[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BPRX5Z747V28NHT3JBGY48":3,"skill-same:01M7BPRX5Z747V28NHT3JBGY48":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7BPRX5Z747V28NHT3JBGY48","discovering-gcp-data-assets",null,"Finds and inspects data assets within Google Cloud.\nRelevant when any of the following conditions are true:\n  1. The user request involves finding, exploring, or inspecting data assets\n     in Google Cloud, such as:\n       - BigQuery datasets, tables, or views\n       - BigLake catalog or tables\n       - Spanner instances, databases or tables\n       - etc.\n  2. You need to retrieve the schema, metadata, or governance policies for a\n     GCP data asset.\n  3. You have a keyword or topic (e.g., \"sales data\") but lack the specific\n     table or resource ID.\n  4. You are attempting to find data using `bq ls`, as this skill offers a\n     superior approach.\nDon't use when:\n  - Assets are outside Google Cloud","hikmet4434\u002Fclaude-skills","hikmet4434","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F301146035?v=4","01M7BNXPE7A92JBFSZV3GXVQA4","hikmet tanriverdi","01M7BNXPEXW1JAJ271VVPSK87C",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fdiscovering-gcp-data-assets\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: discovering-gcp-data-assets\ndescription: |\n  Finds and inspects data assets within Google Cloud.\n  Relevant when any of the following conditions are true:\n    1. The user request involves finding, exploring, or inspecting data assets\n       in Google Cloud, such as:\n         - BigQuery datasets, tables, or views\n         - BigLake catalog or tables\n         - Spanner instances, databases or tables\n         - etc.\n    2. You need to retrieve the schema, metadata, or governance policies for a\n       GCP data asset.\n    3. You have a keyword or topic (e.g., \"sales data\") but lack the specific\n       table or resource ID.\n    4. You are attempting to find data using `bq ls`, as this skill offers a\n       superior approach.\n  Don't use when:\n    - Assets are outside Google Cloud\nlicense: Apache-2.0\nmetadata:\n  version: v4\n  publisher: google\n---\n\n# Instructions\n\n## Step 1: Prioritize Assets from the Conversation\n\nIf the asset was created or mentioned earlier in the same conversation, then\nproceed with that asset instead of searching. Skip steps 2, 3, and 4.\n\n## Step 2: Handle Public Datasets or Proceed to Search\n\nDataplex Lookup Context provides the richest metadata for data assets. You MUST\nprioritize using it for all Google Cloud assets, even if you already know their\nIDs.\n\n-   **Public Datasets (Direct Inspection)**: If the requested asset belongs to\n    the `bigquery-public-data` project, Dataplex Lookup Context will fail. You\n    MUST skip Steps 3 and 4 and inspect the table directly using the `bq` CLI or\n    BigQuery MCP tools instead.\n-   **All Other Assets (Proceed to Step 3)**: For all other BigQuery, Cloud\n    Storage, Spanner, BigLake Iceberg or general GCP data assets (whether their\n    IDs are known or missing), you MUST proceed to **Step 3** to search the\n    Dataplex catalog and obtain their full Entry Name.\n\n## Step 3: Execute Discovery Search\n\nYou MUST use the Dataplex search command to discover assets and retrieve their\nfull `projects\u002F...` entry names. This step is required even if you already know\nthe asset's short ID (e.g., `my_dataset.my_table`), because Step 4 strictly\nrequires the full entry name.\n\n> [!IMPORTANT]\n>\n> The `--project` parameter MUST ALWAYS be provided. This project_id is used to\n> attribute the search only and does NOT restrict the search scope. The project\n> must have the dataplex API enabled and user must have the\n> `dataplex.entries.get` permissions.\n\n### A. Semantic Search (Natural Language Intent)\n\nUse this when the user describes the **meaning** or **intent** of the data\n(e.g., \"Find Q4 product sales data\").