[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D5KGCMHXACG1KEY6GF0YSF":3,"skill-same:01M7D5KGCMHXACG1KEY6GF0YSF":120},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":29,"commitSha":30,"skillDirectory":5,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7D5KGCMHXACG1KEY6GF0YSF","application-design-center-design-deploy",null,"Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment failures. Boundaries: - Only use for GCP-specific cloud infrastructure. - Only use for Terraform coding within the ADC context.","tangyixiao\u002Ftangyixiao-skills","tangyixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115929632?v=4","01M7D582YK6A4M63CAK4CSY4EW","Tang Yixiao","01M7D582Z64DMRSYR872SR34SA",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: application-design-center-design-deploy\ndescription: 'Processes GCP infrastructure design and deployment workflows within\n  Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform.\n  - Validating local HCL. - Performing best-practice plan scans. - Importing templates\n  to Application Design Center (ADC). - Deploying templates. - Troubleshooting deployment\n  failures. Boundaries: - Only use for GCP-specific cloud infrastructure. - Only use\n  for Terraform coding within the ADC context.'\nlicense: Apache-2.0\nmetadata:\n  version: 1.0.1\n  publisher: google\n  category: CloudInfrastructure\n---\n\n# Designing and Deploying GCP Infrastructure with Application Design Center\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:application-design-center-design-deploy)\"`\nand append `agent-skills\u002F1.0 (skill:application-design-center-design-deploy)` to `User-Agent` headers.\n\n## Overview\n\nThis skill provides a prescriptive, production-grade workflow for the entire\ninfrastructure lifecycle on Google Cloud Platform (GCP). It replaces the\nautomated, opaque-box GAD `design_infra` tool with an **agent-controlled design\nand validation loop** utilizing modular Terraform and local CLI validation,\nfollowed by a **shifted-left best practices plan scan** prior to synchronization\nwith the Application Design Center (ADC) registry for deployment and lifecycle\nmanagement.\n\nAlways maintain the persona of a Principal Cloud Architect. Keep the local\nTerraform configuration as the source of truth, and ensure the design is fully\ncompliant with best practices before importing it into the cloud registry.\n\n--------------------------------------------------------------------------------\n\n## Index\n\n1.  [Pre-requisites: Setup & Confirmation](#pre-requisites-setup-confirmation)\n2.  [Phase 1: Local Infrastructure Design & Validation](#phase-1-local-infrastructure-design-validation)\n3.  [Phase 2: Shifted-Left Best Practices Assessment & Iterative Remediation](#phase-2-shifted-left-best-practices-assessment-iterative-remediation)\n4.  [Phase 3: Import IaC to Application Design Center](#phase-3-import-iac-to-application-design-center)\n5.  [Phase 4: Application Deployment & Monitoring](#phase-4-application-deployment-monitoring)\n6.  [Phase 5: Troubleshoot Deployment Failures](#phase-5-troubleshoot-deployment-failures)\n7.  [Phase 6: Verification & E2E Testing](#phase-6-verification-e2e-testing)\n\n--------------------------------------------------------------------------------\n\n## Pre-requisites: Setup & Confirmation\n\nBefore executing Phase 1, you **must** perform the following setup steps:\n\n1.  **Confirm Target Project & Location**:\n\n    *   Explicitly ask the user to confirm the target GCP **project ID** and\n        **location** (region).\n    *   If the user does not specify a location, use **`us-central1`** as the\n        default.\n    *   Verify that your local environment has the active project set:\n\n        ```bash\n        gcloud config set project \u003Cproject_id>\n        ```\n\n--------------------------------------------------------------------------------\n\n## Phase 1: Local Infrastructure Design & Validation\n\n**Goal**: Transform user requirements and codebase characteristics into a 100%\nvalidated, secure, and compile-ready Terraform configuration locally.\n\n1.  **Invoke the `design` Skill**: Call and execute the `design` skill (defined\n    in [design](references\u002Fdesign_guide.md))\n    for the user's prompt.\n    *   The `design` skill will autonomously perform the Codebase Analysis,\n        query the catalog registry, planning, HCL generation, and local CLI\n        validation loop (`terraform init`, `validate`, `plan`) in a dedicated\n        scratch directory.\n2.  **Locate Validated HCL**: Identify the scratch directory where the `design`\n    skill saved the validated, compile-ready Terraform files (e.g.,\n    `scratch\u002Ftf_validate_\u003Csession_id>\u002F`).\n3.  **Verify Handover (MANDATORY)**: Ensure that the local validation loop in\n    the `design` skill completed successfully with a clean plan before\n    proceeding. Meticulously inspect the HCL to verify:\n    *   **Secret-Safe Policy**: Confirm that no plaintext credentials,\n        passwords, or hardcoded secrets are written in `terraform.tfvars` or HCL\n        resource blocks. All sensitive inputs must be wired through GCP Secret\n        Manager.