[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6996W1JSZ99XVHXWNG14PSB":3,"skill-same:01M6996W1JSZ99XVHXWNG14PSB":140},{"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":53,"linkOnly":54,"markdownContent":55,"markdownBody":56,"frontMatter":57,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":6,"ownerHtmlUrl":68,"ownerBlogUrl":69,"ownerDescription":70,"updatedAt":71,"install":72,"resources":85},"01M6996W1JSZ99XVHXWNG14PSB","google-cloud-storage-basics",null,"Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets. Use when you need to interact with Cloud Storage — set up a Storage MCP server (remote or local Toolbox), create or configure buckets, upload, download, stream, or transfer data, organize objects with folders, generate signed URLs, control access (IAM, ACLs, public access prevention), set storage classes (Standard, Nearline, Coldline, Archive), manage lifecycle and cost, protect data (versioning, CMEK, retention, Bucket Lock, holds, soft delete), host static websites, trigger Pub\u002FSub notifications, mount buckets (gcsfuse), or optimize performance. Covers gcloud storage \u002F gsutil, JSON\u002FXML APIs, client libraries, Terraform, and Cloud Storage MCP servers. Don't use for generic MCP setup that doesn't mention Cloud Storage, other MCP servers, block storage (Persistent Disk), BigQuery, or databases (Cloud SQL, Spanner, Bigtable, Firestore).","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",24235,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[9,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"google cloud","Cloud Storage","google cloud storage basics","storage","cloud","basics","static","MCP","cloud-storage","remote","retention","host","local","objects","databases","up","access","SET","mcp server","performance","gcloud","2026-11-10 10:12:30",false,"---\nname: google-cloud-storage-basics\ndescription: >-\n  Stores, retrieves, and manages data as objects in Cloud Storage on Google\n  Cloud (also known colloquially as GCS) buckets. Use when you need to interact\n  with Cloud Storage — set up a Storage MCP server (remote or local Toolbox),\n  create or configure buckets, upload, download, stream, or transfer data,\n  organize objects with folders, generate signed URLs, control access (IAM,\n  ACLs, public access prevention), set storage classes (Standard, Nearline,\n  Coldline, Archive), manage lifecycle and cost, protect data (versioning,\n  CMEK, retention, Bucket Lock, holds, soft delete), host static websites,\n  trigger Pub\u002FSub notifications, mount buckets (gcsfuse), or optimize\n  performance. Covers gcloud storage \u002F gsutil, JSON\u002FXML APIs, client\n  libraries, Terraform, and Cloud Storage MCP servers. Don't use for generic\n  MCP setup that doesn't mention Cloud Storage, other MCP servers, block\n  storage (Persistent Disk), BigQuery, or databases (Cloud SQL, Spanner,\n  Bigtable, Firestore).\nlicense: Apache-2.0\nmetadata:\n  version: \"1.1.2\"\n  publisher: google\n  tags: \"gcs, storage, cloud-storage, buckets, objects\"\n  category: Storage\n  support_tier: primary\n---\n\n# Cloud Storage Basics\n\nCloud Storage on Google Cloud is a managed service for storing data as\nobjects at any scale. You read and write whole objects rather than querying or\nupdating individual records in place. It stores immutable objects in buckets\nwith strong global consistency, offers multiple storage classes and location\ntypes to balance cost, performance, and availability, and integrates with IAM\nfor fine-grained access control. Cloud Storage serves workloads ranging from\nwebsite content and backups to data lakes and high-throughput AI\u002FML training.\n\n## Tool Execution Priority (MCP Toolbox First)\n\nFollow this execution hierarchy whenever you perform or recommend Cloud Storage\nbucket and object operations:\n\n### 1. Priority 1 — Use `cloud-storage` MCP Tools When Connected\n\nBefore running `gcloud storage` or `curl` in a shell, check your available tools\nfor the `cloud-storage` MCP server (either the local\n[MCP Toolbox](references\u002Fmcp-usage.md) or the Google-hosted remote Cloud Storage\nMCP server). **Whenever a `cloud-storage` MCP tool covers the requested\noperation, call the MCP tool directly instead of shelling out to `gcloud\nstorage` or `curl`.**\n\n**Why MCP first:** MCP tools are built for agents. Each operation is a single\ndirect call, so it runs faster than starting a new `gcloud` command every time,\nand it returns clean results instead of terminal output the agent has to\ninterpret. It also doesn't need the `gcloud` CLI installed and signed in. You\nstay in control, too: you can approve or block each Cloud Storage tool\nindividually in your agent's settings.\n\nOperation              | Tool                                  | Server\n:--------------------- | :------------------------------------ | :-----\nList buckets           | `cloud-storage:list_buckets`          | Both\nBucket metadata        | `cloud-storage:get_bucket_metadata`   | Both\nBucket IAM policy      | `cloud-storage:get_bucket_iam_policy` | Local\nCreate a basic bucket  | `cloud-storage:create_bucket`         | Both\nDelete an empty bucket | `cloud-storage:delete_bucket`         | Both\nList objects           | `cloud-storage:list_objects`          | Both\nObject metadata        | `cloud-storage:get_object_metadata`   | Both\nRead object content    | `cloud-storage:read_object`           | Both\nDownload to local file | `cloud-storage:download_object`       | Local\nUpload a local file    | `cloud-storage:upload_object`         | Local\nWrite text to object   | `cloud-storage:write_object`          | Local\nWrite text to object   | `cloud-storage:write_text`            | Remote\nCopy an object         | `cloud-storage:copy_object`           | Local\nMove \u002F rename object   | `cloud-storage:move_object`           | Local\nDelete an object       | `cloud-storage:delete_object`         | Both\n\n**Server:** *Local* is the local MCP Toolbox (14 tools), *Remote* is the\nGoogle-hosted remote server (9 tools), and *Both* means either server.