\n\nUse the `search_entries` MCP tool\n\nOR\n\n```bash\ngcloud dataplex entries search \"\u003CNATURAL_LANGUAGE_QUERY>\" \\\n  --project=\"\u003CPROJECT_ID>\" \\\n  --semantic-search \\\n  --limit=50\n```\n\n### B. Keyword Search (Technical Strings)\n\nUse this for exact keyword matches or technical strings (e.g., `name:order_v2`).\n\n#### Search Query Rules (MANDATORY)\n\n-   **Mode-Specific Syntax**:\n    -   **Semantic Search**: Logical operators (`AND`, `OR`) MUST be\n        **UPPERCASE**. Use plural `labels.` for label filters (e.g.,\n        `labels.env=prod`).\n    -   **Keyword Search**: Operators are case-insensitive. Use singular\n        `label.` for label filters (e.g., `label.env=prod`).\n-   **Abbreviated Logic**: Use `|` for OR and `,` for AND within parentheses to\n    shorten queries (e.g., `projectid:(prod|staging)` or `column:(id,name)`).\n-   **Exact vs. Token Match**:\n    -   Use `:` for token\u002Fsubstring matches (e.g., `name:sales`).\n    -   Use `=` for exact matches. REQUIRED for `system`, `type`, and\n        `location`.\n-   **Singular Keywords**: When performing keyword search, ALWAYS convert\n    plurals to singular (e.g., \"product\" NOT \"products\"). Semantic search\n    handles singular\u002Fplural variations and synonyms automatically.\n-   **Scope Restriction**: You SHOULD restrict the search scope using a `parent`\n    filter if the project or dataset is known (e.g.,\n    `parent:projects\u002F\u003CPROJECT_ID>`).\n\n#### Dataplex Search Syntax Reference\n\n-   **`name:x`**: Substring\u002Ftoken match on resource ID.\n-   **`displayname:x`**: Substring\u002Ftoken match on display name.\n-   **`projectid:x`**: Substring\u002Ftoken match on GCP project ID.\n-   **`parent:x`**: Substring match on hierarchical path (e.g.,\n    `projects\u002Fmy-proj`).\n-   **`location=x`**: Exact match on location (e.g., `us-central1`, `us`).\n-   **`column:x`**: Substring\u002Ftoken match on column names in the schema.\n-   **`system=x`**: Exact match on source system. Common values: `bigquery`,\n    `storage`, `biglake`, `cloud_sql`, `cloud_spanner`, `cloud_bigtable`,\n    `pubsub`.\n-   **`type=x`**: Exact match on entry type (e.g., `bigquery-table`,\n    `storage-bucket`, `storage-folder`).\n-   **`labels.key=value`**: (Semantic Mode ONLY) Exact match on a label.\n-   **`label.key=value`**: (Keyword Mode ONLY) Exact match on a label.\n-   **`createtime[>|\u003C|=]x`**: Match assets created after\u002Fbefore date\n    `YYYY-MM-DD`.\n-   **`fully_qualified_name=x`**: Exact match on the FQN (e.g.,\n    `bigquery:project.dataset.table`).\n\n> [!TIP]\n>\n> Dataplex search results rely on metadata being ingested into the Universal\n> Catalog (often via **Discovery Scans**). If an asset is missing from search,\n> it may not be indexed. - **Fallback 1**: Try searching by the\n> `fully_qualified_name` qualifier. - **Fallback 2**: Use native tools (e.g.,\n> `bq show`, `gcloud storage`) or specific skills for that asset type if you\n> already know the ID.\n\n```bash\ngcloud dataplex entries search \"\u003CKEYWORD_SEARCH_QUERY>\" \\\n  --project=\"\u003CPROJECT_ID>\" \\\n  --limit=50\n```\n\n> [!IMPORTANT]\n>\n> Handling Search Results and Avoiding Loops:\n>\n> 1.  **No Results:** If the search returns no entries:\n>     *   **Variation Rule:** You may try AT MOST 3 variations of the search\n>         query (e.g., switching AND\u002FOR clauses, adding\u002Fremoving `parent:`,\n>         removing `projectid:` or `location:`, trying `fully_qualified_name=`).\n>     *   **Stop Rule:** If after 3 attempts no results are found, STOP and\n>         inform the user. Ask for clarification, specifically the Dataplex\n>         **full entry name** if known, or identifiers such as **project ID**,\n>         **dataset ID**, or **instance ID** to help narrow the search. Example:\n>         \"I couldn't find any tables matching that description after several\n>         attempts. If you know the Dataplex full entry name (`projects\u002F...