[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D5WTPSMKHPTS7ST0THC218":3,"skill-same:01M7D5WTPSMKHPTS7ST0THC218":97},{"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":28,"commitSha":29,"skillDirectory":5,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7D5WTPSMKHPTS7ST0THC218","bigquery-optimization",null,"Provides workflows to optimize BigQuery environments (capacity planning, editions), storage assets (partitioning, clustering, storage lifecycles, billing models), and SQL queries. Use when optimizing cost, modeling Edition migrations, rightsizing reservations, evaluating logical vs. physical storage, designing table partitioning\u002Fclustering, generating table DDL, migrating unpartitioned tables, managing partition expiration, optimizing individual SQL queries, or evaluating acceleration structures (search indexes, materialized views, BI Engine).\nDo not use for raw usage reporting (use bigquery-observability), query execution plan analysis, error troubleshooting, or diagnosing why a specific job was slow (use bigquery-troubleshooting).","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\u002Fbigquery-optimization\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bigquery-optimization\nmetadata:\n  version: 1.1.1\n  category: BigDataAndAnalytics\ndescription: 'Provides workflows to optimize BigQuery environments (capacity planning,\n  editions), storage assets (partitioning, clustering, storage lifecycles, billing\n  models), and SQL queries. Use when optimizing cost, modeling Edition migrations,\n  rightsizing reservations, evaluating logical vs. physical storage, designing table\n  partitioning\u002Fclustering, generating table DDL, migrating unpartitioned tables, managing\n  partition expiration, optimizing individual SQL queries, or evaluating acceleration\n  structures (search indexes, materialized views, BI Engine).\n\n  Do not use for raw usage reporting (use bigquery-observability), query execution\n  plan analysis, error troubleshooting, or diagnosing why a specific job was slow\n  (use bigquery-troubleshooting).'\n---\n\n# BigQuery Optimization Workflow\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:bigquery-optimization)\"`\nand append `agent-skills\u002F1.0 (skill:bigquery-optimization)` to `User-Agent` headers.\n\n## Prerequisites & Environment Setup\n\nBefore executing optimization analyses, evaluating editions, or applying DDL\nmodifications:\n\n1.  **Google Cloud SDK**: Ensure the\n    [Google Cloud SDK](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall) is installed\n    and configured.\n2.  **Project Selection**: Set the active Google Cloud project:\n\n    ```bash\n    gcloud config set project {project_id}\n    ```\n\n3.  **API Enablement**: Ensure BigQuery and BigQuery Reservation APIs are\n    enabled:\n\n    ```bash\n    gcloud services enable \\\n        bigquery.googleapis.com bigqueryreservation.googleapis.com\n    ```\n\n4.  **Authentication**: Authenticate the environment:\n    *   CLI tools and `bq` commands: `gcloud auth login`\n    *   SDKs and automation: `gcloud auth application-default login`\n    *   Service accounts: Set\n        `GOOGLE_APPLICATION_CREDENTIALS=\"\u002Fpath\u002Fto\u002Fkey.json\"`\n\n5.  **Billing & IAM Roles**:\n    *   Verify an active Google Cloud Billing account is attached to\n        `{project_id}`.\n    *   Ensure appropriate IAM roles:\n        *   `roles\u002Fbigquery.admin` or `roles\u002Fbigquery.resourceAdmin`:\n            Reservation and capacity commitment management.\n        *   `roles\u002Fbigquery.dataEditor` or `roles\u002Fbigquery.admin`: Modifying\n            table schemas, partitioning, clustering, and storage billing\n            models.\n        *   `roles\u002Fbigquery.jobUser`: Running evaluation queries.\n\n6.  **Companion Skills Installation**:\n    This skill is part of a 3-pillar operations suite (`bigquery-observability`,\n    `bigquery-optimization`, `bigquery-troubleshooting`). If any companion skill\n    is not yet installed in your environment, install the full suite:\n\n    ```bash\n    npx skills add google\u002Fskills --skill bigquery-observability --skill bigquery-optimization --skill bigquery-troubleshooting\n    ```\n\n    *(If `bigquery-observability` is not installed, use the self-contained\n    baseline formulas and query templates provided directly in the reference\n    sections below).