\n    *   **State Isolation Policy**: Confirm that there is no remote backend\n        block (e.g., `backend \"gcs\" {}`) in the HCL files. State must remain\n        local in the scratch folder during validation, allowing ADC to handle\n        the remote state registry upon import.\n    *   *Remediation*: If any violations are found, correct them in the HCL,\n        re-run local validation, and verify again. Do not proceed with\n        unvalidated or insecure code.\n4.  **Export Terraform Plan to JSON (MANDATORY)**: In the scratch directory, run\n    the following commands to generate a binary plan and convert it into a clean\n    JSON representation:\n\n    ```bash\n    terraform plan -out=tfplan && terraform show -json tfplan > tfplan.json\n    ```\n\n    Verify that the `tfplan.json` file is successfully written in your scratch\n    directory.\n\n--------------------------------------------------------------------------------\n\n## Phase 2: Shifted-Left Best Practices Assessment & Iterative Remediation\n\n**Goal**: Validate the local plan's alignment with security, cost, and\nreliability benchmarks BEFORE importing it into the cloud registry, using the\nnative ADC plan assessment API.\n\n1.  **Discover Space ID (MANDATORY)**: Before running the assessment or creating\n    templates, you **must** dynamically discover the active ADC Space ID in your\n    target location:\n\n    *   **List Spaces**: Run the command:\n\n        ```bash\n        gcloud design-center spaces list --project=\u003Cproject_id> --location=\u003Clocation>\n        ```\n\n    *   **Select Space**: Parse the output to identify the active space (e.g.,\n        `test-deploy` or `googlespace`). If multiple spaces exist, ask the user\n        to confirm. If no space exists, ask the user or create one:\n\n        ```bash\n        gcloud design-center spaces create \u003Cspace_id> --project=\u003Cproject_id> --location=\u003Clocation>\n        ```\n\n2.  **Execute Plan Assessment via gcloud**: Run the plan-based assessment using\n    the discovered Space ID and your exported `tfplan.json` file. Execute the\n    command directly in your terminal:\n\n    ```bash\n    gcloud design-center spaces generate-terraform-assessment-report \u003Cspace_id> \\\n        --location=\u003Clocation> \\\n        --project=\u003Cproject_id> \\\n        --terraform-plan=\"\u003Cscratch_directory_path>\u002Ftfplan.json\" \\\n        --format=json\n    ```\n\n3.  **Analyze Findings**: Present all findings to the user in a clean tabular\n    format, detailing specific violations, resource scopes, and associated\n    severity levels.\n\n4.  **Local Remediation Loop**:\n\n    *   **Do not** attempt to import or commit insecure code.\n    *   Edit your **local HCL files** in the scratch directory to fix the\n        reported violations (e.g., adding encryption keys, enabling OS Login, or\n        restricting IAM scopes).\n    *   Re-run Phase 1 local validation and plan export:\n\n        ```bash\n        terraform validate && terraform plan -out=tfplan && terraform show -json tfplan > tfplan.json\n        ```\n\n    *   Re-run the plan assessment command shown in step 2.\n\n5.  **Exit Criteria**:\n\n    *   All high\u002Fcritical findings resolved, or acceptable trade-offs\n        documented.\n    *   Maximum of three (3) iterative attempts reached. Once clean or\n        acceptable, proceed to Phase 3.\n\n--------------------------------------------------------------------------------\n\n## Phase 3: Import IaC to Application Design Center\n\n**Goal**: Synchronize the fully validated and best-practice-compliant local HCL\nconfiguration with the ADC cloud registry to establish the deployable template\nresource.\n\n1.  **Verify or Create the Application Template (MANDATORY)**: Before importing\n    the HCL, you **must** ensure the parent Application Template resource exists\n    in the discovered ADC space.\n\n    *   **Check Existence**: Run `gcloud design-center spaces\n        application-templates describe \u003Ctemplate_id> --space=\u003Cspace_id>\n        --project=\u003Cproject_id> --location=\u003Clocation>` to check if the template\n        exists.\n    *   **Create if Missing**: If the describe command returns a `NOT_FOUND`\n        error, create the template resource first by running:\n\n        ```bash\n        gcloud design-center spaces application-templates create \u003Ctemplate_id> --space=\u003Cspace_id> --project=\u003Cproject_id> --location=\u003Clocation> --display-name=\"\u003CName>\" --description=\"\u003CDescription>\"\n        ```\n\n2.  **Strict HCL Parser Constraints (CRITICAL):** Before calling the import\n    operation, ensure your local HCL complies with the ADC registry's strict\n    ingestion rules:\n\n    *   **Pure Module Policy (No Resource Blocks):** The ADC parser strictly\n        **prohibits any `resource` blocks** inside the imported HCL. Only\n        `module`, `variable`, `output`, and `provider` blocks are allowed. If a\n        resource is required (e.g. Private Service Access peering) but no\n        standalone module is registered for it in the catalog, you MUST check if\n        it is supported as a built-in configuration option inside an existing\n        registered module (e.g. setting `private_service_access_config` inside\n        `module \"vpc\"`).