[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6992Y037TMWAB3Z885V2J83":3,"skill-same:01M6992Y037TMWAB3Z885V2J83":86},{"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":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6992Y037TMWAB3Z885V2J83","gke-ai-troubleshooting-tpu-dynamic-slices-monitoring",null,"Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use for generic GKE cluster node pool creation or standard non-TPU workload management (use gke-basics or gke-cluster-creation instead).","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",24122,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgke-ai-troubleshooting-tpu-dynamic-slices-monitoring\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"gke ai troubleshooting tpu dynamic slices monitoring","tpu","monitoring","gke","troubleshooting","when","containers","generic","slice","for","manifests","states","cluster","resources","creation","basics","node","patching","controller","workload","2026-11-10 10:12:30",false,"---\nname: gke-ai-troubleshooting-tpu-dynamic-slices-monitoring\ndescription: >-\n  Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use for generic GKE cluster node pool creation or standard non-TPU workload management (use gke-basics or gke-cluster-creation instead).\nmetadata:\n  version: \"1.0.1\"\n  category: Containers\n---\n\n# GKE TPU Dynamic Slices Monitoring & Management\n\nMonitors the status of TPU Slice custom resources, troubleshoots provisioning\nfailures, validates workload manifests on dynamic slices, and performs cleanups.\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with\n`CLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:gke-ai-troubleshooting-tpu-dynamic-slices-monitoring)\"`\nand append `agent-skills\u002F1.0 (skill:gke-ai-troubleshooting-tpu-dynamic-slices-monitoring)` to `User-Agent` headers.\n\n## Prerequisites\n\n-   Cloud Logging enabled for the project.\n-   `kubectl` and `gcloud` CLIs configured to access the GKE cluster.\n\n## Diagnostic Workflow\n\n### Step 0: Context Acquisition & Time Window Definition\n\nGather project, cluster, and slice context using cluster tools or the following\nparameters:\n\n-   **Project ID**: `{project_id}` (e.g., `my-gcp-project`)\n-   **Cluster Name**: `{cluster_name}` (e.g., `tpu-cluster`)\n-   **Region\u002FZone**: `{location}` (e.g., `us-central1-a`)\n-   **Slice Name**: `{slice_name}` (e.g., `test-slice`)\n-   **Issue Time**: `{timestamp}` (Optional; default to the last 30 minutes\n    window `[T - 30m]` to `[T + 30m]`)\n\n--------------------------------------------------------------------------------\n\n### Step 1: Describe the Slice Custom Resource [Low Risk]\n\nWhen asked to inspect, troubleshoot, or check a slice status, immediately execute `kubectl describe slice {slice_name}` using available cluster tools to perform the inspection. Parse the resulting `Status.Conditions` output against the condition table below to diagnose the exact state and provide concrete recommendations.\n\n-   **Command**:\n\n    ```bash\n    kubectl describe slice {slice_name}\n    ```\n\n#### State & Reason Analysis\n\nAnalyze the `Status.Conditions` (especially `Type: Ready` and its `Reason` and\n`Status`):\n\n| Lifecycle State \u002F Reason | Meaning | Recommended Action |\n| :--- | :--- | :--- |\n| **`SliceNotCreated`** | GKE Slice Controller is initializing the slice and performing resource checks. | Wait a few minutes and re-check slice status. |\n| **`SliceCreationFailed`** | Prerequisites validation failed (e.g., selected nodes don't exist, nodes are already used by another slice, or the topology doesn't match the number of partitions). | Verify selected nodes exist, are unallocated, and topology matches partition count. |\n| **`ACTIVATING`** | GKE is actively forming and provisioning the TPU slice. | Monitor node provisioning. |\n| **`ACTIVE`** | The TPU slice is successfully formed and ready to host workloads. | Proceed to deploy or check workloads. |\n| **`ACTIVE_DEGRADED`** | The slice is usable, but one or more sub-blocks are degraded. | Monitor workload logs for interconnect or device errors. Check faulty node VMs. |\n| **`FAILED`** | GKE failed to form the TPU slice (e.g., selected nodes are not part of the same reservation block). | Ensure all selected nodes belong to the same reservation