*\n\n## Workflows\n\nDetermine the optimization focus of the user's request and follow the relevant\nworkflow:\n\n-   **Telemetry & Observability Baseline:** For direct raw usage telemetry,\n    `INFORMATION_SCHEMA` queries, and baseline metric calculations, consult\n    [bigquery-observability](..\u002Fbigquery-observability)\n    (`bigquery_observability`). If the `bigquery-observability` companion skill\n    is not available in the active environment, all optimization guidelines, DDL\n    templates, and decision models across this skill and its reference guides\n    are fully self-contained.\n-   **Capacity & Editions Modeling:** Evaluate the cost-efficiency of migrating\n    workloads from On-Demand to Editions, as well as rightsizing active Edition\n    reservations, baseline commitments, and autoscaling caps.\n    *   *Instructions:* Read `references\u002Fcapacity_planning_editions.md` to\n        provide deep links to BigQuery's built-in recommendation UIs (e.g., Slot\n        Estimator) and guide the user through UI navigation: 1. navigate to the\n        Slot Estimator tab, 2. select 'On-Demand' as the source to analyze\n        historical query volume, and 3. review the Cost-Optimized\n        Recommendations and Slot Usage Chart.\n-   **Table & Storage Optimization:** Optimize storage costs from a billing\n    model, physical layout, and lifecycle perspective.\n    *   *Billing Architecture:* Read `references\u002Fstorage_billing_models.md` for\n        guidance on evaluating aggregate compression ratios (e.g. >2:1 threshold\n        in US) to recommend Physical vs. Logical billing, noting that the\n        break-even ratio depends on specific regional rates and custom\n        enterprise contracts. When providing `TABLE_STORAGE` queries, always\n        scope with `WHERE table_schema = '{dataset_id}'`, use the regional\n        dataset view, and warn that 0 rows indicates a region mismatch or lack\n        of native tables rather than zero billable usage.\n    *   *Partitioning & Clustering Strategy:* Read\n        `references\u002Ftable_partitioning_clustering.md` to generate production DDL\n        templates (CREATE TABLE, CTAS migrations for unpartitioned tables, and\n        modifying clustering specifications), enforce pruning with\n        `require_partition_filter = true`, and manage partition limits (up to\n        10,000 partitions\u002Ftable).\n    *   *Lifecycle Management:* Read\n        `references\u002Fstorage_lifecycle_management.md` to pinpoint inactive data\n        and define precise Time-to-Live (TTL) partition expirations, dataset\n        expirations, and Time Travel window reductions.\n    *   *Acceleration Structures:* Read `references\u002Fsearch_indexes.md` to decide\n        when to propose a search index for selective lookups over `STRING` or\n        `JSON` data, write the `CREATE SEARCH INDEX` DDL, and tell the user how\n        to verify index coverage and usage. Read\n        `references\u002Fmaterialized_views.md` to decide when to propose a\n        materialized view for repeated aggregations or joins over large base\n        tables, write the `CREATE MATERIALIZED VIEW` DDL, and tell the user how\n        to verify that smart tuning uses it. Read `references\u002Fbi_engine.md` to\n        decide when to propose BI Engine vs. Materialized Views for BI dashboard\n        acceleration, diagnose `PARTIAL` or `DISABLED` BI Engine fallback\n        reasons (`bi_engine_statistics`), and combine BI Engine with\n        materialized views that pre-join or pre-aggregate the data.\n-   **SQL Optimization:** Optimize individual SQL queries to reduce slot-time\n    and the amount of data read.\n    *   *Instructions:* Follow the instructions in\n        `references\u002Fsql_optimization.md` to provide recommendations to the user\n        on how to rewrite their SQL query to reduce slot-time and the amount of\n        data read.\n\n## Execution Guardrails\n\n-   **Terminology & Cost Framing:** Never promise or guarantee \"cost-reduction\"\n    or \"reducing expenditure.\" Always frame recommendations using the\n    terminology **\"optimizing your bill\"** or **\"improving cost-efficiency.\"**\n-   **Explicit Scope Framing & Region Resolution:** Always state the target\n    `project_id` and `region` at the very top of your response so the user\n    immediately knows the exact scope being evaluated. Follow this 3-tier\n    resolution hierarchy:\n    1.  *Explicit Region:* Use the region specified in the user's prompt (e.g.,\n        `europe-west1`).\n    2.  *Contextual Region:* Resolve the region from the specific dataset or\n        resource mentioned in the context.\n    3.  *Unspecified Fallback:* Default to `us` \u002F `region-us`, explicitly state\n        that `us` was assumed as the default, and instruct the user to\n        substitute their region if their resources reside elsewhere. *Region\n        Formatting:* In Cloud Console deep links, use the region identifier\n        directly (e.g., `region=us`, `region=europe-west1`). In SQL queries\n        against `INFORMATION_SCHEMA`, use the regional dataset qualifier (e.g.,\n        `region-us`, `region-europe-west1`).\n-   **Zero-Row Result Guard:** If querying `TABLE_STORAGE` with `WHERE\n    table_schema = '{dataset_id}'` returns 0 rows, do not proceed with an empty\n    or zero-usage evaluation. Treat this as an indicator that the dataset may\n    reside in a different region or have no native tables; stop and prompt the\n    user to confirm the dataset's regional location.\n-   **Populate Concrete Parameters:** When generating URLs and SQL queries,\n    always substitute known `project_id` and `region` values directly into the\n    code and links. Never leave literal `{project_id}` or `{location}`\n    placeholders for the user to manually edit.\n-   **No Autonomous Purchasing or Financial Mutations:** Never provide the user\n    with executable scripts (e.g., `gcloud` or `bq` shell commands like `bq\n    update --storage_billing_model=...`) designed to autonomously purchase\n    annual commitments, alter edition tier bindings, or mutate storage billing\n    models. Always guide the user to execute commitment purchases, reservation\n    changes, and storage billing model updates manually via the Cloud Console\n    UI.\n","# BigQuery Optimization Workflow\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:bigquery-optimization)\"`\nand append `agent-skills\u002F1.0 (skill:bigquery-optimization)` to `User-Agent` headers.\n\n## Prerequisites & Environment Setup\n\nBefore executing optimization analyses, evaluating editions, or applying DDL\nmodifications:\n\n1.  **Google Cloud SDK**: Ensure the\n    [Google Cloud SDK](https:\u002F\u002Fcloud.google.com\u002Fsdk\u002Fdocs\u002Finstall) is installed\n    and configured.\n2.  **Project Selection**: Set the active Google Cloud project:\n\n    ```bash\n    gcloud config set project {project_id}\n    ```\n\n3.  **API Enablement**: Ensure BigQuery and BigQuery Reservation APIs are\n    enabled:\n\n    ```bash\n    gcloud services enable \\\n        bigquery.googleapis.com bigqueryreservation.googleapis.com\n    ```\n\n4.  **Authentication**: Authenticate the environment:\n    *   CLI tools and `bq` commands: `gcloud auth login`\n    *   SDKs and automation: `gcloud auth application-default login`\n    *   Service accounts: Set\n        `GOOGLE_APPLICATION_CREDENTIALS=\"\u002Fpath\u002Fto\u002Fkey.json\"`\n\n5.  **Billing & IAM Roles**:\n    *   Verify an active Google Cloud Billing account is attached to\n        `{project_id}`.\n    *   Ensure appropriate IAM roles:\n        *   `roles\u002Fbigquery.admin` or `roles\u002Fbigquery.resourceAdmin`:\n            Reservation and capacity commitment management.\n        *   `roles\u002Fbigquery.dataEditor` or `roles\u002Fbigquery.admin`: Modifying\n            table schemas, partitioning, clustering, and storage billing\n            models.\n        *   `roles\u002Fbigquery.jobUser`: Running evaluation queries.\n\n6.  **Companion Skills Installation**:\n    This skill is part of a 3-pillar operations suite (`bigquery-observability`,\n    `bigquery-optimization`, `bigquery-troubleshooting`). If any companion skill\n    is not yet installed in your environment, install the full suite:\n\n    ```bash\n    npx skills add google\u002Fskills --skill bigquery-observability --skill bigquery-optimization --skill bigquery-troubleshooting\n    ```\n\n    *(If `bigquery-observability` is not installed, use the self-contained\n    baseline formulas and query templates provided directly in the reference\n    sections below).*\n\n## Workflows\n\nDetermine the optimization focus of the user's request and follow the relevant\nworkflow:\n\n-   **Telemetry & Observability Baseline:** For direct raw usage telemetry,\n    `INFORMATION_SCHEMA` queries, and baseline metric calculations, consult\n    [bigquery-observability](..