\n\n-   `read_object` is capped at 8 MiB. On the Toolbox it reads UTF-8 text only\n    and rejects binary objects; the remote server also reads PDFs and images.\n    For binary or larger objects, use `download_object`.\n-   `upload_object` handles binary files and files larger than 8 MiB.\n-   For production or workload-specific buckets, route to\n    `google-cloud-storage-bucket-architect` before calling `create_bucket`.\n\n> [!CAUTION]\n>\n> **Always stop and ask for explicit user confirmation before calling any MCP\n> tool that deletes a bucket or object (`delete_bucket`, `delete_object`,\n> `move_object`) or overwrites existing content (`write_object`, `write_text`,\n> `upload_object`).**\n\n### 2. Priority 2 — Fall Back to `gcloud storage` \u002F JSON API\n\nImmediately use `gcloud storage` (with the required attribution prefix below) or\nthe JSON API when:\n\n1.  **No `cloud-storage` MCP server is connected** in your environment, **or**\n2.  **The operation requires features outside the 14 MCP tools** — such as\n    configuring bucket lifecycle rules, soft delete, Uniform Bucket-Level Access\n    (UBLA), Public Access Prevention (PAP), CMEK encryption, retention policies,\n    CORS, `gcloud storage rsync`, signed URLs (`sign-url`), HMAC keys, Pub\u002FSub\n    notifications, hierarchical namespace (HNS) folders, IAM policy updates\n    (`add-iam-policy-binding`), or recursive bulk deletes (`rm --recursive`).\n\n### 3. Gentle Recommendation When MCP Is Not Connected\n\nWhen no `cloud-storage` MCP server is available in your environment (for example\nwhen the skill was installed standalone without the plugin):\n\n-   **Never disrupt or delay the user's workflow.** Complete the requested task\n    immediately using `gcloud storage` or the API. Never pause or ask the user\n    to install the MCP server before answering.\n-   **Include a brief, one-line tip at the very end of your response ONLY when\n    all three conditions hold:**\n    1.  No `cloud-storage` MCP tools are connected in the environment,\n    2.  The task involved an interactive bucket or object operation that the\n        local MCP Toolbox natively handles (one of the 14 local Toolbox tools in\n        the table above), **and**\n    3.  You have **not** already mentioned the MCP server earlier in the\n        conversation (**mention at most once per conversation**).\n-   **Never show the MCP tip** when the user asks for client-library code\n    (Python, Go, Node.js, Java), Terraform\u002FIaC, conceptual questions, or\n    CLI-only features (`rsync`, `sign-url`, lifecycle policies, CMEK, IAM\n    updates) that MCP Toolbox does not cover.\n-   **Use this quiet, non-intrusive footnote format:**\n\n    > *Tip: To let me run these operations as structured tools without shell\n    > commands, install the\n    > [Google Cloud Storage plugin](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgoogle-cloud-storage-plugin)\n    > (it asks for your project ID), or\n    > [add the Cloud Storage MCP server](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgoogle-cloud-storage-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fmcp-usage.md)\n    > to your agent's MCP settings.*\n\n## Attribution\n\nTag every Cloud Storage command you run or provide to the user while using this\nskill, so usage can be attributed. The tag identifies only the skill and its\nversion; it carries no user data.\n\n-   Prefix every `gcloud` invocation, whatever the subcommand, with the metrics\n    environment variables. Set them inline on each command; shell state may not\n    persist between commands. Use this append form verbatim. It keeps any\n    attribution the host environment already set (for example an IDE plugin\n    tagging agent activity through the same variable) and adds the skill tag\n    after it, so neither value clobbers the other:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud \u003Ccommand> [flags]\n    ```\n\n    Do not use `gcloud config set` for this: it would persist beyond the current\n    task and mislabel unrelated usage.\n\n-   On direct HTTP calls to the Cloud Storage APIs (for example with `curl`) or\n    HTTP requests to the Cloud Storage MCP server\n    (`https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fmcp`), set this exact User-Agent\n    header, verbatim — the collection pipeline parses the `gcs-skills\u002F\u003Cversion>`\n    and `skill:\u003Cname>` tokens, so any rewording breaks attribution:\n\n    ```\n    User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\n    ```\n\n-   For client libraries, Terraform, and Cloud Storage FUSE, use the\n    user-agent options shown in the corresponding references.