[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698YGYFVZ4MEHZTRWXCYY2A":3,"skill-same:01M698YGYFVZ4MEHZTRWXCYY2A":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":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M698YGYFVZ4MEHZTRWXCYY2A","agent-platform-prompt-management",null,"Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.","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\u002Fagent-platform-prompt-management\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"agent platform","prompt management","prompt","platform","management","agent platform prompt management","use","when","managed","for","you","endpoints","prompts","version","list","model","delete","create","deployment","training","model deployment","2026-11-10 10:12:30",false,"---\nname: agent-platform-prompt-management\nmetadata:\n  version: \"1.0.1\"\n  category: AiAndMachineLearning\ndescription: >-\n  Manages and orchestrates prompts in Agent Platform. Use when you need to create,\n  list, retrieve, version, or delete managed prompts in Agent Platform. Don't use\n  for model training, model deployment to endpoints, or managing non-Agent Platform\n  prompts.\n---\n\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you MUST\nread [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with `CLOUDSDK_METRICS_REQUEST_ATTRIBUTION` and append the\nattribution suffix to `User-Agent` headers:\n\n```text\nCLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:agent-platform-prompt-management)\"\nUser-Agent: \u003Cexisting_user_agent> agent-skills\u002F1.0 (skill:agent-platform-prompt-management)\n```\n\n## Usage Guide\n\nTo use this skill effectively:\n\n1.  **Execute Operations via Python**: Run the Python snippets below using\n    `run_command` in the execution environment to manage prompts in Agent\n    Platform on behalf of the user. Do not delegate execution to the user or\n    claim lack of access once approved.\n\n2.  **No File System Search**: Do not try to find Python files or scripts on the\n    file system for these operations.\n\n## Safety & Confirmation Tiers (CRITICAL)\n\nBefore executing any commands or scripts on behalf of the user, you must adhere\nto the following safety tiers based on the action requested, to prevent\naccidental mutation or permanent deletion of prompt resources:\n\n1.  **Tier R: Read-only (`list`, `get`)**\n    *   No confirmation needed. Execute immediately to gather information.\n2.  **Tier M: Mutating & Reversible (`create`)**\n\n    *   Requires **interactive confirmation** with 'Yes'\u002F'No' options before\n        executing prompt creation, to prevent unintended resource proliferation\n        or misconfiguration. The confirmation prompt must clearly explain the\n        proposed prompt creation and its key parameters (e.g., display name,\n        template text, target model). Natural-language paraphrases without\n        specifying the parameters are not sufficient.\n    *   **Same-turn restriction**: Do not execute the creation code in the same\n        turn as presenting the confirmation prompt. Stop and wait for the user's\n        reply; only execute after explicit 'Yes' \u002F approval.\n    *   Every parameter in the card must trace back to something the user said.\n        The target model is a user choice, not a default: if the user did not\n        name one, ASK before building the card. Do not carry over the model that\n        appears in the examples here or in `references\u002Fcreate.md`.\n    *   **Gold Standard Example** — for a user who said \"create a prompt called\n        Customer Support Greeting for gemini-2.5-pro with the template Hello\n        {{user_name}}, how can I help...\":\n\n        > I will create a prompt in Agent Platform with the following\n        > parameters. Please confirm this information before I proceed:\n        >\n        > *   **Display Name**: `Customer Support Greeting`\n        > *   **Target Model**: `gemini-2.5-pro`\n        > *   **Template Text**: \"Hello {{user_name}}, how can I help...\"\n        >\n        > ```python\n        > vertexai.init(project=\"\u003CPROJECT_ID>\", location=\"\u003CLOCATION_ID>\")\n        > prompt = Prompt(\n        >     prompt_data=[\"Hello {user_name}, how can I help...