`),\n>         please provide it. Otherwise, please provide any identifiers you know,\n>         such as project, dataset, or instance name, to help locate the asset.\"\n> 2.  **Multiple Results:**\n>     *   If more than 10 results are returned, state that many matches were\n>         found. Show the names of the first 5 entries and ask for\n>         clarification.\n>     *   If 2-10 results are returned and you cannot definitively choose, list\n>         them and ask the user.\n> 3.  **Single Result:** Proceed to Step 3 with the full entry name.\n> 4.  **Avoid Infinite Loops:** MUST NOT re-run identical or near-identical\n>     queries. If Dataplex fails to return the expected asset, prioritize asking\n>     the user for the exact resource ID or using Fallback 2 (Native Tools).\n\n*Criteria*: Once candidate assets are returned, proceed to Step 4 using the\n**full entry names** from the search results.\n\n## Step 4: Lookup Context\n\nYou MUST use the **Lookup Context** command to fetch schema and deep metadata\nfor the relevant results obtained from Step 3.\n\n> [!IMPORTANT]\n>\n> The `--resources` parameter MUST be the **full name** (starting with\n> `projects\u002F`) returned by the search result. Passing short table IDs, GCS URIs,\n> or fully qualified `bigquery:` prefixes is PROHIBITED and will fail.\n\n### Command Execution\n\nUse the `lookup_context` MCP tool\n\nOR\n\n```bash\ngcloud dataplex context lookup --resources=\"\u003CFULL_ENTRY_NAME>\"\n```\n\n*Completion Criteria*: The command returns the detailed schema and business\ncontext.\n\n--------------------------------------------------------------------------------\n\n## Troubleshooting\n\n### Context Lookup Fails or \"Resource not found\"\n\n-   **Cause**: Short table names were used improperly.\n-   **Fix**: Ensure you use the correct entry name format from the search\n    results (starting with `projects\u002F`).\n\n### Search Returns No Results\n\n-   **Cause**: Plural terms in keyword search or lack of scoping.\n-   **Fix**: Switch to singular keywords. For semantic search, try more\n    descriptive natural language.\n\n### Context Lookup Fails with \"NOT_FOUND\" (despite correct format)\n\n-   **Cause**: The table belongs to a project (e.g., `bigquery-public-data`)\n    that has not fully synchronized its metadata with the Dataplex Universal\n    Catalog. While the entry appears in search, `context lookup` is unavailable.\n-   **Fix**: Fall back to direct inspection using native tools (e.g., `bq` CLI).\n-   **Stop Rule:** If the native tool (e.g., `bq show`) also returns \"Not\n    Found\", STOP. Do not restart the Dataplex discovery loop. Specifically ask\n    the user to verify the **project ID** and **table ID**.\n\n### Breaking the Research Loop\n\nIf you find yourself repeatedly searching for the same asset:\n\n1.  **STOP.**\n2.  State what you have tried (e.g., \"I tried searching Dataplex with X and Y,\n    and checked `bq show`\").\n3.  Ask the user for the exact project, dataset, and table ID.\n\n### Search Fails with \"--project: Must be specified.\"\n\n-   **Cause**: `--project \u003CPROJECT_ID>` arguments were not provided\n-   **Fix**: Provide a project which will be used to authorize and attribute the\n    search request.\n\n### Search Fails with \"PERMISSION_DENIED\"\n\n-   **Cause**: The project_id provided in the `--project \u003CPROJECT_ID>` arguments\n    does not have the Dataplex API enabled or the user is missing necessary IAM\n    permissions.\n-   **Fix**: Ask the user if they have a project which has the Dataplex API\n    enabled with the dataplex.entries.get permission\n","# Instructions\n\n## Step 1: Prioritize Assets from the Conversation\n\nIf the asset was created or mentioned earlier in the same conversation, then\nproceed with that asset instead of searching. Skip steps 2, 3, and 4.\n\n## Step 2: Handle Public Datasets or Proceed to Search\n\nDataplex Lookup Context provides the richest metadata for data assets. You MUST\nprioritize using it for all Google Cloud assets, even if you already know their\nIDs.