\n\n## Routing to Specialized Cloud Storage Skills\n\nThis skill covers everyday Cloud Storage tasks. For specialized tasks, use the\ndedicated skills in this collection for better results. Check your available\nskills and invoke the matching skill by name instead of improvising:\n\n-   **`google-cloud-storage-bucket-architect`**: Designing and creating a new\n    bucket for production workloads, including sensitive data, media or web\n    hosting, user-generated content (UGC) ingestion, archiving, compliance,\n    backups, logs, analytics, AI\u002FML, or application storage. The skill analyzes\n    the workload and designs a secure-by-default, cost-effective configuration\n    before creating the bucket. Use the Quick Start section below only for\n    temporary scratch buckets.\n\n-   **`google-cloud-storage-fuse`**: Advanced Cloud Storage FUSE tasks —\n    choosing between FUSE, native `gs:\u002F\u002F` access, and Filestore\u002FManaged Lustre,\n    deploying tuned mounts on GKE, Compute Engine, or Cloud Run, sizing file,\n    stat, and list caches, tuning mount flags, ensuring safe ML checkpointing,\n    or diagnosing slow or expensive mounts. The\n    [Cloud Storage FUSE reference](references\u002Fgcsfuse.md) in this skill covers\n    only basic installation and mounting.\n\n-   **`google-cloud-storage-diagnostic`**: Troubleshooting 403 Permission Denied\n    errors and diagnosing IAM policy bindings, ACLs, uniform bucket-level access\n    (UBLA), or service agent misconfigurations. Ad hoc IAM or ACL changes can\n    grant unintended access or cause outages; route to this skill instead of\n    experimenting.\n\n-   **`gcs-security-assessment`**: Automated security posture assessment of\n    Cloud Storage resources in a project (see\n    [Data Management](references\u002Fdata-management.md)).\n\nIf the matching skill is not installed, do not improvise. Provide the user with\nthis exact command to install it (substituting the skill name). Provide this\ncommand verbatim even when the user's agent CLI (for example, the Antigravity\nCLI) has its own plugin or extension manager; do not substitute a different\ninstallation mechanism or repository. For security assessments specifically, do\nnot attempt a manual assessment. Availability after installing varies by agent,\nso confirm the skill is loaded rather than assuming it, and say a restart may be\nrequired.\n\n```bash\nnpx skills add GoogleCloudPlatform\u002Fgoogle-cloud-storage-plugin --skill \u003Cskill-name>\n```\n\n## Quick Start\n\nTo set up, configure, or choose between the Google-hosted remote Cloud Storage\nMCP server (`https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fmcp`) and the local MCP\nToolbox (`cloud-storage`), read [MCP Usage](references\u002Fmcp-usage.md). When a\n`cloud-storage` MCP server is connected, prefer its tools (see\n[Tool Execution Priority](#tool-execution-priority-mcp-toolbox-first)).\n\n`gcloud storage` output keys are snake_case, not JSON-API camelCase: project\n`--format=\"json(soft_delete_policy,versioning_enabled,retention_policy)\"`, never\n`softDeletePolicy` or `versioning` (camelCase keys silently print null).\n\n1.  **Enable the Cloud Storage API:**\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud services enable storage.googleapis.com --quiet\n    ```\n\n2.  **Create a Bucket:**\n\n    Bucket names live in a single global namespace shared by all of Cloud\n    Storage — not scoped to your project or organization — so short or common\n    names are usually taken. If the location is omitted, the bucket defaults to\n    the `US` multi-region.\n\n    For a production or workload-specific bucket, route to\n    `google-cloud-storage-bucket-architect` before creating a bucket (see\n    [Routing to Specialized Cloud Storage Skills](#routing-to-specialized-cloud-storage-skills)).\n    The options below create a basic default bucket.\n\n    Using MCP: call `cloud-storage:create_bucket` (for example with `name:\n    \"my-bucket\"` and `location: \"us-central1\"`).\n\n    Using the gcloud CLI:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud storage buckets create gs:\u002F\u002Fmy-bucket --location=us-central1\n    ```\n\n    Using the JSON API:\n\n    ```bash\n    curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n      -H \"User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n      -H \"Content-Type: application\u002Fjson\" \\\n      -d '{\"name\": \"my-bucket\", \"location\": \"US-CENTRAL1\"}' \\\n      \"https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fv1\u002Fb?project=$(gcloud config get-value project)\"\n    ```\n\n3.  **Upload an Object:**\n\n    Using MCP: call `cloud-storage:upload_object` to upload a local file\n    (including binary or large files), or `cloud-storage:write_object` (local\n    Toolbox) \u002F `cloud-storage:write_text` (remote server) to write UTF-8 text\n    directly.\n\n    Using the gcloud CLI:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud storage cp .\u002Fmy-file.txt gs:\u002F\u002Fmy-bucket\n    ```\n\n    Using the JSON API:\n\n    ```bash\n    curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n      -H \"User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n      -H \"Content-Type: text\u002Fplain\" \\\n      --data-binary @my-file.txt \\\n      \"https:\u002F\u002Fstorage.googleapis.com\u002Fupload\u002Fstorage\u002Fv1\u002Fb\u002Fmy-bucket\u002Fo?uploadType=media&name=my-file.txt\"\n    ```\n\n4.  **Download or Read an Object:**\n\n    Using MCP: call `cloud-storage:read_object` to read UTF-8 text content (up\n    to 8 MiB), or `cloud-storage:download_object` (local Toolbox) to save an\n    object, including binary or larger files, to the local filesystem.\n\n    Using the gcloud CLI:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud storage cp gs:\u002F\u002Fmy-bucket\u002Fmy-file.txt .