\"],\n        >     model_name=\"gemini-2.5-pro\",\n        >     prompt_name=\"Customer Support Greeting\",\n        > )\n        > created_prompt = prompts.create_version(prompt=prompt)\n        > ```\n        >\n        > Do you confirm? [Yes\u002FNo]\n\n3.  **Tier D: Destructive & Irreversible (`delete`)**\n\n    *   Requires **explicit typed confirmation** (e.g. \"I confirm\" or \"Yes,\n        delete it\") before executing prompt deletion, to prevent accidental\n        permanent loss of production prompt assets. Ask for confirmation before\n        any pre-flight checks.\n    *   **Same-turn restriction**: NEVER execute in the same turn as asking for\n        typed confirmation. Wait for the user to reply in a new turn.\n    *   **Gold Standard Example**:\n\n        > I will permanently delete the following prompt from Agent Platform.\n        > This action is irreversible. Please explicitly type your confirmation\n        > (e.g., \"I confirm\") before I proceed:\n        >\n        > *   **Prompt ID**: `prompt_12345abc`\n        > *   **Display Name**: `Legacy Outdated Prompt`\n        >\n        > Please type your confirmation to proceed.\n\n## Phase 0: Environment Setup\n\n**CRITICAL**: Before the user runs any of the Python snippets below, you MUST\nadvise them to ensure the environment is correctly initialized by following\nthese steps:\n\n1.  **Google Cloud Authentication**: Authenticate with your Google Cloud account\n    and configure active Application Default Credentials (ADC) for Agent\n    Platform access:\n\n    ```bash\n    gcloud auth login\n    gcloud auth application-default login\n    ```\n\n2.  **Python Dependencies**: This skill needs `google-cloud-aiplatform` and\n    `google-genai`. Do **not** create a virtual environment — it starts empty\n    and hides packages the environment already provides, forcing a redundant\n    install. Probe, and install only what is missing:\n\n    ```bash\n    python3 -c \"import vertexai, google.genai\" \\\n      || pip install google-cloud-aiplatform google-genai\n    ```\n\n3.  **Execution**: Run Python snippets with a plain `python3`. There is no\n    environment to activate first.\n\n> [!TIP]\n>\n> **Placeholder Parameter Replacement:** The Python scripts below use uppercase\n> string placeholders (like `\"PROJECT_ID\"`, `\"LOCATION_ID\"`, `\"PROMPT_ID\"`, and\n> `\"MODEL_ID\"`). You **MUST** dynamically replace these placeholders with the\n> actual Project ID, Region, Prompt ID, and target model values provided in the\n> user's prompt (or discovered context) before generating or providing the\n> scripts. If the user did not supply one of these, ask -- a placeholder is\n> never satisfied by guessing a plausible value.\n\n## 1. Managing Prompts via Agent Platform SDK\n\nThe SDK provides a high-level `Prompt` class in the preview module.\n\n### Create a Prompt (Tier M)\n\nUse when you need to create a new managed prompt in Agent Platform.\n\n*   **Reference**: See [create.md](references\u002Fcreate.md) for detailed\n    instructions and Python snippets.\n\n### List Prompts (Tier R)\n\n```python\nimport vertexai\nfrom vertexai.preview import prompts\n\nvertexai.init(project=\"PROJECT_ID\", location=\"LOCATION_ID\")\n\nall_prompts = prompts.list()\nfor p in all_prompts:\n    print(f\"Name: {p.display_name}, ID: {p.prompt_id}\")\n```\n\n### Retrieve and Use a Prompt (Tier R)\n\n```python\nimport vertexai\nfrom vertexai.preview import prompts\n\nvertexai.init(project=\"PROJECT_ID\", location=\"LOCATION_ID\")\n\nretrieved_prompt = prompts.get(prompt_id=\"PROMPT_ID\")\n# Attributes on retrieved Prompt:\n# - retrieved_prompt.prompt_id (e.g. \"123456789...\")\n# - retrieved_prompt.prompt_data (template text string)\n# - retrieved_prompt.model_name (target model)\n# - retrieved_prompt.prompt_name (display name, or\n#   retrieved_prompt._dataset.display_name)\n# Versions are supported: prompts.get(prompt_id=\"PROMPT_ID\", version_id=\"2\")\n\n# Assemble with variables (kwargs must match template variable names)\nassembled = retrieved_prompt.assemble_contents(text=\"The quick brown fox...