block. |\n| **`DEACTIVATING`** | The slice is dismantling (triggered by user deletion or a critical systemic failure). | Wait for dismantling to finish, or patch finalizers if stuck. |\n| **`INCOMPLETE`** | The terminal phase before the Slice CR is deleted from the cluster. | No action required; the resource will be removed shortly. |\n\n#### Provisioning Failure Troubleshooting Checklist\n\nWhen investigating slice creation or provisioning failures (`SliceCreationFailed` or `FAILED`), perform the following verification steps:\n\n1. **Node Existence & Allocation Check**: Verify that the selected TPU nodes exist in the cluster and are not already allocated to another slice (`kubectl get nodes -l cloud.google.com\u002Fgke-tpu-slice`, `kubectl get slice -A`).\n2. **Topology Alignment**: Confirm that the partition count matches the requested topology dimensions (e.g. topology `2x2` requires 4 nodes).\n3. **Reservation Block Alignment Check**: Confirm that all selected TPU nodes belong to the same reservation and reservation block.\n\n--------------------------------------------------------------------------------\n\n### Step 2: Verify Workload Specification [Low Risk]\n\nEnsure workload manifests are configured correctly to target the dynamic slice.\n\n#### 1. Single-Slice Workload Requirements\n\nCheck that the Pod template contains the following annotations and selectors:\n\n-   **Annotations**:\n    -   `cloud.google.com\u002Fgke-tpu-slice-topology: \"{topology}\"` (e.g.,\n        `\"4x4x4\"`)\n-   **NodeSelector**:\n    -   `cloud.google.com\u002Fgke-tpu-topology: \"{topology}\"` (e.g., `\"4x4x4\"`)\n    -   `cloud.google.com\u002Fgke-tpu-accelerator: \"{accelerator_type}\"` (e.g.,\n        `\"tpu7x\"`)\n    -   `cloud.google.com\u002Fgke-tpu-slice: \"{slice_name}\"` (e.g., `\"test-slice\"`)\n\n#### 2. Multi-Slice (JobSet) Workload Requirements\n\nIf deploying a multi-slice JobSet, verify:\n\n-   **JobSet Annotation**:\n    -   `alpha.jobset.sigs.k8s.io\u002Fexclusive-topology:\n        cloud.google.com\u002Fgke-tpu-slice`\n-   **Pod Template Annotations**:\n    -   `cloud.google.com\u002Fgke-tpu-slice-topology: \"{topology}\"`\n-   **Pod Template NodeSelector**:\n    -   `cloud.google.com\u002Fgke-tpu-topology: \"{topology}\"`\n    -   `cloud.google.com\u002Fgke-tpu-accelerator: \"{accelerator_type}\"`\n    -   *Note: Do NOT manually specify `cloud.google.com\u002Fgke-tpu-slice` in the\n        nodeSelector; JobSet handles slice assignment automatically.*\n\n--------------------------------------------------------------------------------\n\n## Resolution & Management Workflow\n\n### Resolution 1: Force Delete a Stuck Slice [High Risk]\n\nIf a slice is stuck in `DEACTIVATING` or deletion hangs indefinitely due to stuck finalizers:\n\n1. **Identify Cause**: Explain that finalizers on the slice resource (`metadata.finalizers`) are preventing Kubernetes from completing resource deletion.\n2. **Propose Resolution**: Propose removing finalizers from the metadata path (`\u002Fmetadata\u002Ffinalizers`) using a JSON patch operation:\n\n    ```bash\n    kubectl patch slice {slice_name} --type json -p='[{\"op\": \"remove\", \"path\": \"\u002Fmetadata\u002Ffinalizers\"}]'\n    ```\n\n3. **Provide Warning**: Explicitly warn the user that removing finalizers bypasses standard controller dismantling and may leave underlying VM, network, or accelerator resources uncleaned or orphaned.\n4. **CRITICAL SAFETY MANDATE**: The response MUST explicitly ask the user for confirmation (e.g. *\"Removing finalizers on `\u002Fmetadata\u002Ffinalizers` via JSON patch is a high-risk operation that may leave orphaned resources. Do you confirm you want to apply this patch to slice `{slice_name}`?\"*) and pause for user confirmation before applying or executing the patch.\n\n--------------------------------------------------------------------------------\n\n### Resolution 2: Disable and Clean Up Slice Controller [High Risk]\n\nIf dynamic slicing needs to be disabled:\n\n1.  **Check for existing Slices**:\n\n    ```bash\n    kubectl get slice -A\n    ```\n\n    Ensure all slices are deleted before disabling the controller.\n\n2.  **Disable Slice Controller via gcloud**:\n\n    ```bash\n    gcloud container clusters update {cluster_name} \\\n        --location={location} \\\n        --no-enable-slice-controller\n    ```\n\n3.  **Delete the Slice CRD**:\n\n    ```bash\n    kubectl delete crd slices.accelerator.gke.io\n    ```\n\n4.  **Clean up Node Labels**: Remove GKE TPU Slice labels from all nodes in the\n    cluster:\n\n    ```bash\n    kubectl label nodes --all cloud.google.com\u002Fgke-tpu-slice- cloud.google.com\u002Fgke-tpu-slice-topology-\n    ```\n\n-   **Safety Rule**: Propose the exact commands and confirm before executing\n    disabling or destructive cleanup steps.\n","# GKE TPU Dynamic Slices Monitoring & Management\n\nMonitors the status of TPU Slice custom resources, troubleshoots provisioning\nfailures, validates workload manifests on dynamic slices, and performs cleanups.\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with\n`CLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:gke-ai-troubleshooting-tpu-dynamic-slices-monitoring)\"`\nand append `agent-skills\u002F1.0 (skill:gke-ai-troubleshooting-tpu-dynamic-slices-monitoring)` to `User-Agent` headers.\n\n## Prerequisites\n\n-   Cloud Logging enabled for the project.\n-   `kubectl` and `gcloud` CLIs configured to access the GKE cluster.\n\n## Diagnostic Workflow\n\n### Step 0: Context Acquisition & Time Window Definition\n\nGather project, cluster, and slice context using cluster tools or the following\nparameters:\n\n-   **Project ID**: `{project_id}` (e.g., `my-gcp-project`)\n-   **Cluster Name**: `{cluster_name}` (e.g., `tpu-cluster`)\n-   **Region\u002FZone**: `{location}` (e.g., `us-central1-a`)\n-   **Slice Name**: `{slice_name}` (e.g., `test-slice`)\n-   **Issue Time**: `{timestamp}` (Optional; default to the last 30 minutes\n    window `[T - 30m]` to `[T + 30m]`)\n\n--------------------------------------------------------------------------------\n\n### Step 1: Describe the Slice Custom Resource [Low Risk]\n\nWhen asked to inspect, troubleshoot, or check a slice status, immediately execute `kubectl describe slice {slice_name}` using available cluster tools to perform the inspection. Parse the resulting `Status.Conditions` output against the condition table below to diagnose the exact state and provide concrete recommendations.\n\n-   **Command**:\n\n    ```bash\n    kubectl describe slice {slice_name}\n    ```\n\n#### State & Reason Analysis\n\nAnalyze the `Status.Conditions` (especially `Type: Ready` and its `Reason` and\n`Status`):\n\n| Lifecycle State \u002F Reason | Meaning | Recommended Action |\n| :--- | :--- | :--- |\n| **`SliceNotCreated`** | GKE Slice Controller is initializing the slice and performing resource checks. | Wait a few minutes and re-check slice status. |\n| **`SliceCreationFailed`** | Prerequisites validation failed (e.g., selected nodes don't exist, nodes are already used by another slice, or the topology doesn't match the number of partitions). | Verify selected nodes exist, are unallocated, and topology matches partition count. |\n| **`ACTIVATING`** | GKE is actively forming and provisioning the TPU slice. | Monitor node provisioning. |\n| **`ACTIVE`** | The TPU slice is successfully formed and ready to host workloads. | Proceed to deploy or check workloads. |\n| **`ACTIVE_DEGRADED`** | The slice is usable, but one or more sub-blocks are degraded. | Monitor workload logs for interconnect or device errors. Check faulty node VMs. |\n| **`FAILED`** | GKE failed to form the TPU slice (e.g., selected nodes are not part of the same reservation block). | Ensure all selected nodes belong to the same reservation block. |\n| **`DEACTIVATING`** | The slice is dismantling (triggered by user deletion or a critical systemic failure). | Wait for dismantling to finish, or patch finalizers if stuck. |\n| **`INCOMPLETE`** | The terminal phase before the Slice CR is deleted from the cluster. | No action required; the resource will be removed shortly. |\n\n#### Provisioning Failure Troubleshooting Checklist\n\nWhen investigating slice creation or provisioning failures (`SliceCreationFailed` or `FAILED`), perform the following verification steps:\n\n1. **Node Existence & Allocation Check**: Verify that the selected TPU nodes exist in the cluster and are not already allocated to another slice (`kubectl get nodes -l cloud.google.com\u002Fgke-tpu-slice`, `kubectl get slice -A`).\n2. **Topology Alignment**: Confirm that the partition count matches the requested topology dimensions (e.g. topology `2x2` requires 4 nodes).