\n    *   **Strict String Typing:** The ADC parser does not perform implicit type\n        coercion from boolean to string. For example, subnet private access must\n        be declared as a literal string: `subnet_private_access = \"true\"`, NOT\n        as a boolean `true`.\n    *   **No Terraform Block:** The parser strictly prohibits the `terraform {}`\n        version constraint block. Omit it entirely from `providers.tf` or\n        `main.tf`.\n\n3.  **Import to ADC Template**: Once the template resource is confirmed to exist\n    and the HCL is validated against the above constraints, invoke the hosted\n    `application_design_center:manage_application_template` MCP tool with the\n    `APPLICATION_TEMPLATE_OPERATION_IMPORT_IAC` operation:\n\n    *   **Arguments**:\n\n        *   `project`: The target project ID.\n        *   `location`: The GCP deployment region (e.g., `us-central1`).\n        *   `spaceId`: The discovered ADC space ID.\n        *   `applicationTemplateId`: A unique name for your application\n            template.\n        *   `operation`: `APPLICATION_TEMPLATE_OPERATION_IMPORT_IAC`\n        *   `iacModule`: A structured object containing the files list:\n\n            ```json\n            {\n              \"files\": [\n                { \"name\": \"main.tf\", \"content\": \"\u003Ccontent of main.tf>\" },\n                { \"name\": \"variables.tf\", \"content\": \"\u003Ccontent of variables.tf>\" },\n                { \"name\": \"terraform.tfvars\", \"content\": \"\u003Ccontent of terraform.tfvars>\" }\n              ]\n            }\n            ```\n\n    *   **Resilience & Retries (MANDATORY)**:\n\n        *   If the `IMPORT_IAC` call fails due to a transient error (e.g., `502\n            Bad Gateway`, `504 Gateway Timeout`, or `429 Rate Limit`), **do not\n            immediately retry**.\n        *   Use **exponential backoff with jitter** (e.g., waiting 2s, 4s, 8s\n            plus a random fraction of a second).\n        *   **Verify Revision before Retry**: If a timeout occurred, first call\n            `gcloud alpha design-center spaces application-templates describe`\n            to check if the import actually succeeded in the background. Only\n            retry if the template was not updated.\n\n4.  **Capture Template URI**: Upon success, this establishes the template\n    resource in your space. Construct the `applicationTemplateUri` using the\n    pattern:\n    `projects\u002F{project}\u002Flocations\u002F{location}\u002Fspaces\u002F{spaceId}\u002FapplicationTemplates\u002F{applicationTemplateId}`\n\n--------------------------------------------------------------------------------\n\n## Phase 4: Application Deployment & Monitoring\n\n**Goal**: Deploy the validated, best-practice-compliant application template to\nthe GCP environment.\n\n1.  **Deploy Application**: Invoke the hosted\n    `application_design_center:manage_application` MCP tool with the\n    `APPLICATION_OPERATION_DEPLOY` operation:\n    *   **Arguments**:\n        *   `project`: Target project ID.\n        *   `location`: Target deployment location.\n        *   `spaceId`: Target space ID.\n        *   `applicationId`: A unique ID for the deployed application instance.\n        *   `applicationTemplateUri`: The URI established in Phase 3.\n        *   `serviceAccount`: The deployment service account.\n    *   **Resilience & Retries (MANDATORY)**:\n        *   If the `DEPLOY` operation fails with transient network or gateway\n            errors (e.g., `502`, `504`), apply **exponential backoff with\n            jitter** before retrying.\n        *   If the deployment LRO times out or fails with a state conflict,\n            verify the application status using `gcloud design-center spaces\n            applications describe` to confirm its status before retrying the\n            deploy call, avoiding concurrent conflicting deployments.\n2.  **Active LRO Monitoring**:\n    *   The tool returns a Long-Running Operation (LRO). Inform the user that\n        the deployment has started.\n    *   **Do not sleep** during deployment status polling. Poll the LRO actively\n        every 30–60 seconds until `done: true` using the command `gcloud\n        design-center operations describe \u003Coperation_name>`.\n3.  **Handle Results**:\n    *   **Success**: If `done` is `true` and there is no `error` field, proceed\n        to Phase 6.\n    *   **Failure**: If an `error` field is present, analyze the error type and\n        proceed to Phase 5.\n\n--------------------------------------------------------------------------------\n\n## Phase 5: Troubleshoot Deployment Failures\n\n**Goal**: Diagnose and remediate deployment failures iteratively using the\nspecialized troubleshooting skill and established cloud resolution patterns.\n\n1.  **Iterative Cloud Resolution Patterns (CRITICAL):** If the deployment fails\n    with a `REVISION_FAILED` or `TERRAFORM` error, check for these common\n    resource conflicts:\n\n    *   **Service Account 409 Conflict (`alreadyExists`):** If the deployment\n        fails because a service account generated by the module (e.g.