\")\nprint(assembled)\n```\n\n### Delete a Prompt (Tier D)\n\n**CRITICAL**: You must pass the numeric prompt ID (e.g.,\n`\"1234567890123456789\"`) to `prompts.delete()`. The SDK constructs the full\nresource path internally using the project and location from `vertexai.init()`.\n\n**Confirmation Required**: As a Tier D (Destructive) operation, the agent MUST\npause and request explicit, high-friction typed re-confirmation of the prompt ID\nfrom the user before executing the deletion code. The action is irreversible.\nOnce the user replies with typed confirmation (e.g., \"I confirm\"), proceed\nimmediately to execute the deletion code via `run_command`.\n\n> [!IMPORTANT]\n>\n> **NEVER pre-emptively execute any deletion code before receiving the user's\n> response in a new turn.** You must never speculate or assume that confirmation\n> will be given. Asking for confirmation and running the code in a single\n> parallel turn is a severe safety violation.\n\n```python\nimport vertexai\nfrom vertexai.preview import prompts\n\nvertexai.init(project=\"PROJECT_ID\", location=\"LOCATION_ID\")\n\nprompts.delete(prompt_id=\"PROMPT_ID\")\n```\n\n### Verification After Deletion\n\nWhenever listing prompts or verifying state after deleting a prompt in the same\nconversation, you **MUST**:\n\n1.  Check in Python whether the deleted `prompt_id` appears in `prompts.list()`.\n2.  In your prose reply (even when the list is also shown as a card):\n    *   If it is not found, explicitly confirm: *\"I have verified that the\n        deleted prompt (ID: `\u003CPROMPT_ID>`) is no longer present in project\n        `\u003CPROJECT_ID>` (`\u003CLOCATION_ID>`).\"*\n    *   If it is still listed, report its current presence and ID to the user.\n\n## 2. Best Practices\n\n-   **Idempotency**:\n    *   **Tier R** (List, Get): Inherently idempotent.\n    *   **Tier D** (Delete): Re-running a delete on a non-existent or already\n        deleted resource returns NOT_FOUND. Treat this as success.\n-   **Placeholders**: Use the standard placeholder syntax (variable name\n    enclosed in double curly braces) in your prompt templates.\n-   **Versioning**: Always tag or record version IDs when making updates to\n    production prompts.\n-   **Model Reference**: A prompt is created against a target model ID, which\n    the snippets carry as the `\"MODEL_ID\"` placeholder. Like the other\n    placeholders it is MUST-replace, and it is replaced from what the user\n    said -- if they named no model, ask. Do not substitute a plausible current\n    model such as `gemini-2.5-pro`.\n-   **Underlying Schema**: When using the Dataset API, always use the correct\n    `metadata_schema_uri` and nested `metadata` structure to ensure the prompt\n    is recognized by Agent Platform Studio and the Prompts SDK.\n","## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you MUST\nread [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with `CLOUDSDK_METRICS_REQUEST_ATTRIBUTION` and append the\nattribution suffix to `User-Agent` headers:\n\n```text\nCLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:agent-platform-prompt-management)\"\nUser-Agent: \u003Cexisting_user_agent> agent-skills\u002F1.0 (skill:agent-platform-prompt-management)\n```\n\n## Usage Guide\n\nTo use this skill effectively:\n\n1.  **Execute Operations via Python**: Run the Python snippets below using\n    `run_command` in the execution environment to manage prompts in Agent\n    Platform on behalf of the user. Do not delegate execution to the user or\n    claim lack of access once approved.\n\n2.  **No File System Search**: Do not try to find Python files or scripts on the\n    file system for these operations.\n\n## Safety & Confirmation Tiers (CRITICAL)\n\nBefore executing any commands or scripts on behalf of the user, you must adhere\nto the following safety tiers based on the action requested, to prevent\naccidental mutation or permanent deletion of prompt resources:\n\n1.  **Tier R: Read-only (`list`, `get`)**\n    *   No confirmation needed. Execute immediately to gather information.\n2.  **Tier M: Mutating & Reversible (`create`)**\n\n    *   Requires **interactive confirmation** with 'Yes'\u002F'No' options before\n        executing prompt creation, to prevent unintended resource proliferation\n        or misconfiguration. The confirmation prompt must clearly explain the\n        proposed prompt creation and its key parameters (e.g., display name,\n        template text, target model). Natural-language paraphrases without\n        specifying the parameters are not sufficient.\n    *   **Same-turn restriction**: Do not execute the creation code in the same\n        turn as presenting the confirmation prompt. Stop and wait for the user's\n        reply; only execute after explicit 'Yes' \u002F approval.\n    *   Every parameter in the card must trace back to something the user said.\n        The target model is a user choice, not a default: if the user did not\n        name one, ASK before building the card. Do not carry over the model that\n        appears in the examples here or in `references\u002Fcreate.md`.\n    *   **Gold Standard Example** — for a user who said \"create a prompt called\n        Customer Support Greeting for gemini-2.5-pro with the template Hello\n        {{user_name}}, how can I help...\":\n\n        > I will create a prompt in Agent Platform with the following\n        > parameters. Please confirm this information before I proceed:\n        >\n        > *   **Display Name**: `Customer Support Greeting`\n        > *   **Target Model**: `gemini-2.5-pro`\n        > *   **Template Text**: \"Hello {{user_name}}, how can I help...\"\n        >\n        > ```python\n        > vertexai.init(project=\"\u003CPROJECT_ID>\", location=\"\u003CLOCATION_ID>\")\n        > prompt = Prompt(\n        >     prompt_data=[\"Hello {user_name}, how can I help...\"],\n        >     model_name=\"gemini-2.5-pro\",\n        >     prompt_name=\"Customer Support Greeting\",\n        > )\n        > created_prompt = prompts.create_version(prompt=prompt)\n        > ```\n        >\n        > Do you confirm? [Yes\u002FNo]\n\n3.  **Tier D: Destructive & Irreversible (`delete`)**\n\n    *   Requires **explicit typed confirmation** (e.g. \"I confirm\" or \"Yes,\n        delete it\") before executing prompt deletion, to prevent accidental\n        permanent loss of production prompt assets. Ask for confirmation before\n        any pre-flight checks.\n    *   **Same-turn restriction**: NEVER execute in the same turn as asking for\n        typed confirmation. Wait for the user to reply in a new turn.\n    *   **Gold Standard Example**:\n\n        > I will permanently delete the following prompt from Agent Platform.\n        > This action is irreversible. Please explicitly type your confirmation\n        > (e.g., \"I confirm\") before I proceed:\n        >\n        > *   **Prompt ID**: `prompt_12345abc`\n        > *   **Display Name**: `Legacy Outdated Prompt`\n        >\n        > Please type your confirmation to proceed.\n\n## Phase 0: Environment Setup\n\n**CRITICAL**: Before the user runs any of the Python snippets below, you MUST\nadvise them to ensure the environment is correctly initialized by following\nthese steps:\n\n1.  **Google Cloud Authentication**: Authenticate with your Google Cloud account\n    and configure active Application Default Credentials (ADC) for Agent\n    Platform access:\n\n    ```bash\n    gcloud auth login\n    gcloud auth application-default login\n    ```\n\n2.  **Python Dependencies**: This skill needs `google-cloud-aiplatform` and\n    `google-genai`. Do **not** create a virtual environment — it starts empty\n    and hides packages the environment already provides, forcing a redundant\n    install. Probe, and install only what is missing:\n\n    ```bash\n    python3 -c \"import vertexai, google.genai\" \\\n      || pip install google-cloud-aiplatform google-genai\n    ```\n\n3.  **Execution**: Run Python snippets with a plain `python3`. There is no\n    environment to activate first.