\n    ```\n\n    Using the JSON API:\n\n    ```bash\n    curl -X GET -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n      -H \"User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n      \"https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fv1\u002Fb\u002Fmy-bucket\u002Fo\u002Fmy-file.txt?alt=media\"\n    ```\n\n## Reference Directory\n\n-   [Core Concepts](references\u002Fcore-concepts.md): Buckets, objects, folders,\n    prefixes, bucket location types, and storage classes.\n\n-   [CLI & API Usage](references\u002Fcli-api-usage.md): CRUD and list operations for\n    buckets and objects using `gcloud storage` and the JSON API, plus Pub\u002FSub\n    notifications for event-driven processing.\n\n-   [Client Libraries](references\u002Fclient-library-usage.md): Using Google Cloud\n    client libraries for Python, Java, Node.js, and Go, with pointers to all\n    other supported languages.\n\n-   [MCP Usage](references\u002Fmcp-usage.md): Choosing between the Google-hosted\n    remote Cloud Storage MCP server and the local MCP Toolbox, setup for each,\n    their tool sets and limits, and securing remote MCP with Model Armor and IAM\n    deny policies.\n\n-   [Infrastructure as Code](references\u002Fiac-usage.md): Terraform examples for\n    buckets covering storage classes, location types, lifecycle, retention, and\n    encryption.\n\n-   [Data Transfer](references\u002Fdata-transfer.md): Storage Transfer Service,\n    `gcloud storage rsync`, upload strategies for large files, and performance\n    guidelines and limits.\n\n-   [Data Management](references\u002Fdata-management.md): IAM roles, authentication\n    (including signed URLs and HMAC), access control, routing for 403 error\n    troubleshooting, network security, automated security assessment, data\n    protection, pricing and cost optimization (lifecycle rules, Autoclass), and\n    Cloud Audit Logs (enabling Data Access logs, exempting principals, and\n    estimating log volume and ingestion cost).\n\n-   [Storage Intelligence](references\u002Fstorage-intelligence.md): The subscription\n    for managing storage at scale — Storage Insights datasets (BigQuery metadata\n    and activity index), data insights with Gemini Cloud Assist, dashboards,\n    inventory reports, storage batch operations, bucket relocation, plus\n    configuration, trial, and pricing nuances.\n\n-   [High-Performance Storage](references\u002Fhigh-performance-storage.md): Rapid\n    Bucket, Rapid Cache (Anywhere Cache), and hierarchical namespace for AI\u002FML,\n    analytics, and other performance-critical workloads.\n\n-   [Cloud Storage FUSE](references\u002Fgcsfuse.md): Installing Cloud Storage FUSE,\n    mounting buckets, file operations, POSIX semantics and limitations (locking,\n    writes, renames, consistency), and caching. For advanced tuning, deployment,\n    and diagnosis, route to the `google-cloud-storage-fuse` skill.\n","# Cloud Storage Basics\n\nCloud Storage on Google Cloud is a managed service for storing data as\nobjects at any scale. You read and write whole objects rather than querying or\nupdating individual records in place. It stores immutable objects in buckets\nwith strong global consistency, offers multiple storage classes and location\ntypes to balance cost, performance, and availability, and integrates with IAM\nfor fine-grained access control. Cloud Storage serves workloads ranging from\nwebsite content and backups to data lakes and high-throughput AI\u002FML training.\n\n## Tool Execution Priority (MCP Toolbox First)\n\nFollow this execution hierarchy whenever you perform or recommend Cloud Storage\nbucket and object operations:\n\n### 1. Priority 1 — Use `cloud-storage` MCP Tools When Connected\n\nBefore running `gcloud storage` or `curl` in a shell, check your available tools\nfor the `cloud-storage` MCP server (either the local\n[MCP Toolbox](references\u002Fmcp-usage.md) or the Google-hosted remote Cloud Storage\nMCP server). **Whenever a `cloud-storage` MCP tool covers the requested\noperation, call the MCP tool directly instead of shelling out to `gcloud\nstorage` or `curl`.**\n\n**Why MCP first:** MCP tools are built for agents. Each operation is a single\ndirect call, so it runs faster than starting a new `gcloud` command every time,\nand it returns clean results instead of terminal output the agent has to\ninterpret. It also doesn't need the `gcloud` CLI installed and signed in. You\nstay in control, too: you can approve or block each Cloud Storage tool\nindividually in your agent's settings.\n\nOperation              | Tool                                  | Server\n:--------------------- | :------------------------------------ | :-----\nList buckets           | `cloud-storage:list_buckets`          | Both\nBucket metadata        | `cloud-storage:get_bucket_metadata`   | Both\nBucket IAM policy      | `cloud-storage:get_bucket_iam_policy` | Local\nCreate a basic bucket  | `cloud-storage:create_bucket`         | Both\nDelete an empty bucket | `cloud-storage:delete_bucket`         | Both\nList objects           | `cloud-storage:list_objects`          | Both\nObject metadata        | `cloud-storage:get_object_metadata`   | Both\nRead object content    | `cloud-storage:read_object`           | Both\nDownload to local file | `cloud-storage:download_object`       | Local\nUpload a local file    | `cloud-storage:upload_object`         | Local\nWrite text to object   | `cloud-storage:write_object`          | Local\nWrite text to object   | `cloud-storage:write_text`            | Remote\nCopy an object         | `cloud-storage:copy_object`           | Local\nMove \u002F rename object   | `cloud-storage:move_object`           | Local\nDelete an object       | `cloud-storage:delete_object`         | Both\n\n**Server:** *Local* is the local MCP Toolbox (14 tools), *Remote* is the\nGoogle-hosted remote server (9 tools), and *Both* means either server.