\n        `frontend-service-us-central-sa`) already exists in the project,\n        remediate the local HCL by disabling service account creation and\n        referencing the existing one:\n\n        ```hcl\n        create_service_account = false\n        service_account        = \"\u003Cexisting_service_account_email>\"\n        ```\n\n    *   **Container Image 404 NotFound:** If the deployment fails because a\n        container image is not found, confirm that the image exists in your\n        registry. For testing or hello-world deployments, leverage the official\n        public Google hello-world image:\n        `us-docker.pkg.dev\u002Fcloudrun\u002Fcontainer\u002Fhello`\n\n2.  **Delegate to the Troubleshooting Skill**: If a deployment failure occurs\n    and does not match the above patterns, invoke and execute the specialized\n    `infra-deployment-debugging` guide (located in\n    [infra-deployment-debugging](references\u002Ftroubleshooting_guide.md)).\n\n3.  **Select the Troubleshooting Context**:\n\n    *   **For Local Validation Errors (Phase 1\u002F2)**: Follow **Case B: Raw\n        Terraform Deployment** instructions in the troubleshooting skill to\n        isolate syntax, compilation, and plan-time validation errors.\n    *   **For Cloud Deployment Failures (Phase 4)**: Follow **Case A: ADC\n        Application Deployment** instructions in the troubleshooting skill to\n        analyze LRO errors, retrieve service logs, and diagnose cloud\n        environment issues.\n\n4.  **Apply Local-First Remediation**:\n\n    *   Follow the troubleshooting skill's remediation guides to formulate a\n        fix.\n    *   **MANDATORY**: Apply the fix directly to your **local HCL files** in the\n        scratch directory, re-run local validation, re-import the HCL, and\n        trigger a new deployment.\n    *   Re-run Phase 1 local validation and plan export:\n\n        ```bash\n        terraform validate && terraform plan -out=tfplan && terraform show -json tfplan > tfplan.json\n        ```\n\n    *   Re-run the plan assessment (Phase 2) to ensure no new violations are\n        introduced.\n\n    *   Re-import the corrected HCL to ADC using\n        `APPLICATION_TEMPLATE_OPERATION_IMPORT_IAC`.\n\n    *   Trigger a new deployment using `APPLICATION_OPERATION_DEPLOY`.\n\n5.  **Iteration Threshold**: Repeat the troubleshooting, validation, import, and\n    redeployment cycle up to five (5) times. If it still fails, report the full\n    history and diagnostics to the user.\n\n--------------------------------------------------------------------------------\n\n## Phase 6: Verification & E2E Testing\n\n**Goal**: Confirm that the deployed services are healthy and fully functional.\n\n1.  **Retrieve Deployed Resources**: Invoke the hosted\n    `application_design_center:manage_application` MCP tool with the\n    `APPLICATION_OPERATION_GET` operation to retrieve the resource details,\n    public endpoints, and output parameters.\n2.  **Health Check**: Verify that all services are using the correct container\n    image URLs and that their runtime status is healthy.\n3.  **E2E Validation**: Conduct a simple demo test (e.g., checking public HTTP\n    endpoints or triggering a dry-run transaction) to ensure E2E functionality.\n    Present the results and public URLs to the user to conclude the task.\n\n## Reporting Issues\n\nReport bugs or improvements for this skill at [Google Skills Issues](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fissues).\n","# Designing and Deploying GCP Infrastructure with Application Design Center\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:application-design-center-design-deploy)\"`\nand append `agent-skills\u002F1.0 (skill:application-design-center-design-deploy)` to `User-Agent` headers.\n\n## Overview\n\nThis skill provides a prescriptive, production-grade workflow for the entire\ninfrastructure lifecycle on Google Cloud Platform (GCP). It replaces the\nautomated, opaque-box GAD `design_infra` tool with an **agent-controlled design\nand validation loop** utilizing modular Terraform and local CLI validation,\nfollowed by a **shifted-left best practices plan scan** prior to synchronization\nwith the Application Design Center (ADC) registry for deployment and lifecycle\nmanagement.\n\nAlways maintain the persona of a Principal Cloud Architect. Keep the local\nTerraform configuration as the source of truth, and ensure the design is fully\ncompliant with best practices before importing it into the cloud registry.\n\n--------------------------------------------------------------------------------\n\n## Index\n\n1.  [Pre-requisites: Setup & Confirmation](#pre-requisites-setup-confirmation)\n2.  [Phase 1: Local Infrastructure Design & Validation](#phase-1-local-infrastructure-design-validation)\n3.  [Phase 2: Shifted-Left Best Practices Assessment & Iterative Remediation](#phase-2-shifted-left-best-practices-assessment-iterative-remediation)\n4.  [Phase 3: Import IaC to Application Design Center](#phase-3-import-iac-to-application-design-center)\n5.  [Phase 4: Application Deployment & Monitoring](#phase-4-application-deployment-monitoring)\n6.  [Phase 5: Troubleshoot Deployment Failures](#phase-5-troubleshoot-deployment-failures)\n7.  [Phase 6: Verification & E2E Testing](#phase-6-verification-e2e-testing)\n\n--------------------------------------------------------------------------------\n\n## Pre-requisites: Setup & Confirmation\n\nBefore executing Phase 1, you **must** perform the following setup steps:\n\n1.  **Confirm Target Project & Location**:\n\n    *   Explicitly ask the user to confirm the target GCP **project ID** and\n        **location** (region).\n    *   If the user does not specify a location, use **`us-central1`** as the\n        default.\n    *   Verify that your local environment has the active project set:\n\n        ```bash\n        gcloud config set project \u003Cproject_id>\n        ```\n\n--------------------------------------------------------------------------------\n\n## Phase 1: Local Infrastructure Design & Validation\n\n**Goal**: Transform user requirements and codebase characteristics into a 100%\nvalidated, secure, and compile-ready Terraform configuration locally.\n\n1.  **Invoke the `design` Skill**: Call and execute the `design` skill (defined\n    in [design](references\u002Fdesign_guide.md))\n    for the user's prompt.\n    *   The `design` skill will autonomously perform the Codebase Analysis,\n        query the catalog registry, planning, HCL generation, and local CLI\n        validation loop (`terraform init`, `validate`, `plan`) in a dedicated\n        scratch directory.\n2.  **Locate Validated HCL**: Identify the scratch directory where the `design`\n    skill saved the validated, compile-ready Terraform files (e.g.,\n    `scratch\u002Ftf_validate_\u003Csession_id>\u002F`).\n3.  **Verify Handover (MANDATORY)**: Ensure that the local validation loop in\n    the `design` skill completed successfully with a clean plan before\n    proceeding. Meticulously inspect the HCL to verify:\n    *   **Secret-Safe Policy**: Confirm that no plaintext credentials,\n        passwords, or hardcoded secrets are written in `terraform.tfvars` or HCL\n        resource blocks. All sensitive inputs must be wired through GCP Secret\n        Manager.\n    *   **State Isolation Policy**: Confirm that there is no remote backend\n        block (e.g., `backend \"gcs\" {}`) in the HCL files. State must remain\n        local in the scratch folder during validation, allowing ADC to handle\n        the remote state registry upon import.\n    *   *Remediation*: If any violations are found, correct them in the HCL,\n        re-run local validation, and verify again. Do not proceed with\n        unvalidated or insecure code.\n4.  **Export Terraform Plan to JSON (MANDATORY)**: In the scratch directory, run\n    the following commands to generate a binary plan and convert it into a clean\n    JSON representation:\n\n    ```bash\n    terraform plan -out=tfplan && terraform show -json tfplan > tfplan.json\n    ```\n\n    Verify that the `tfplan.json` file is successfully written in your scratch\n    directory.\n\n--------------------------------------------------------------------------------\n\n## Phase 2: Shifted-Left Best Practices Assessment & Iterative Remediation\n\n**Goal**: Validate the local plan's alignment with security, cost, and\nreliability benchmarks BEFORE importing it into the cloud registry, using the\nnative ADC plan assessment API.\n\n1.  **Discover Space ID (MANDATORY)**: Before running the assessment or creating\n    templates, you **must** dynamically discover the active ADC Space ID in your\n    target location:\n\n    *   **List Spaces**: Run the command:\n\n        ```bash\n        gcloud design-center spaces list --project=\u003Cproject_id> --location=\u003Clocation>\n        ```\n\n    *   **Select Space**: Parse the output to identify the active space (e.g.,\n        `test-deploy` or `googlespace`). If multiple spaces exist, ask the user\n        to confirm. If no space exists, ask the user or create one:\n\n        ```bash\n        gcloud design-center spaces create \u003Cspace_id> --project=\u003Cproject_id> --location=\u003Clocation>\n        ```\n\n2.  **Execute Plan Assessment via gcloud**: Run the plan-based assessment using\n    the discovered Space ID and your exported `tfplan.json` file. Execute the\n    command directly in your terminal:\n\n    ```bash\n    gcloud design-center spaces generate-terraform-assessment-report \u003Cspace_id> \\\n        --location=\u003Clocation> \\\n        --project=\u003Cproject_id> \\\n        --terraform-plan=\"\u003Cscratch_directory_path>\u002Ftfplan.json\" \\\n        --format=json\n    ```\n\n3.  **Analyze Findings**: Present all findings to the user in a clean tabular\n    format, detailing specific violations, resource scopes, and associated\n    severity levels.\n\n4.  **Local Remediation Loop**:\n\n    *   **Do not** attempt to import or commit insecure code.\n    *   Edit your **local HCL files** in the scratch directory to fix the\n        reported violations (e.g., adding encryption keys, enabling OS Login, or\n        restricting IAM scopes).\n    *   Re-run Phase 1 local validation and plan export:\n\n        ```bash\n        terraform validate && terraform plan -out=tfplan && terraform show -json tfplan > tfplan.json\n        ```\n\n    *   Re-run the plan assessment command shown in step 2.\n\n5.  **Exit Criteria**:\n\n    *   All high\u002Fcritical findings resolved, or acceptable trade-offs\n        documented.\n    *   Maximum of three (3) iterative attempts reached. Once clean or\n        acceptable, proceed to Phase 3.\n\n--------------------------------------------------------------------------------\n\n## Phase 3: Import IaC to Application Design Center\n\n**Goal**: Synchronize the fully validated and best-practice-compliant local HCL\nconfiguration with the ADC cloud registry to establish the deployable template\nresource.\n\n1.  **Verify or Create the Application Template (MANDATORY)**: Before importing\n    the HCL, you **must** ensure the parent Application Template resource exists\n    in the discovered ADC space.\n\n    *   **Check Existence**: Run `gcloud design-center spaces\n        application-templates describe \u003Ctemplate_id> --space=\u003Cspace_id>\n        --project=\u003Cproject_id> --location=\u003Clocation>` to check if the template\n        exists.\n    *   **Create if Missing**: If the describe command returns a `NOT_FOUND`\n        error, create the template resource first by running:\n\n        ```bash\n        gcloud design-center spaces application-templates create \u003Ctemplate_id> --space=\u003Cspace_id> --project=\u003Cproject_id> --location=\u003Clocation> --display-name=\"\u003CName>\" --description=\"\u003CDescription>\"\n        ```\n\n2.  **Strict HCL Parser Constraints (CRITICAL):** Before calling the import\n    operation, ensure your local HCL complies with the ADC registry's strict\n    ingestion rules:\n\n    *   **Pure Module Policy (No Resource Blocks):** The ADC parser strictly\n        **prohibits any `resource` blocks** inside the imported HCL. Only\n        `module`, `variable`, `output`, and `provider` blocks are allowed. If a\n        resource is required (e.g. Private Service Access peering) but no\n        standalone module is registered for it in the catalog, you MUST check if\n        it is supported as a built-in configuration option inside an existing\n        registered module (e.g. setting `private_service_access_config` inside\n        `module \"vpc\"`).\n    *   **Strict String Typing:** The ADC parser does not perform implicit type\n        coercion from boolean to string. For example, subnet private access must\n        be declared as a literal string: `subnet_private_access = \"true\"`, NOT\n        as a boolean `true`.\n    *   **No Terraform Block:** The parser strictly prohibits the `terraform {}`\n        version constraint block. Omit it entirely from `providers.tf` or\n        `main.tf`.\n\n3.  **Import to ADC Template**: Once the template resource is confirmed to exist\n    and the HCL is validated against the above constraints, invoke the hosted\n    `application_design_center:manage_application_template` MCP tool with the\n    `APPLICATION_TEMPLATE_OPERATION_IMPORT_IAC` operation:\n\n    *   **Arguments**:\n\n        *   `project`: The target project ID.\n        *   `location`: The GCP deployment region (e.g., `us-central1`).\n        *   `spaceId`: The discovered ADC space ID.\n        *   `applicationTemplateId`: A unique name for your application\n            template.\n        *   `operation`: `APPLICATION_TEMPLATE_OPERATION_IMPORT_IAC`\n        *   `iacModule`: A structured object containing the files list:\n\n            ```json\n            {\n              \"files\": [\n                { \"name\": \"main.tf\", \"content\": \"\u003Ccontent of main.tf>\" },\n                { \"name\": \"variables.tf\", \"content\": \"\u003Ccontent of variables.tf>\" },\n                { \"name\": \"terraform.tfvars\", \"content\": \"\u003Ccontent of terraform.tfvars>\" }\n              ]\n            }\n            ```\n\n    *   **Resilience & Retries (MANDATORY)**:\n\n        *   If the `IMPORT_IAC` call fails due to a transient error (e.g., `502\n            Bad Gateway`, `504 Gateway Timeout`, or `429 Rate Limit`), **do not\n            immediately retry**.\n        *   Use **exponential backoff with jitter** (e.g., waiting 2s, 4s, 8s\n            plus a random fraction of a second).\n        *   **Verify Revision before Retry**: If a timeout occurred, first call\n            `gcloud alpha design-center spaces application-templates describe`\n            to check if the import actually succeeded in the background. Only\n            retry if the template was not updated.\n\n4.  **Capture Template URI**: Upon success, this establishes the template\n    resource in your space. Construct the `applicationTemplateUri` using the\n    pattern:\n    `projects\u002F{project}\u002Flocations\u002F{location}\u002Fspaces\u002F{spaceId}\u002FapplicationTemplates\u002F{applicationTemplateId}`\n\n--------------------------------------------------------------------------------\n\n## Phase 4: Application Deployment & Monitoring\n\n**Goal**: Deploy the validated, best-practice-compliant application template to\nthe GCP environment.\n\n1.  **Deploy Application**: Invoke the hosted\n    `application_design_center:manage_application` MCP tool with the\n    `APPLICATION_OPERATION_DEPLOY` operation:\n    *   **Arguments**:\n        *   `project`: Target project ID.\n        *   `location`: Target deployment location.