\n\n> [!TIP]\n>\n> **Placeholder Parameter Replacement:** The Python scripts below use uppercase\n> string placeholders (like `\"PROJECT_ID\"`, `\"LOCATION_ID\"`, `\"PROMPT_ID\"`, and\n> `\"MODEL_ID\"`). You **MUST** dynamically replace these placeholders with the\n> actual Project ID, Region, Prompt ID, and target model values provided in the\n> user's prompt (or discovered context) before generating or providing the\n> scripts. If the user did not supply one of these, ask -- a placeholder is\n> never satisfied by guessing a plausible value.\n\n## 1. Managing Prompts via Agent Platform SDK\n\nThe SDK provides a high-level `Prompt` class in the preview module.\n\n### Create a Prompt (Tier M)\n\nUse when you need to create a new managed prompt in Agent Platform.\n\n*   **Reference**: See [create.md](references\u002Fcreate.md) for detailed\n    instructions and Python snippets.\n\n### List Prompts (Tier R)\n\n```python\nimport vertexai\nfrom vertexai.preview import prompts\n\nvertexai.init(project=\"PROJECT_ID\", location=\"LOCATION_ID\")\n\nall_prompts = prompts.list()\nfor p in all_prompts:\n    print(f\"Name: {p.display_name}, ID: {p.prompt_id}\")\n```\n\n### Retrieve and Use a Prompt (Tier R)\n\n```python\nimport vertexai\nfrom vertexai.preview import prompts\n\nvertexai.init(project=\"PROJECT_ID\", location=\"LOCATION_ID\")\n\nretrieved_prompt = prompts.get(prompt_id=\"PROMPT_ID\")\n# Attributes on retrieved Prompt:\n# - retrieved_prompt.prompt_id (e.g. \"123456789...\")\n# - retrieved_prompt.prompt_data (template text string)\n# - retrieved_prompt.model_name (target model)\n# - retrieved_prompt.prompt_name (display name, or\n#   retrieved_prompt._dataset.display_name)\n# Versions are supported: prompts.get(prompt_id=\"PROMPT_ID\", version_id=\"2\")\n\n# Assemble with variables (kwargs must match template variable names)\nassembled = retrieved_prompt.assemble_contents(text=\"The quick brown fox...\")\nprint(assembled)\n```\n\n### Delete a Prompt (Tier D)\n\n**CRITICAL**: You must pass the numeric prompt ID (e.g.,\n`\"1234567890123456789\"`) to `prompts.delete()`. The SDK constructs the full\nresource path internally using the project and location from `vertexai.init()`.\n\n**Confirmation Required**: As a Tier D (Destructive) operation, the agent MUST\npause and request explicit, high-friction typed re-confirmation of the prompt ID\nfrom the user before executing the deletion code. The action is irreversible.\nOnce the user replies with typed confirmation (e.g., \"I confirm\"), proceed\nimmediately to execute the deletion code via `run_command`.\n\n> [!IMPORTANT]\n>\n> **NEVER pre-emptively execute any deletion code before receiving the user's\n> response in a new turn.** You must never speculate or assume that confirmation\n> will be given. Asking for confirmation and running the code in a single\n> parallel turn is a severe safety violation.\n\n```python\nimport vertexai\nfrom vertexai.preview import prompts\n\nvertexai.init(project=\"PROJECT_ID\", location=\"LOCATION_ID\")\n\nprompts.delete(prompt_id=\"PROMPT_ID\")\n```\n\n### Verification After Deletion\n\nWhenever listing prompts or verifying state after deleting a prompt in the same\nconversation, you **MUST**:\n\n1.  Check in Python whether the deleted `prompt_id` appears in `prompts.list()`.\n2.  In your prose reply (even when the list is also shown as a card):\n    *   If it is not found, explicitly confirm: *\"I have verified that the\n        deleted prompt (ID: `\u003CPROMPT_ID>`) is no longer present in project\n        `\u003CPROJECT_ID>` (`\u003CLOCATION_ID>`).\"*\n    *   If it is still listed, report its current presence and ID to the user.\n\n## 2. Best Practices\n\n-   **Idempotency**:\n    *   **Tier R** (List, Get): Inherently idempotent.\n    *   **Tier D** (Delete): Re-running a delete on a non-existent or already\n        deleted resource returns NOT_FOUND. Treat this as success.\n-   **Placeholders**: Use the standard placeholder syntax (variable name\n    enclosed in double curly braces) in your prompt templates.\n-   **Versioning**: Always tag or record version IDs when making updates to\n    production prompts.\n-   **Model Reference**: A prompt is created against a target model ID, which\n    the snippets carry as the `\"MODEL_ID\"` placeholder. Like the other\n    placeholders it is MUST-replace, and it is replaced from what the user\n    said -- if they named no model, ask. Do not substitute a plausible current\n    model such as `gemini-2.5-pro`.