\n\n-   `read_object` is capped at 8 MiB. On the Toolbox it reads UTF-8 text only\n    and rejects binary objects; the remote server also reads PDFs and images.\n    For binary or larger objects, use `download_object`.\n-   `upload_object` handles binary files and files larger than 8 MiB.\n-   For production or workload-specific buckets, route to\n    `google-cloud-storage-bucket-architect` before calling `create_bucket`.\n\n> [!CAUTION]\n>\n> **Always stop and ask for explicit user confirmation before calling any MCP\n> tool that deletes a bucket or object (`delete_bucket`, `delete_object`,\n> `move_object`) or overwrites existing content (`write_object`, `write_text`,\n> `upload_object`).**\n\n### 2. Priority 2 — Fall Back to `gcloud storage` \u002F JSON API\n\nImmediately use `gcloud storage` (with the required attribution prefix below) or\nthe JSON API when:\n\n1.  **No `cloud-storage` MCP server is connected** in your environment, **or**\n2.  **The operation requires features outside the 14 MCP tools** — such as\n    configuring bucket lifecycle rules, soft delete, Uniform Bucket-Level Access\n    (UBLA), Public Access Prevention (PAP), CMEK encryption, retention policies,\n    CORS, `gcloud storage rsync`, signed URLs (`sign-url`), HMAC keys, Pub\u002FSub\n    notifications, hierarchical namespace (HNS) folders, IAM policy updates\n    (`add-iam-policy-binding`), or recursive bulk deletes (`rm --recursive`).\n\n### 3. Gentle Recommendation When MCP Is Not Connected\n\nWhen no `cloud-storage` MCP server is available in your environment (for example\nwhen the skill was installed standalone without the plugin):\n\n-   **Never disrupt or delay the user's workflow.** Complete the requested task\n    immediately using `gcloud storage` or the API. Never pause or ask the user\n    to install the MCP server before answering.\n-   **Include a brief, one-line tip at the very end of your response ONLY when\n    all three conditions hold:**\n    1.  No `cloud-storage` MCP tools are connected in the environment,\n    2.  The task involved an interactive bucket or object operation that the\n        local MCP Toolbox natively handles (one of the 14 local Toolbox tools in\n        the table above), **and**\n    3.  You have **not** already mentioned the MCP server earlier in the\n        conversation (**mention at most once per conversation**).\n-   **Never show the MCP tip** when the user asks for client-library code\n    (Python, Go, Node.js, Java), Terraform\u002FIaC, conceptual questions, or\n    CLI-only features (`rsync`, `sign-url`, lifecycle policies, CMEK, IAM\n    updates) that MCP Toolbox does not cover.\n-   **Use this quiet, non-intrusive footnote format:**\n\n    > *Tip: To let me run these operations as structured tools without shell\n    > commands, install the\n    > [Google Cloud Storage plugin](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgoogle-cloud-storage-plugin)\n    > (it asks for your project ID), or\n    > [add the Cloud Storage MCP server](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgoogle-cloud-storage-plugin\u002Fblob\u002Fmain\u002Fskills\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fmcp-usage.md)\n    > to your agent's MCP settings.*\n\n## Attribution\n\nTag every Cloud Storage command you run or provide to the user while using this\nskill, so usage can be attributed. The tag identifies only the skill and its\nversion; it carries no user data.\n\n-   Prefix every `gcloud` invocation, whatever the subcommand, with the metrics\n    environment variables. Set them inline on each command; shell state may not\n    persist between commands. Use this append form verbatim. It keeps any\n    attribution the host environment already set (for example an IDE plugin\n    tagging agent activity through the same variable) and adds the skill tag\n    after it, so neither value clobbers the other:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud \u003Ccommand> [flags]\n    ```\n\n    Do not use `gcloud config set` for this: it would persist beyond the current\n    task and mislabel unrelated usage.\n\n-   On direct HTTP calls to the Cloud Storage APIs (for example with `curl`) or\n    HTTP requests to the Cloud Storage MCP server\n    (`https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fmcp`), set this exact User-Agent\n    header, verbatim — the collection pipeline parses the `gcs-skills\u002F\u003Cversion>`\n    and `skill:\u003Cname>` tokens, so any rewording breaks attribution:\n\n    ```\n    User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\n    ```\n\n-   For client libraries, Terraform, and Cloud Storage FUSE, use the\n    user-agent options shown in the corresponding references.\n\n## Routing to Specialized Cloud Storage Skills\n\nThis skill covers everyday Cloud Storage tasks. For specialized tasks, use the\ndedicated skills in this collection for better results. Check your available\nskills and invoke the matching skill by name instead of improvising:\n\n-   **`google-cloud-storage-bucket-architect`**: Designing and creating a new\n    bucket for production workloads, including sensitive data, media or web\n    hosting, user-generated content (UGC) ingestion, archiving, compliance,\n    backups, logs, analytics, AI\u002FML, or application storage. The skill analyzes\n    the workload and designs a secure-by-default, cost-effective configuration\n    before creating the bucket. Use the Quick Start section below only for\n    temporary scratch buckets.