\n3. **Reservation Block Alignment Check**: Confirm that all selected TPU nodes belong to the same reservation and reservation block.\n\n--------------------------------------------------------------------------------\n\n### Step 2: Verify Workload Specification [Low Risk]\n\nEnsure workload manifests are configured correctly to target the dynamic slice.\n\n#### 1. Single-Slice Workload Requirements\n\nCheck that the Pod template contains the following annotations and selectors:\n\n-   **Annotations**:\n    -   `cloud.google.com\u002Fgke-tpu-slice-topology: \"{topology}\"` (e.g.,\n        `\"4x4x4\"`)\n-   **NodeSelector**:\n    -   `cloud.google.com\u002Fgke-tpu-topology: \"{topology}\"` (e.g., `\"4x4x4\"`)\n    -   `cloud.google.com\u002Fgke-tpu-accelerator: \"{accelerator_type}\"` (e.g.,\n        `\"tpu7x\"`)\n    -   `cloud.google.com\u002Fgke-tpu-slice: \"{slice_name}\"` (e.g., `\"test-slice\"`)\n\n#### 2. Multi-Slice (JobSet) Workload Requirements\n\nIf deploying a multi-slice JobSet, verify:\n\n-   **JobSet Annotation**:\n    -   `alpha.jobset.sigs.k8s.io\u002Fexclusive-topology:\n        cloud.google.com\u002Fgke-tpu-slice`\n-   **Pod Template Annotations**:\n    -   `cloud.google.com\u002Fgke-tpu-slice-topology: \"{topology}\"`\n-   **Pod Template NodeSelector**:\n    -   `cloud.google.com\u002Fgke-tpu-topology: \"{topology}\"`\n    -   `cloud.google.com\u002Fgke-tpu-accelerator: \"{accelerator_type}\"`\n    -   *Note: Do NOT manually specify `cloud.google.com\u002Fgke-tpu-slice` in the\n        nodeSelector; JobSet handles slice assignment automatically.*\n\n--------------------------------------------------------------------------------\n\n## Resolution & Management Workflow\n\n### Resolution 1: Force Delete a Stuck Slice [High Risk]\n\nIf a slice is stuck in `DEACTIVATING` or deletion hangs indefinitely due to stuck finalizers:\n\n1. **Identify Cause**: Explain that finalizers on the slice resource (`metadata.finalizers`) are preventing Kubernetes from completing resource deletion.\n2. **Propose Resolution**: Propose removing finalizers from the metadata path (`\u002Fmetadata\u002Ffinalizers`) using a JSON patch operation:\n\n    ```bash\n    kubectl patch slice {slice_name} --type json -p='[{\"op\": \"remove\", \"path\": \"\u002Fmetadata\u002Ffinalizers\"}]'\n    ```\n\n3. **Provide Warning**: Explicitly warn the user that removing finalizers bypasses standard controller dismantling and may leave underlying VM, network, or accelerator resources uncleaned or orphaned.\n4. **CRITICAL SAFETY MANDATE**: The response MUST explicitly ask the user for confirmation (e.g. *\"Removing finalizers on `\u002Fmetadata\u002Ffinalizers` via JSON patch is a high-risk operation that may leave orphaned resources. Do you confirm you want to apply this patch to slice `{slice_name}`?\"*) and pause for user confirmation before applying or executing the patch.\n\n--------------------------------------------------------------------------------\n\n### Resolution 2: Disable and Clean Up Slice Controller [High Risk]\n\nIf dynamic slicing needs to be disabled:\n\n1.  **Check for existing Slices**:\n\n    ```bash\n    kubectl get slice -A\n    ```\n\n    Ensure all slices are deleted before disabling the controller.\n\n2.  **Disable Slice Controller via gcloud**:\n\n    ```bash\n    gcloud container clusters update {cluster_name} \\\n        --location={location} \\\n        --no-enable-slice-controller\n    ```\n\n3.  **Delete the Slice CRD**:\n\n    ```bash\n    kubectl delete crd slices.accelerator.gke.io\n    ```\n\n4.  **Clean up Node Labels**: Remove GKE TPU Slice labels from all nodes in the\n    cluster:\n\n    ```bash\n    kubectl label nodes --all cloud.google.com\u002Fgke-tpu-slice- cloud.google.com\u002Fgke-tpu-slice-topology-\n    ```\n\n-   **Safety Rule**: Propose the exact commands and confirm before executing\n    disabling or destructive cleanup steps.