\n        *   `spaceId`: Target space ID.\n        *   `applicationId`: A unique ID for the deployed application instance.\n        *   `applicationTemplateUri`: The URI established in Phase 3.\n        *   `serviceAccount`: The deployment service account.\n    *   **Resilience & Retries (MANDATORY)**:\n        *   If the `DEPLOY` operation fails with transient network or gateway\n            errors (e.g., `502`, `504`), apply **exponential backoff with\n            jitter** before retrying.\n        *   If the deployment LRO times out or fails with a state conflict,\n            verify the application status using `gcloud design-center spaces\n            applications describe` to confirm its status before retrying the\n            deploy call, avoiding concurrent conflicting deployments.\n2.  **Active LRO Monitoring**:\n    *   The tool returns a Long-Running Operation (LRO). Inform the user that\n        the deployment has started.\n    *   **Do not sleep** during deployment status polling. Poll the LRO actively\n        every 30–60 seconds until `done: true` using the command `gcloud\n        design-center operations describe \u003Coperation_name>`.\n3.  **Handle Results**:\n    *   **Success**: If `done` is `true` and there is no `error` field, proceed\n        to Phase 6.\n    *   **Failure**: If an `error` field is present, analyze the error type and\n        proceed to Phase 5.\n\n--------------------------------------------------------------------------------\n\n## Phase 5: Troubleshoot Deployment Failures\n\n**Goal**: Diagnose and remediate deployment failures iteratively using the\nspecialized troubleshooting skill and established cloud resolution patterns.\n\n1.  **Iterative Cloud Resolution Patterns (CRITICAL):** If the deployment fails\n    with a `REVISION_FAILED` or `TERRAFORM` error, check for these common\n    resource conflicts:\n\n    *   **Service Account 409 Conflict (`alreadyExists`):** If the deployment\n        fails because a service account generated by the module (e.g.\n        `frontend-service-us-central-sa`) already exists in the project,\n        remediate the local HCL by disabling service account creation and\n        referencing the existing one:\n\n        ```hcl\n        create_service_account = false\n        service_account        = \"\u003Cexisting_service_account_email>\"\n        ```\n\n    *   **Container Image 404 NotFound:** If the deployment fails because a\n        container image is not found, confirm that the image exists in your\n        registry. For testing or hello-world deployments, leverage the official\n        public Google hello-world image:\n        `us-docker.pkg.dev\u002Fcloudrun\u002Fcontainer\u002Fhello`\n\n2.  **Delegate to the Troubleshooting Skill**: If a deployment failure occurs\n    and does not match the above patterns, invoke and execute the specialized\n    `infra-deployment-debugging` guide (located in\n    [infra-deployment-debugging](references\u002Ftroubleshooting_guide.md)).\n\n3.  **Select the Troubleshooting Context**:\n\n    *   **For Local Validation Errors (Phase 1\u002F2)**: Follow **Case B: Raw\n        Terraform Deployment** instructions in the troubleshooting skill to\n        isolate syntax, compilation, and plan-time validation errors.\n    *   **For Cloud Deployment Failures (Phase 4)**: Follow **Case A: ADC\n        Application Deployment** instructions in the troubleshooting skill to\n        analyze LRO errors, retrieve service logs, and diagnose cloud\n        environment issues.\n\n4.  **Apply Local-First Remediation**:\n\n    *   Follow the troubleshooting skill's remediation guides to formulate a\n        fix.\n    *   **MANDATORY**: Apply the fix directly to your **local HCL files** in the\n        scratch directory, re-run local validation, re-import the HCL, and\n        trigger a new deployment.\n    *   Re-run Phase 1 local validation and plan export:\n\n        ```bash\n        terraform validate && terraform plan -out=tfplan && terraform show -json tfplan > tfplan.json\n        ```\n\n    *   Re-run the plan assessment (Phase 2) to ensure no new violations are\n        introduced.\n\n    *   Re-import the corrected HCL to ADC using\n        `APPLICATION_TEMPLATE_OPERATION_IMPORT_IAC`.\n\n    *   Trigger a new deployment using `APPLICATION_OPERATION_DEPLOY`.\n\n5.  **Iteration Threshold**: Repeat the troubleshooting, validation, import, and\n    redeployment cycle up to five (5) times. If it still fails, report the full\n    history and diagnostics to the user.\n\n--------------------------------------------------------------------------------\n\n## Phase 6: Verification & E2E Testing\n\n**Goal**: Confirm that the deployed services are healthy and fully functional.\n\n1.  **Retrieve Deployed Resources**: Invoke the hosted\n    `application_design_center:manage_application` MCP tool with the\n    `APPLICATION_OPERATION_GET` operation to retrieve the resource details,\n    public endpoints, and output parameters.\n2.  **Health Check**: Verify that all services are using the correct container\n    image URLs and that their runtime status is healthy.\n3.  **E2E Validation**: Conduct a simple demo test (e.g., checking public HTTP\n    endpoints or triggering a dry-run transaction) to ensure E2E functionality.