\n\n-   **`google-cloud-storage-fuse`**: Advanced Cloud Storage FUSE tasks —\n    choosing between FUSE, native `gs:\u002F\u002F` access, and Filestore\u002FManaged Lustre,\n    deploying tuned mounts on GKE, Compute Engine, or Cloud Run, sizing file,\n    stat, and list caches, tuning mount flags, ensuring safe ML checkpointing,\n    or diagnosing slow or expensive mounts. The\n    [Cloud Storage FUSE reference](references\u002Fgcsfuse.md) in this skill covers\n    only basic installation and mounting.\n\n-   **`google-cloud-storage-diagnostic`**: Troubleshooting 403 Permission Denied\n    errors and diagnosing IAM policy bindings, ACLs, uniform bucket-level access\n    (UBLA), or service agent misconfigurations. Ad hoc IAM or ACL changes can\n    grant unintended access or cause outages; route to this skill instead of\n    experimenting.\n\n-   **`gcs-security-assessment`**: Automated security posture assessment of\n    Cloud Storage resources in a project (see\n    [Data Management](references\u002Fdata-management.md)).\n\nIf the matching skill is not installed, do not improvise. Provide the user with\nthis exact command to install it (substituting the skill name). Provide this\ncommand verbatim even when the user's agent CLI (for example, the Antigravity\nCLI) has its own plugin or extension manager; do not substitute a different\ninstallation mechanism or repository. For security assessments specifically, do\nnot attempt a manual assessment. Availability after installing varies by agent,\nso confirm the skill is loaded rather than assuming it, and say a restart may be\nrequired.\n\n```bash\nnpx skills add GoogleCloudPlatform\u002Fgoogle-cloud-storage-plugin --skill \u003Cskill-name>\n```\n\n## Quick Start\n\nTo set up, configure, or choose between the Google-hosted remote Cloud Storage\nMCP server (`https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fmcp`) and the local MCP\nToolbox (`cloud-storage`), read [MCP Usage](references\u002Fmcp-usage.md). When a\n`cloud-storage` MCP server is connected, prefer its tools (see\n[Tool Execution Priority](#tool-execution-priority-mcp-toolbox-first)).\n\n`gcloud storage` output keys are snake_case, not JSON-API camelCase: project\n`--format=\"json(soft_delete_policy,versioning_enabled,retention_policy)\"`, never\n`softDeletePolicy` or `versioning` (camelCase keys silently print null).\n\n1.  **Enable the Cloud Storage API:**\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud services enable storage.googleapis.com --quiet\n    ```\n\n2.  **Create a Bucket:**\n\n    Bucket names live in a single global namespace shared by all of Cloud\n    Storage — not scoped to your project or organization — so short or common\n    names are usually taken. If the location is omitted, the bucket defaults to\n    the `US` multi-region.\n\n    For a production or workload-specific bucket, route to\n    `google-cloud-storage-bucket-architect` before creating a bucket (see\n    [Routing to Specialized Cloud Storage Skills](#routing-to-specialized-cloud-storage-skills)).\n    The options below create a basic default bucket.\n\n    Using MCP: call `cloud-storage:create_bucket` (for example with `name:\n    \"my-bucket\"` and `location: \"us-central1\"`).\n\n    Using the gcloud CLI:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud storage buckets create gs:\u002F\u002Fmy-bucket --location=us-central1\n    ```\n\n    Using the JSON API:\n\n    ```bash\n    curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n      -H \"User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n      -H \"Content-Type: application\u002Fjson\" \\\n      -d '{\"name\": \"my-bucket\", \"location\": \"US-CENTRAL1\"}' \\\n      \"https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fv1\u002Fb?project=$(gcloud config get-value project)\"\n    ```\n\n3.  **Upload an Object:**\n\n    Using MCP: call `cloud-storage:upload_object` to upload a local file\n    (including binary or large files), or `cloud-storage:write_object` (local\n    Toolbox) \u002F `cloud-storage:write_text` (remote server) to write UTF-8 text\n    directly.\n\n    Using the gcloud CLI:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud storage cp .\u002Fmy-file.txt gs:\u002F\u002Fmy-bucket\n    ```\n\n    Using the JSON API:\n\n    ```bash\n    curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n      -H \"User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n      -H \"Content-Type: text\u002Fplain\" \\\n      --data-binary @my-file.txt \\\n      \"https:\u002F\u002Fstorage.googleapis.com\u002Fupload\u002Fstorage\u002Fv1\u002Fb\u002Fmy-bucket\u002Fo?uploadType=media&name=my-file.txt\"\n    ```\n\n4.  **Download or Read an Object:**\n\n    Using MCP: call `cloud-storage:read_object` to read UTF-8 text content (up\n    to 8 MiB), or `cloud-storage:download_object` (local Toolbox) to save an\n    object, including binary or larger files, to the local filesystem.\n\n    Using the gcloud CLI:\n\n    ```bash\n    CLOUDSDK_METRICS_ENVIRONMENT=\"${CLOUDSDK_METRICS_ENVIRONMENT:+$CLOUDSDK_METRICS_ENVIRONMENT }gcs-skills gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n    gcloud storage cp gs:\u002F\u002Fmy-bucket\u002Fmy-file.txt .