\n\n-   **Public Datasets (Direct Inspection)**: If the requested asset belongs to\n    the `bigquery-public-data` project, Dataplex Lookup Context will fail. You\n    MUST skip Steps 3 and 4 and inspect the table directly using the `bq` CLI or\n    BigQuery MCP tools instead.\n-   **All Other Assets (Proceed to Step 3)**: For all other BigQuery, Cloud\n    Storage, Spanner, BigLake Iceberg or general GCP data assets (whether their\n    IDs are known or missing), you MUST proceed to **Step 3** to search the\n    Dataplex catalog and obtain their full Entry Name.\n\n## Step 3: Execute Discovery Search\n\nYou MUST use the Dataplex search command to discover assets and retrieve their\nfull `projects\u002F...` entry names. This step is required even if you already know\nthe asset's short ID (e.g., `my_dataset.my_table`), because Step 4 strictly\nrequires the full entry name.\n\n> [!IMPORTANT]\n>\n> The `--project` parameter MUST ALWAYS be provided. This project_id is used to\n> attribute the search only and does NOT restrict the search scope. The project\n> must have the dataplex API enabled and user must have the\n> `dataplex.entries.get` permissions.\n\n### A. Semantic Search (Natural Language Intent)\n\nUse this when the user describes the **meaning** or **intent** of the data\n(e.g., \"Find Q4 product sales data\").\n\nUse the `search_entries` MCP tool\n\nOR\n\n```bash\ngcloud dataplex entries search \"\u003CNATURAL_LANGUAGE_QUERY>\" \\\n  --project=\"\u003CPROJECT_ID>\" \\\n  --semantic-search \\\n  --limit=50\n```\n\n### B. Keyword Search (Technical Strings)\n\nUse this for exact keyword matches or technical strings (e.g., `name:order_v2`).\n\n#### Search Query Rules (MANDATORY)\n\n-   **Mode-Specific Syntax**:\n    -   **Semantic Search**: Logical operators (`AND`, `OR`) MUST be\n        **UPPERCASE**. Use plural `labels.` for label filters (e.g.,\n        `labels.env=prod`).\n    -   **Keyword Search**: Operators are case-insensitive. Use singular\n        `label.` for label filters (e.g., `label.env=prod`).\n-   **Abbreviated Logic**: Use `|` for OR and `,` for AND within parentheses to\n    shorten queries (e.g., `projectid:(prod|staging)` or `column:(id,name)`).\n-   **Exact vs. Token Match**:\n    -   Use `:` for token\u002Fsubstring matches (e.g., `name:sales`).\n    -   Use `=` for exact matches. REQUIRED for `system`, `type`, and\n        `location`.\n-   **Singular Keywords**: When performing keyword search, ALWAYS convert\n    plurals to singular (e.g., \"product\" NOT \"products\"). Semantic search\n    handles singular\u002Fplural variations and synonyms automatically.\n-   **Scope Restriction**: You SHOULD restrict the search scope using a `parent`\n    filter if the project or dataset is known (e.g.,\n    `parent:projects\u002F\u003CPROJECT_ID>`).\n\n#### Dataplex Search Syntax Reference\n\n-   **`name:x`**: Substring\u002Ftoken match on resource ID.\n-   **`displayname:x`**: Substring\u002Ftoken match on display name.\n-   **`projectid:x`**: Substring\u002Ftoken match on GCP project ID.\n-   **`parent:x`**: Substring match on hierarchical path (e.g.,\n    `projects\u002Fmy-proj`).\n-   **`location=x`**: Exact match on location (e.g., `us-central1`, `us`).\n-   **`column:x`**: Substring\u002Ftoken match on column names in the schema.\n-   **`system=x`**: Exact match on source system. Common values: `bigquery`,\n    `storage`, `biglake`, `cloud_sql`, `cloud_spanner`, `cloud_bigtable`,\n    `pubsub`.\n-   **`type=x`**: Exact match on entry type (e.g., `bigquery-table`,\n    `storage-bucket`, `storage-folder`).\n-   **`labels.key=value`**: (Semantic Mode ONLY) Exact match on a label.\n-   **`label.key=value`**: (Keyword Mode ONLY) Exact match on a label.\n-   **`createtime[>|\u003C|=]x`**: Match assets created after\u002Fbefore date\n    `YYYY-MM-DD`.\n-   **`fully_qualified_name=x`**: Exact match on the FQN (e.g.,\n    `bigquery:project.dataset.table`).