runs, evaluations, and post-deployment validation checks (e.g.,\n      `agents-cli run --url \u003Cservice-url>` to test the deployed service\n      endpoint).\n\n- [ ] **Step 4: Compile validation report**: Document the validation steps,\n  verification scripts, and expected outcomes in a single Markdown file.\n\n- [ ] **Step 5: Conduct validation and finalize**: Assist the user in executing\n  the validation checks and troubleshooting any deployment issues. After you\n  validate the solution successfully, request final approval from the user.\n\n- [ ] **Step 6: Iterate**: If the user requests changes, then generate an\n  updated validation plan and repeat the validation drafting and script\n  generation steps in this phase until the user approves the validation plan.\n",{"name":5,"metadata":56,"description":7},{"version":57,"category":58},"1.0.3","MultiProductSolutions","main","bb9b3f464aae37af360d079c1d863524955b0363","skills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow",1994,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-12 00:37:41",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add google\u002Fskills --skill google-cloud-solution-agentic-ai-data-science-workflow",{"tool":74,"command":75},"bunx","bunx skills add google\u002Fskills --skill google-cloud-solution-agentic-ai-data-science-workflow",{"tool":77,"command":78},"pnpm","pnpm dlx skills add google\u002Fskills --skill google-cloud-solution-agentic-ai-data-science-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow\u002FSKILL.md",true,[82,88,94,98],{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"assets\u002Foutput-template.md","ASSET","资产文件",7924,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow\u002Fassets\u002Foutput-template.md",{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fattribution.md","REFERENCE","参考文档",2010,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow\u002Freferences\u002Fattribution.md",{"path":95,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fdesign-recommendations.md",4902,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow\u002Freferences\u002Fdesign-recommendations.md",{"path":99,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fproduct-mapping.md",3164,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-solution-agentic-ai-data-science-workflow\u002Freferences\u002Fproduct-mapping.md",[103,138,164,193,219,243],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":115,"publishedAt":51},"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",[109,112],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[9,116,117,118,119,120,121,122,123,34,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"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":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":149,"publishedAt":51},"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",[144,145,146],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":147,"categoryName":148,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[150,151,9,34,152,153,154,155,156,48,129,157,158,159,160,161,162,134,137,163,41],"dpop adoption","adoption","es6","retry","authentication","flows","challenge","browser","loops","at","node","token","pair","platform",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":176,"publishedAt":51},"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",[170,171,174,175],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":172,"categoryName":173,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":147,"categoryName":148,"taxonomyType":26,"taxonomyTypeDesc":27},[177,178,179,180,34,181,182,183,184,185,186,187,188,41,189,190,191,129,192,130],"retrieving developer knowledge","knowledge","developer","MCP","mcp server","official","developer documentation","get","search","local","choice","documents","query","api","across","documentation",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":199,"publishedAt":51},"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",[],[200,201,202,203,204,205,206,207,126,208,209,210,211,212,213,186,214,215,216,41,217,50,191,218],"migrate to rust","rust","migrate","github","memory","performance","directory","safe","ports","llvm","soa","cycle","porting","fix","arrays","infographic","high-performance","URL","unrelated",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":223,"categories":224,"keywords":228,"publishedAt":51},"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",[225,226,227],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":147,"categoryName":148,"taxonomyType":26,"taxonomyTypeDesc":27},[9,229,230,231,232,163,233,234,235,236,237,154,238,239,240,187,46,241,41,242,190],"finding google skills","storage","as","messaging","model","trade-offs","provider","answer","fit","catalog","up","decision","database","candidate",{"skillNo":244,"name":245,"nameZh":6,"description":246,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":247,"categories":248,"keywords":251,"publishedAt":51},"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",[249,250],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[252,253,133,254,9,180,255,34,181,256,257,258,259,41,260,190,129,261,262,263,264],"workload manager basics","workload","basics","cli","review","vpc","resources","inspect","you","create","libraries","server","run"]