\n-   **Underlying Schema**: When using the Dataset API, always use the correct\n    `metadata_schema_uri` and nested `metadata` structure to ensure the prompt\n    is recognized by Agent Platform Studio and the Prompts SDK.\n",{"name":5,"metadata":50,"description":7},{"version":51,"category":52},"1.0.1","AiAndMachineLearning","main","071c4f7eba880767a647ce778650db8dbf7e16fc","skills\u002Fcloud\u002Fagent-platform-prompt-management",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":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add google\u002Fskills --skill agent-platform-prompt-management",{"tool":68,"command":69},"bunx","bunx skills add google\u002Fskills --skill agent-platform-prompt-management",{"tool":71,"command":72},"pnpm","pnpm dlx skills add google\u002Fskills --skill agent-platform-prompt-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fagent-platform-prompt-management\u002FSKILL.md",true,[76,82],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fattribution.md","REFERENCE","参考文档",1970,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fagent-platform-prompt-management\u002Freferences\u002Fattribution.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fcreate.md",2588,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fagent-platform-prompt-management\u002Freferences\u002Fcreate.md",[87,123,151,180,207,230],{"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":99,"publishedAt":45},"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",[93,96],{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[9,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122],"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":136,"publishedAt":45},"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",[129,130,131],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":132,"categoryName":133,"taxonomyType":134,"taxonomyTypeDesc":135},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[137,138,9,108,139,140,141,142,143,144,114,145,146,147,148,149,150,119,122,27,31],"dpop adoption","adoption","es6","retry","authentication","flows","challenge","code","browser","loops","at","node","token","pair",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":163,"publishedAt":45},"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",[157,158,161,162],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":132,"categoryName":133,"taxonomyType":134,"taxonomyTypeDesc":135},[164,165,166,167,108,168,169,170,171,172,173,174,175,31,176,177,178,114,179,115],"retrieving developer knowledge","knowledge","developer","MCP","mcp server","official","developer documentation","get","search","local","choice","documents","query","api","across","documentation",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":45},"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",[],[187,188,189,190,191,192,193,194,111,195,196,197,198,199,200,173,201,202,203,31,204,205,178,206],"migrate to rust","rust","migrate","github","memory","performance","directory","safe","ports","llvm","soa","cycle","porting","fix","arrays","infographic","high-performance","URL","architecture","unrelated",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":216,"publishedAt":45},"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",[213,214,215],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":132,"categoryName":133,"taxonomyType":134,"taxonomyTypeDesc":135},[9,217,218,219,220,27,39,221,222,223,224,141,225,226,227,174,30,228,31,229,177],"finding google skills","storage","as","messaging","trade-offs","provider","answer","fit","catalog","up","decision","database","candidate",{"skillNo":231,"name":232,"nameZh":6,"description":233,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":234,"categories":235,"keywords":238,"publishedAt":45},"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",[236,237],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[239,240,118,241,9,167,242,108,168,243,244,245,246,31,34,177,114,41,247,248,249],"workload manager basics","workload","basics","cli","review","vpc","resources","inspect","libraries","server","run"]