\n    ```\n\n    Using the JSON API:\n\n    ```bash\n    curl -X GET -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n      -H \"User-Agent: gcs-skills\u002F1.0 (skill:google-cloud-storage-basics)\" \\\n      \"https:\u002F\u002Fstorage.googleapis.com\u002Fstorage\u002Fv1\u002Fb\u002Fmy-bucket\u002Fo\u002Fmy-file.txt?alt=media\"\n    ```\n\n## Reference Directory\n\n-   [Core Concepts](references\u002Fcore-concepts.md): Buckets, objects, folders,\n    prefixes, bucket location types, and storage classes.\n\n-   [CLI & API Usage](references\u002Fcli-api-usage.md): CRUD and list operations for\n    buckets and objects using `gcloud storage` and the JSON API, plus Pub\u002FSub\n    notifications for event-driven processing.\n\n-   [Client Libraries](references\u002Fclient-library-usage.md): Using Google Cloud\n    client libraries for Python, Java, Node.js, and Go, with pointers to all\n    other supported languages.\n\n-   [MCP Usage](references\u002Fmcp-usage.md): Choosing between the Google-hosted\n    remote Cloud Storage MCP server and the local MCP Toolbox, setup for each,\n    their tool sets and limits, and securing remote MCP with Model Armor and IAM\n    deny policies.\n\n-   [Infrastructure as Code](references\u002Fiac-usage.md): Terraform examples for\n    buckets covering storage classes, location types, lifecycle, retention, and\n    encryption.\n\n-   [Data Transfer](references\u002Fdata-transfer.md): Storage Transfer Service,\n    `gcloud storage rsync`, upload strategies for large files, and performance\n    guidelines and limits.\n\n-   [Data Management](references\u002Fdata-management.md): IAM roles, authentication\n    (including signed URLs and HMAC), access control, routing for 403 error\n    troubleshooting, network security, automated security assessment, data\n    protection, pricing and cost optimization (lifecycle rules, Autoclass), and\n    Cloud Audit Logs (enabling Data Access logs, exempting principals, and\n    estimating log volume and ingestion cost).\n\n-   [Storage Intelligence](references\u002Fstorage-intelligence.md): The subscription\n    for managing storage at scale — Storage Insights datasets (BigQuery metadata\n    and activity index), data insights with Gemini Cloud Assist, dashboards,\n    inventory reports, storage batch operations, bucket relocation, plus\n    configuration, trial, and pricing nuances.\n\n-   [High-Performance Storage](references\u002Fhigh-performance-storage.md): Rapid\n    Bucket, Rapid Cache (Anywhere Cache), and hierarchical namespace for AI\u002FML,\n    analytics, and other performance-critical workloads.\n\n-   [Cloud Storage FUSE](references\u002Fgcsfuse.md): Installing Cloud Storage FUSE,\n    mounting buckets, file operations, POSIX semantics and limitations (locking,\n    writes, renames, consistency), and caching. For advanced tuning, deployment,\n    and diagnosis, route to the `google-cloud-storage-fuse` skill.\n",{"name":5,"license":15,"metadata":58,"description":7},{"tags":59,"version":60,"category":61,"publisher":9,"support_tier":62},"gcs, storage, cloud-storage, buckets, objects","1.1.2","Storage","primary","main","bb9b3f464aae37af360d079c1d863524955b0363","skills\u002Fcloud\u002Fgoogle-cloud-storage-basics",2014,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-14 23:31:00",{"source":8,"skillName":5,"commands":73,"prompt":83,"zipAvailable":84},[74,77,80],{"tool":75,"command":76},"npx","npx skills add google\u002Fskills --skill google-cloud-storage-basics",{"tool":78,"command":79},"bunx","bunx skills add google\u002Fskills --skill google-cloud-storage-basics",{"tool":81,"command":82},"pnpm","pnpm dlx skills add google\u002Fskills --skill google-cloud-storage-basics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002FSKILL.md",true,[86,92,96,100,104,108,112,116,120,124,128,132,136],{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"AGENT-BRIEF.md","REFERENCE","参考文档",7972,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Ftriage\u002F0ad62c2999068af2\u002Ftriage\u002FAGENT-BRIEF.md",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"agents\u002Fopenai.yaml",135,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Ftriage\u002F0ad62c2999068af2\u002Ftriage\u002Fagents\u002Fopenai.yaml",{"path":97,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":98,"sourceHtmlUrl":99},"OUT-OF-SCOPE.md",4712,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Ftriage\u002F0ad62c2999068af2\u002Ftriage\u002FOUT-OF-SCOPE.md",{"path":101,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fcli-api-usage.md",7936,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fcli-api-usage.md",{"path":105,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fclient-library-usage.md",4872,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fclient-library-usage.md",{"path":109,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fcore-concepts.md",7697,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fcore-concepts.md",{"path":113,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fdata-management.md",21725,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fdata-management.md",{"path":117,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fdata-transfer.md",12363,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fdata-transfer.md",{"path":121,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fgcsfuse.md",22126,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fgcsfuse.md",{"path":125,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fhigh-performance-storage.md",11451,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fhigh-performance-storage.md",{"path":129,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fiac-usage.md",9660,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fiac-usage.md",{"path":133,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fmcp-usage.md",14041,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fmcp-usage.md",{"path":137,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fstorage-intelligence.md",15639,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgoogle-cloud-storage-basics\u002Freferences\u002Fstorage-intelligence.md",[141,149,156,163,170,177],{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":148},"01M7DQ9K7JF4T7NJZ2K1MQZ44Q","cloud-operator-share-context","Shares