[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M788MBJKC4MT5G2J8D6ATAB3":3,"skill-same:01M788MBJKC4MT5G2J8D6ATAB3":59},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M788MBJKC4MT5G2J8D6ATAB3","iam-recommendations-fetcher",null,"Fetches raw IAM recommendations and associated security insights from Google Cloud for a specified target scope (Organization, Folder, or Project). Use when you need to retrieve security recommendations before analyzing or applying them. Don't use for applying\u002Facting on recommendations (use the recommendation applier skill) or for general allow policy querying (use the allow policy viewer skill).","Solizardking\u002Fskillhub-main","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786NYYXSZK1D05WM8JQPC48",0,"MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fiam-recommendations-fetcher\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: iam-recommendations-fetcher\nmetadata:\n  category: Identity\ndescription: >-\n  Fetches raw IAM recommendations and associated security insights from Google Cloud for a\n  specified target scope (Organization, Folder, or Project). Use when you need to\n  retrieve security recommendations before analyzing or applying them. Don't use\n  for applying\u002Facting on recommendations (use the recommendation applier skill)\n  or for general allow policy querying (use the allow policy viewer skill).\n---\n\n# IAM Recommendations Retrieval\n\nThis skill provides instructions for fetching IAM recommendations and insights\nfrom Google Cloud. It covers validating the input target scope, retrieving\nrecommendations using MCP tools, gcloud commands, or direct API calls, and\nhandling common API errors.\n\n## Procedures\n\n### 1. Validate Input Target\n\nVerify the input target scope.\n\n1.  **Check Format**: Check if the target matches one of these formats:\n\n    *   `organizations\u002F{org_id}`\n    *   `folders\u002F{folder_id}`\n    *   `projects\u002F{project_id}`\n\n2.  **Handle Ambiguous\u002FRaw Target**: If the user provides only a raw ID (without\n    the prefix):\n\n    *   **Alphanumeric (starts with a letter)**: Assume it is a Project ID.\n        Format it as `projects\u002F{project_id}` and proceed.\n    *   **Purely Numeric**: It is ambiguous (could be Organization, Folder, or\n        Project Number).\n        *   Ask the user to clarify the resource type: > \"Is the target ID\n            '{provided_id}' an Organization, a Folder, or a Project?\"\n        *   Once the user specifies, format the target scope accordingly (e.g.,\n            prepend `organizations\u002F`, `folders\u002F`, or `projects\u002F`) and proceed.\n        *   If the user's response is invalid or they cannot clarify, treat it\n            as an error and proceed to [Handle Errors](#5-handle-errors)\n            (incorrect target).\n\n3.  **Handle Project Numbers**: If the target is a project but uses a purely\n    numeric ID (Project Number) instead of a Project ID (e.g.,\n    `projects\u002F123456789`):\n\n    *   `gcloud` recommender commands require a Project ID. Attempt to resolve\n        the Project Number to a Project ID using: `gcloud projects list\n        --filter=\"projectNumber={project_number}\" --format=\"value(projectId)\"`\n    *   If this resolution returns empty or fails with a permission error, do\n        not attempt to describe the project, search the codebase, or search for\n        mock data. Immediately return the standardized error JSON specified in\n        [Handle Errors](#5-handle-errors) and stop execution (do not call any\n        more tools).\n\n4.  **Record Validation**: Explicitly state the validated and formatted target\n    scope (e.g., `projects\u002F123456789` or `organizations\u002F123456789012`) in your\n    thought\u002Freasoning before proceeding to the fetch step.\n\n### 2. Fetch Recommendations and Insights (Fallback Flow)\n\nAttempt the following retrieval methods in order. Stop at the first success.