\n\n> [!TIP]\n>\n> Dataplex search results rely on metadata being ingested into the Universal\n> Catalog (often via **Discovery Scans**). If an asset is missing from search,\n> it may not be indexed. - **Fallback 1**: Try searching by the\n> `fully_qualified_name` qualifier. - **Fallback 2**: Use native tools (e.g.,\n> `bq show`, `gcloud storage`) or specific skills for that asset type if you\n> already know the ID.\n\n```bash\ngcloud dataplex entries search \"\u003CKEYWORD_SEARCH_QUERY>\" \\\n  --project=\"\u003CPROJECT_ID>\" \\\n  --limit=50\n```\n\n> [!IMPORTANT]\n>\n> Handling Search Results and Avoiding Loops:\n>\n> 1.  **No Results:** If the search returns no entries:\n>     *   **Variation Rule:** You may try AT MOST 3 variations of the search\n>         query (e.g., switching AND\u002FOR clauses, adding\u002Fremoving `parent:`,\n>         removing `projectid:` or `location:`, trying `fully_qualified_name=`).\n>     *   **Stop Rule:** If after 3 attempts no results are found, STOP and\n>         inform the user. Ask for clarification, specifically the Dataplex\n>         **full entry name** if known, or identifiers such as **project ID**,\n>         **dataset ID**, or **instance ID** to help narrow the search. Example:\n>         \"I couldn't find any tables matching that description after several\n>         attempts. If you know the Dataplex full entry name (`projects\u002F...`),\n>         please provide it. Otherwise, please provide any identifiers you know,\n>         such as project, dataset, or instance name, to help locate the asset.\"\n> 2.  **Multiple Results:**\n>     *   If more than 10 results are returned, state that many matches were\n>         found. Show the names of the first 5 entries and ask for\n>         clarification.\n>     *   If 2-10 results are returned and you cannot definitively choose, list\n>         them and ask the user.\n> 3.  **Single Result:** Proceed to Step 3 with the full entry name.\n> 4.  **Avoid Infinite Loops:** MUST NOT re-run identical or near-identical\n>     queries. If Dataplex fails to return the expected asset, prioritize asking\n>     the user for the exact resource ID or using Fallback 2 (Native Tools).\n\n*Criteria*: Once candidate assets are returned, proceed to Step 4 using the\n**full entry names** from the search results.\n\n## Step 4: Lookup Context\n\nYou MUST use the **Lookup Context** command to fetch schema and deep metadata\nfor the relevant results obtained from Step 3.\n\n> [!IMPORTANT]\n>\n> The `--resources` parameter MUST be the **full name** (starting with\n> `projects\u002F`) returned by the search result. Passing short table IDs, GCS URIs,\n> or fully qualified `bigquery:` prefixes is PROHIBITED and will fail.\n\n### Command Execution\n\nUse the `lookup_context` MCP tool\n\nOR\n\n```bash\ngcloud dataplex context lookup --resources=\"\u003CFULL_ENTRY_NAME>\"\n```\n\n*Completion Criteria*: The command returns the detailed schema and business\ncontext.\n\n--------------------------------------------------------------------------------\n\n## Troubleshooting\n\n### Context Lookup Fails or \"Resource not found\"\n\n-   **Cause**: Short table names were used improperly.\n-   **Fix**: Ensure you use the correct entry name format from the search\n    results (starting with `projects\u002F`).\n\n### Search Returns No Results\n\n-   **Cause**: Plural terms in keyword search or lack of scoping.\n-   **Fix**: Switch to singular keywords. For semantic search, try more\n    descriptive natural language.\n\n### Context Lookup Fails with \"NOT_FOUND\" (despite correct format)\n\n-   **Cause**: The table belongs to a project (e.g., `bigquery-public-data`)\n    that has not fully synchronized its metadata with the Dataplex Universal\n    Catalog. While the entry appears in search, `context lookup` is unavailable.\n-   **Fix**: Fall back to direct inspection using native tools (e.g., `bq` CLI).\n-   **Stop Rule:** If the native tool (e.g., `bq show`) also returns \"Not\n    Found\", STOP. Do not restart the Dataplex discovery loop. Specifically ask\n    the user to verify the **project ID** and **table ID**.