\n",{"name":5,"metadata":44,"description":7},{"version":45,"category":46},"1.0.1","Containers","main","bb9b3f464aae37af360d079c1d863524955b0363","skills\u002Fcloud\u002Fgke-ai-troubleshooting-tpu-dynamic-slices-monitoring",2005,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-14 01:51:35",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add google\u002Fskills --skill gke-ai-troubleshooting-tpu-dynamic-slices-monitoring",{"tool":62,"command":63},"bunx","bunx skills add google\u002Fskills --skill gke-ai-troubleshooting-tpu-dynamic-slices-monitoring",{"tool":65,"command":66},"pnpm","pnpm dlx skills add google\u002Fskills --skill gke-ai-troubleshooting-tpu-dynamic-slices-monitoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgke-ai-troubleshooting-tpu-dynamic-slices-monitoring\u002FSKILL.md",true,[70,76,80],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fattribution.md","REFERENCE","参考文档",1996,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgke-ai-troubleshooting-tpu-dynamic-slices-monitoring\u002Freferences\u002Fattribution.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Ffailure_signatures.md",1621,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgke-ai-troubleshooting-tpu-dynamic-slices-monitoring\u002Freferences\u002Ffailure_signatures.md",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fvalidate_queries.sh","SCRIPT","脚本",537,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgke-ai-troubleshooting-tpu-dynamic-slices-monitoring\u002Fscripts\u002Fvalidate_queries.sh",[87,125,155,184,211,236],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":101,"publishedAt":39},"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",[93,98],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000010","后端与接口",[9,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"sign in with google web","sign","with","web","android","go","security","google workspace","google cloud","implement","policy","python","implementing","react","iam","permissions","buttons","secure","manager","identity","architectures","domain","runtimes",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":140,"publishedAt":39},"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",[131,132,135],{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":133,"categoryName":134,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[141,142,9,110,143,144,145,146,147,148,116,149,150,151,35,152,153,121,124,154,24],"dpop adoption","adoption","es6","retry","authentication","flows","challenge","code","browser","loops","at","token","pair","platform",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":167,"publishedAt":39},"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",[161,162,165,166],{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":163,"categoryName":164,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":133,"categoryName":134,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},[168,169,170,171,110,172,173,174,175,176,177,178,179,24,180,181,182,116,183,117],"retrieving developer knowledge","knowledge","developer","MCP","mcp server","official","developer documentation","get","search","local","choice","documents","query","api","across","documentation",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":39},"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",[],[191,192,193,194,195,196,197,198,113,199,200,201,202,203,204,177,205,206,207,24,208,209,182,210],"migrate to rust","rust","migrate","github","memory","performance","directory","safe","ports","llvm","soa","cycle","porting","fix","arrays","infographic","high-performance","URL","architecture","unrelated",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":220,"publishedAt":39},"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",[217,218,219],{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":133,"categoryName":134,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},[9,221,222,223,224,154,225,226,227,228,229,145,230,231,232,178,233,234,24,235,181],"finding google skills","storage","as","messaging","model","trade-offs","provider","answer","fit","catalog","up","decision","use","database","candidate",{"skillNo":237,"name":238,"nameZh":6,"description":239,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":240,"categories":241,"keywords":244,"publishedAt":39},"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",[242,243],{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":133,"categoryName":134,"taxonomyType":96,"taxonomyTypeDesc":97},[245,38,120,34,9,171,246,110,172,247,248,32,249,24,250,181,116,251,252,253,254],"workload manager basics","cli","review","vpc","inspect","you","create","libraries","server","run"]