\n    Present the results and public URLs to the user to conclude the task.\n\n## Reporting Issues\n\nReport bugs or improvements for this skill at [Google Skills Issues](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fissues).\n",{"name":5,"license":15,"metadata":25,"description":7},{"version":26,"category":27,"publisher":28},"1.0.1","CloudInfrastructure","google","main","2a870f189175a48c39f5f7e26a6d93b0be9cd13b",0,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills","https:\u002F\u002Ftangyixiao.github.io\u002Ftangyixiao-skills\u002F","https:\u002F\u002Fgithub.com\u002Ftangyixiao","http:\u002F\u002Fwww.sxyz.net\u002F","I am Tang Yixiao, a student in Shaoxing No.1 High School. I am eager to learn on GitHub and contribute my part to this community.","2026-11-11 15:45:59",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill application-design-center-design-deploy",{"tool":44,"command":45},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill application-design-center-design-deploy",{"tool":47,"command":48},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill application-design-center-design-deploy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002FSKILL.md",true,[52,58,62,66,70,74,78,82,86,90,94,98,102,108,112,116],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"INSTALL-SOURCE.json","REFERENCE","参考文档",577,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002FINSTALL-SOURCE.json",{"path":59,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":16},"LICENSE","许可证",11358,{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fadc_application_troubleshooting.md",6777,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fadc_application_troubleshooting.md",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fattribution.md",1957,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fattribution.md",{"path":71,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fdesign_guide.md",14601,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fdesign_guide.md",{"path":75,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Ferror_analysis_guide.md",6749,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Ferror_analysis_guide.md",{"path":79,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fgenerator_instructions.md",8582,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fgenerator_instructions.md",{"path":83,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fplanner_instructions.md",2770,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fplanner_instructions.md",{"path":87,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fraw_terraform_troubleshooting.md",4376,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fraw_terraform_troubleshooting.md",{"path":91,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fremediation_guide.md",4386,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fremediation_guide.md",{"path":95,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fterraform_validator_instructions.md",2551,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Fterraform_validator_instructions.md",{"path":99,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Ftroubleshooting_guide.md",2651,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Freferences\u002Ftroubleshooting_guide.md",{"path":103,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Ffetch_terraform_template_test.py","SCRIPT","脚本",1411,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Fscripts\u002Ffetch_terraform_template_test.py",{"path":109,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Ffetch_terraform_template.py",10076,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Fscripts\u002Ffetch_terraform_template.py",{"path":113,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Flist_terraform_templates_test.py",960,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Fscripts\u002Flist_terraform_templates_test.py",{"path":117,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Flist_terraform_templates.py",4125,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fapplication-design-center-design-deploy\u002Fscripts\u002Flist_terraform_templates.py",[121,129,138,146,154,162],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":20},"01M7D8JK8FYBFNNAJXWD89CFH7","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":20},"01M7D8JG8ERGGQQAMX0DWCG9GR","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","MIT","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":142,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":20},"01M7D8JE672GW3EHSE8EF185M4","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":150,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":20},"01M7D8JBK572YDFMND8Q6CEYJW","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":158,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":20},"01M7D8J5QPWEXX61EGBKYH73R8","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[],[],{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":166,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":20},"01M7D8J36YWC8WZS5DK5AH03CD","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fwriting-beats\u002FSKILL.md",[],[]]