\n\n### Breaking the Research Loop\n\nIf you find yourself repeatedly searching for the same asset:\n\n1.  **STOP.**\n2.  State what you have tried (e.g., \"I tried searching Dataplex with X and Y,\n    and checked `bq show`\").\n3.  Ask the user for the exact project, dataset, and table ID.\n\n### Search Fails with \"--project: Must be specified.\"\n\n-   **Cause**: `--project \u003CPROJECT_ID>` arguments were not provided\n-   **Fix**: Provide a project which will be used to authorize and attribute the\n    search request.\n\n### Search Fails with \"PERMISSION_DENIED\"\n\n-   **Cause**: The project_id provided in the `--project \u003CPROJECT_ID>` arguments\n    does not have the Dataplex API enabled or the user is missing necessary IAM\n    permissions.\n-   **Fix**: Ask the user if they have a project which has the Dataplex API\n    enabled with the dataplex.entries.get permission\n",{"name":5,"license":15,"metadata":24,"description":27},{"version":25,"publisher":26},"v4","google","Finds and inspects data assets within Google Cloud.\nRelevant when any of the following conditions are true:\n  1. The user request involves finding, exploring, or inspecting data assets\n     in Google Cloud, such as:\n       - BigQuery datasets, tables, or views\n       - BigLake catalog or tables\n       - Spanner instances, databases or tables\n       - etc.\n  2. You need to retrieve the schema, metadata, or governance policies for a\n     GCP data asset.\n  3. You have a keyword or topic (e.g., \"sales data\") but lack the specific\n     table or resource ID.\n  4. You are attempting to find data using `bq ls`, as this skill offers a\n     superior approach.\nDon't use when:\n  - Assets are outside Google Cloud\n","master","8f65f9c8da48757c0ec3e7d6483545ecc0167ee1","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills","https:\u002F\u002Fgithub.com\u002Fhikmet4434","thirdhand.com.tr","2026-11-01 23:11:46",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add hikmet4434\u002Fclaude-skills --skill discovering-gcp-data-assets",{"tool":40,"command":41},"bunx","bunx skills add hikmet4434\u002Fclaude-skills --skill discovering-gcp-data-assets",{"tool":43,"command":44},"pnpm","pnpm dlx skills add hikmet4434\u002Fclaude-skills --skill discovering-gcp-data-assets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fdiscovering-gcp-data-assets\u002FSKILL.md",true,[],[49,57,65,72,80,88],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":53,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7BTGA12ETGPJZV002TR0YDS","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7BTG43MC8DG3395QZ9V8628","yayin-seo-geo-yasal-denetim","Bir web uygulaması canlıya çıkmadan veya iş teslimi biterken resmî\u002Fkurumsal sayfaları, SEO, GEO, indeksleme ve canlı çıktıyı denetler; eksikleri kodda tamamlar ve üretimde kanıtlar. Uygulama bitti, canlıya hazır mı, yayına al, launch checklist, release readiness, SEO audit, GEO audit, legal pages, privacy policy, terms, cookies, KVKK, robots, sitemap, canonical, hreflang, JSON-LD, llms.txt ifadelerinde kullan. Yeni veya önemli ölçüde değişmiş halka açık web uygulamasının son teslim aşamasında kullanıcı ayrıca istemese de uygula. Güvenlik sızma testi için güvenlik skillini ayrıca kullan.","MIT","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fyayin-seo-geo-yasal-denetim\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7BTG0P2JC1MW62J36K8GTXE","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7BTF744QWNY97F5SQJZ7WQ1","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fwrangler\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7BTD1RVAZTYZ3J6JT97W2XJ","winui-app","Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fwinui-app\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fwinui-app\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7BTCJJ3F3G3VASJYEAWXDQ1","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fhikmet4434\u002Fclaude-skills\u002Fblob\u002Fmaster\u002Fwhisper\u002FSKILL.md",[],[]]