\u002Fbigquery-observability)\n    (`bigquery_observability`). If the `bigquery-observability` companion skill\n    is not available in the active environment, all optimization guidelines, DDL\n    templates, and decision models across this skill and its reference guides\n    are fully self-contained.\n-   **Capacity & Editions Modeling:** Evaluate the cost-efficiency of migrating\n    workloads from On-Demand to Editions, as well as rightsizing active Edition\n    reservations, baseline commitments, and autoscaling caps.\n    *   *Instructions:* Read `references\u002Fcapacity_planning_editions.md` to\n        provide deep links to BigQuery's built-in recommendation UIs (e.g., Slot\n        Estimator) and guide the user through UI navigation: 1. navigate to the\n        Slot Estimator tab, 2. select 'On-Demand' as the source to analyze\n        historical query volume, and 3. review the Cost-Optimized\n        Recommendations and Slot Usage Chart.\n-   **Table & Storage Optimization:** Optimize storage costs from a billing\n    model, physical layout, and lifecycle perspective.\n    *   *Billing Architecture:* Read `references\u002Fstorage_billing_models.md` for\n        guidance on evaluating aggregate compression ratios (e.g. >2:1 threshold\n        in US) to recommend Physical vs. Logical billing, noting that the\n        break-even ratio depends on specific regional rates and custom\n        enterprise contracts. When providing `TABLE_STORAGE` queries, always\n        scope with `WHERE table_schema = '{dataset_id}'`, use the regional\n        dataset view, and warn that 0 rows indicates a region mismatch or lack\n        of native tables rather than zero billable usage.\n    *   *Partitioning & Clustering Strategy:* Read\n        `references\u002Ftable_partitioning_clustering.md` to generate production DDL\n        templates (CREATE TABLE, CTAS migrations for unpartitioned tables, and\n        modifying clustering specifications), enforce pruning with\n        `require_partition_filter = true`, and manage partition limits (up to\n        10,000 partitions\u002Ftable).\n    *   *Lifecycle Management:* Read\n        `references\u002Fstorage_lifecycle_management.md` to pinpoint inactive data\n        and define precise Time-to-Live (TTL) partition expirations, dataset\n        expirations, and Time Travel window reductions.\n    *   *Acceleration Structures:* Read `references\u002Fsearch_indexes.md` to decide\n        when to propose a search index for selective lookups over `STRING` or\n        `JSON` data, write the `CREATE SEARCH INDEX` DDL, and tell the user how\n        to verify index coverage and usage. Read\n        `references\u002Fmaterialized_views.md` to decide when to propose a\n        materialized view for repeated aggregations or joins over large base\n        tables, write the `CREATE MATERIALIZED VIEW` DDL, and tell the user how\n        to verify that smart tuning uses it. Read `references\u002Fbi_engine.md` to\n        decide when to propose BI Engine vs. Materialized Views for BI dashboard\n        acceleration, diagnose `PARTIAL` or `DISABLED` BI Engine fallback\n        reasons (`bi_engine_statistics`), and combine BI Engine with\n        materialized views that pre-join or pre-aggregate the data.\n-   **SQL Optimization:** Optimize individual SQL queries to reduce slot-time\n    and the amount of data read.\n    *   *Instructions:* Follow the instructions in\n        `references\u002Fsql_optimization.md` to provide recommendations to the user\n        on how to rewrite their SQL query to reduce slot-time and the amount of\n        data read.\n\n## Execution Guardrails\n\n-   **Terminology & Cost Framing:** Never promise or guarantee \"cost-reduction\"\n    or \"reducing expenditure.\" Always frame recommendations using the\n    terminology **\"optimizing your bill\"** or **\"improving cost-efficiency.\"**\n-   **Explicit Scope Framing & Region Resolution:** Always state the target\n    `project_id` and `region` at the very top of your response so the user\n    immediately knows the exact scope being evaluated. Follow this 3-tier\n    resolution hierarchy:\n    1.  *Explicit Region:* Use the region specified in the user's prompt (e.g.,\n        `europe-west1`).\n    2.  *Contextual Region:* Resolve the region from the specific dataset or\n        resource mentioned in the context.\n    3.  *Unspecified Fallback:* Default to `us` \u002F `region-us`, explicitly state\n        that `us` was assumed as the default, and instruct the user to\n        substitute their region if their resources reside elsewhere. *Region\n        Formatting:* In Cloud Console deep links, use the region identifier\n        directly (e.g., `region=us`, `region=europe-west1`). In SQL queries\n        against `INFORMATION_SCHEMA`, use the regional dataset qualifier (e.g.,\n        `region-us`, `region-europe-west1`).\n-   **Zero-Row Result Guard:** If querying `TABLE_STORAGE` with `WHERE\n    table_schema = '{dataset_id}'` returns 0 rows, do not proceed with an empty\n    or zero-usage evaluation. Treat this as an indicator that the dataset may\n    reside in a different region or have no native tables; stop and prompt the\n    user to confirm the dataset's regional location.\n-   **Populate Concrete Parameters:** When generating URLs and SQL queries,\n    always substitute known `project_id` and `region` values directly into the\n    code and links. Never leave literal `{project_id}` or `{location}`\n    placeholders for the user to manually edit.\n-   **No Autonomous Purchasing or Financial Mutations:** Never provide the user\n    with executable scripts (e.g., `gcloud` or `bq` shell commands like `bq\n    update --storage_billing_model=...`) designed to autonomously purchase\n    annual commitments, alter edition tier bindings, or mutate storage billing\n    models. Always guide the user to execute commitment purchases, reservation\n    changes, and storage billing model updates manually via the Cloud Console\n    UI.\n",{"name":5,"metadata":25,"description":7},{"version":26,"category":27},"1.1.1","BigDataAndAnalytics","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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add tangyixiao\u002Ftangyixiao-skills --skill bigquery-optimization",{"tool":43,"command":44},"bunx","bunx skills add tangyixiao\u002Ftangyixiao-skills --skill bigquery-optimization",{"tool":46,"command":47},"pnpm","pnpm dlx skills add tangyixiao\u002Ftangyixiao-skills --skill bigquery-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002FSKILL.md",true,[51,57,61,65,69,73,77,81,85,89,93],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"INSTALL-SOURCE.json","REFERENCE","参考文档",523,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002FINSTALL-SOURCE.json",{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":16},"LICENSE","许可证",11358,{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fattribution.md",1903,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fattribution.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fbi_engine.md",7439,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fbi_engine.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fcapacity_planning_editions.md",7148,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fcapacity_planning_editions.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fmaterialized_views.md",5022,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fmaterialized_views.md",{"path":78,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fsearch_indexes.md",4151,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fsearch_indexes.md",{"path":82,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fsql_optimization.md",24066,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fsql_optimization.md",{"path":86,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fstorage_billing_models.md",6381,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fstorage_billing_models.md",{"path":90,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fstorage_lifecycle_management.md",2274,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Fstorage_lifecycle_management.md",{"path":94,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Ftable_partitioning_clustering.md",15714,"https:\u002F\u002Fgithub.com\u002Ftangyixiao\u002Ftangyixiao-skills\u002Fblob\u002Fmain\u002Fbigquery-optimization\u002Freferences\u002Ftable_partitioning_clustering.md",[98,106,115,123,131,139],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"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":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"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":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":110,"licenseFileUrl":143,"sourceHtmlUrl":144,"categories":145,"keywords":146,"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",[],[]]