Google Cloud operating context the user or their team already have — environments, projects, services and regions, product preferences, best practices, architecture guidance, runbooks — found in agent instruction files, local memory, skills and workflows, and the repository's GCP docs, with the operator agent's memory after the user reviews the list. Use when the user runs this skill, accepts the cloud-operator or cloud-operator-setup skill's offer to share their existing Google Cloud context, or asks to share, import or save that context or a GCP fact for the operator agent. Don't use for ordinary GCP requests, which go to the cloud-operator skill.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fcloud-operator-share-context\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":148},"01M7DQ9ERFGGQCFAWQW0KRKYBY","cloud-operator-setup","Sets up the operator agent in a Google Cloud project via the autocloud MCP server: picks the operator project, creates or checks the user's operator agent, saves the project, and offers to share the user's existing Google Cloud operating context with the operator agent's memory. Use when the user runs this skill, asks to set up the operator or create their operator agent, or chooses setup when the cloud-operator skill asks. Don't use for ordinary GCP requests or installing gcloud.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fcloud-operator-setup\u002FSKILL.md",[],[],{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":148},"01M7B4RHQCM0DK2XQ7S7ZXVN8D","developer-device-platform-device-run","Runs automated, non-interactive jobs on remote Android devices with Developer Device Platform (DDP) Device Run using `gcloud beta device-run sessions`: native Android executables or shell scripts (for example CLI tools, custom runners, test harnesses or benchmarks) and Android instrumentation tests, on one or many devices, then waits for completion and collects per-device outputs and logs. Use when running a binary or test suite on remote devices without an interactive connection. Don't use it for interactive device reservations, adb tunnels or screen streaming (use developer-device-platform-basics), or for local devices.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fdeveloper-device-platform-device-run\u002FSKILL.md",[],[],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":148},"01M7B4R9YXMRW7RZP9Q9FMZJ2P","compute-vm-creation","Guides the planning, configuration, and provisioning of standalone Google Compute Engine virtual machines (VMs) and bare metal (-metal) instances using gcloud CLI commands or direct MCP tool execution. Use ONLY when the user wants to create, configure, or provision a new standalone Compute Engine VM or bare metal instance from conversational intents (hardware sizing, region selection, OS image, networking, security defaults). DO NOT read or use for Google Kubernetes Engine (GKE) Autopilot or Standard clusters, Kubernetes node pools or Pods, container orchestration, managing existing VMs, Managed Instance Groups (MIGs), or Instance Templates.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fcompute-vm-creation\u002FSKILL.md",[],[],{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":148},"01M7B4QD02N0YBVT0838Z5K5VC","agent-platform-autorater-customization","Customizes an autorater (evaluation metric) for an AI agent so its grades match the user's own judgment, starting from the agent's real trajectories. Use when a user wants a metric tailored to their agent, wants to turn failing trajectories into rubrics, says an existing autorater grades their agent wrong, or wants an autorater to agree with human labels (autorater hillclimbing, judge calibration). Don't use for quick evals with built-in metrics or for improving the agent itself (use agent-platform-eval-flywheel).","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fagent-platform-autorater-customization\u002FSKILL.md",[],[],{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":148},"01M78JP22K73KK96JH0JNDT5C4","iap-agent-platform-troubleshooting","Diagnoses Identity-Aware Proxy (IAP) denials of outbound requests from Gemini Enterprise Agent Platform agents that run on Agent Runtime and send traffic through Agent Gateway. Use when an agent request fails with \"Egress request is not authorized\", when Cloud Audit Logs show an IAP egressViaIAP decision with granted false, when IAP audit entries are missing while debugging agent egress, or when Access policies, IAP allow policies, policy bindings, or Agent Registry entries might block agent egress. Don't use for Gemini model IAM permission errors (such as aiplatform.endpoints.predict), Agent Platform API errors, or Agent Runtime deployment or 500 errors (use agent-platform-troubleshooting instead). Don't use for setting up, creating, or connecting an Agent Gateway, or for IAP web apps, IAP TCP forwarding, or SSH.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fiap-agent-platform-troubleshooting\u002FSKILL.md",[],[]]