\n\n**CRITICAL: Fail Fast on Errors** (To avoid redundant API calls that will fail\nfor the same authorization\u002Fpermission reasons): If any attempted method (Option\nA or Option B) fails with an API-level error (such as `PERMISSION_DENIED`,\n`UNAUTHENTICATED`, or resource `NOT_FOUND` \u002F does not exist) or a CLI validation\nerror (such as project number not allowed), **do NOT attempt any further\noptions** (including Option C or direct API\u002Fcurl calls). Stop immediately, do\nnot call any more tools, and return the standardized error JSON as specified in\nthe \"Handle Errors\" section.\n\n#### Option A: MCP Tool (Preferred)\n\nUse the MCP tool if available. MCP tools are designed for efficient, secure\nexecution within Google's internal environments, often providing streamlined\nauthentication and better integration compared to general-purpose CLI commands.\n\nIf an IAM Recommender MCP tool is available in your context:\n\n*   Call the tool with the `target` parameter.\n\n#### Option B: gcloud CLI (First Fallback)\n\nIf MCP is unavailable, use `run_command` to execute the following (replace\nvariables accordingly):\n\nTarget                            | Flag\n:-------------------------------- | :---------------------------------\n`projects\u002F{project_id}`           | `--project={project_id}`\n`folders\u002F{folder_id}`             | `--folder={folder_id}`\n`organizations\u002F{organization_id}` | `--organization={organization_id}`\n\n**Commands to run**:\n\n```bash\nGCLOUD_COMMON_FLAGS=\"--format=json --location=global \\\n--filter=stateInfo.state=ACTIVE\"\n\n# 1. Fetch Recommendations\ngcloud recommender recommendations list \\\n--recommender=google.iam.policy.Recommender $GCLOUD_COMMON_FLAGS {mapped_flag}\n\n# 2. Fetch Insights\ngcloud recommender insights list --insight-type=google.iam.policy.Insight\n$GCLOUD_COMMON_FLAGS {mapped_flag}\n```\n\n#### Option C: Google Cloud API (Final Fallback)\n\nOnly attempt this option if `gcloud` is physically unavailable in the\nenvironment (e.g., `gcloud: command not found`). API client libraries require\nmore setup and execution overhead, so they are only used as a last resort if CLI\ntools are missing. Do NOT use this option if `gcloud` is available but failed\nwith an API error.\n\nUse Google Cloud Recommender API client libraries via a helper script (or direct\nAPI calls if libraries are unavailable) to:\n\n1.  Call `list_recommendations` (or `recommendations.list`) for\n    `google.iam.policy.Recommender` (filter: `stateInfo.state=ACTIVE`).\n2.  Call `list_insights` (or `insights.list`) for `google.iam.policy.Insight`\n    (filter: `stateInfo.state=ACTIVE`).\n\n### 3. Determine Output Format and Deliver\n\n**CRITICAL**: Only proceed to this step if the retrieval in Step 2 was\nsuccessful. If the retrieval failed, skip this step and go directly to\n[Handle Errors](#5-handle-errors).\n\nBefore presenting the results, determine the desired output format.\n\n**CRITICAL**: If the user's initial prompt already specifies the output format\n(e.g., \"return the raw results in JSON\" or \"show it in a table\"), bypass asking\nand proceed directly to that format.\n\nOtherwise, ask the user in a dropdown menu, with the options being:\n\n1.  JSON file\n2.  Markdown table in chat\n\nBased on the choice (either pre-specified or chosen by the user), deliver the\noutput:\n\n#### Option A: JSON File\n\n1.  Write the raw results to a file named\n    `iam_recommendations_\u003Ctarget_id>_\u003Ctimestamp>.json` (where `\u003Ctarget_id>` is\n    the sanitized resource identifier and `\u003Ctimestamp>` is formatted as\n    `YYYYMMDD_HHMMSS`) in the current working directory.\n2.  The file content must match the structure shown in\n    [Example Execution](#4-example-execution).\n3.  Respond to the user with the file path.\n\n#### Option B: Chat Table\n\n1.  **Sort Recommendations**: Sort the retrieved recommendations, placing\n    service agent recommendations last in the list.\n2.  **Format Table**: Format the sorted recommendations into a markdown table.\n    The table should contain key fields:\n    -   **Subtype**: The recommender subtype or insight subtype (e.g.,\n        indicating if it's for resource-level roles).\n    -   **Recommended Action**: Summary of the recommendation.\n    -   **Rationale**: Rationale\u002Fjustification.\n    -   **Associated Insights**: The IDs of any linked insights (from\n        `associatedInsights`).\n3.  **Limit Chat Display**: Display only the top 10 recommendations in the chat\n    table.\n4.  **Provide Full List**: Save the complete list of recommendations and\n    insights to a markdown file (e.g.,\n    `iam_recommendations_\u003Ctarget_id>_\u003Ctimestamp>.md`, where `\u003Ctarget_id>` is the\n    sanitized resource identifier and `\u003Ctimestamp>` is formatted as\n    `YYYYMMDD_HHMMSS`) and provide a link for the user to download it.\n5.  **Format Insights Table**: If insights are present, format them in a\n    separate table in the markdown file (and optionally show a summary in chat\n    if appropriate, but keep the chat clean). The table should contain key\n    fields:\n    -   **Insight ID**: The insight identifier (`INSIGHT_ID`).\n    -   **State**: The insight state (`INSIGHT_STATE`).\n    -   **Subtype**: The insight subtype (`INSIGHT_SUBTYPE`).\n    -   **Description**: Description of the insight (`DESCRIPTION`).\n6.  **DO NOT** provide a JSON file with the raw results if this option is\n    chosen.\n\n### 4. Example Execution\n\n*   **Input Target**: projects\u002Fmy-test-project\n*   **Mapped Flag**: --project=my-test-project\n*   **Action (Option B)**: Run `gcloud recommender recommendations list\n    --recommender=google.iam.policy.Recommender --format=json --location=global\n    --filter=stateInfo.state=ACTIVE --project=my-test-project`\n*   **Expected Output Structure**:\n\n    ```json\n    {\n      \"raw_results\": {\n        \"recommendations\": [\n          {\n            \"name\": \"projects\u002Fmy-test-project\u002Flocations\u002Fglobal\u002Frecommenders\u002F \\\n            google.iam.policy.Recommender\u002Frecommendations\u002F123\",\n            \"content\": { ... }\n          }\n        ],\n        \"insights\": []\n      },\n      \"error\": null\n    }\n    ```\n\n### 5. Handle Errors\n\n**CRITICAL**: If you encounter any of the error conditions below (during\nvalidation or fetch), **stop immediately**. Do not attempt to debug, switch\naccounts, search the codebase, or verify resource existence. Immediately output\nthe specified JSON structure as your final response and call no further tools.\n\nIf all methods fail, return:\n\n*   For incorrect target: `{\"raw_results\": null, \"error\": \"The specified target\n    resource is incorrect or does not exist.\"}`\n*   For authentication issues: `{\"raw_results\": null, \"error\": \"User is\n    unauthenticated. Please authenticate (e.g., run 'gcloud auth login').\"}`\n*   For permissions: `{\"raw_results\": null, \"error\": \"Insufficient permissions.\n    Please ensure you have 'roles\u002Frecommender.iamViewer' on the target scope.\"}`\n*   Other: `{\"raw_results\": null, \"error\": \"Failed to fetch: {error_details}\"}`\n    (Do not mention MCP tool failures to the user).\n\n## Gotchas\n\n*   **State Filter**: Always ensure you are filtering for `ACTIVE`\n    recommendations.\n*   **Location**: The location for IAM Recommender is always global.\n","# IAM Recommendations Retrieval\n\nThis skill provides instructions for fetching IAM recommendations and insights\nfrom Google Cloud. It covers validating the input target scope, retrieving\nrecommendations using MCP tools, gcloud commands, or direct API calls, and\nhandling common API errors.\n\n## Procedures\n\n### 1. Validate Input Target\n\nVerify the input target scope.\n\n1.  **Check Format**: Check if the target matches one of these formats:\n\n    *   `organizations\u002F{org_id}`\n    *   `folders\u002F{folder_id}`\n    *   `projects\u002F{project_id}`\n\n2.  **Handle Ambiguous\u002FRaw Target**: If the user provides only a raw ID (without\n    the prefix):\n\n    *   **Alphanumeric (starts with a letter)**: Assume it is a Project ID.\n        Format it as `projects\u002F{project_id}` and proceed.\n    *   **Purely Numeric**: It is ambiguous (could be Organization, Folder, or\n        Project Number).\n        *   Ask the user to clarify the resource type: > \"Is the target ID\n            '{provided_id}' an Organization, a Folder, or a Project?\"\n        *   Once the user specifies, format the target scope accordingly (e.g.,\n            prepend `organizations\u002F`, `folders\u002F`, or `projects\u002F`) and proceed.\n        *   If the user's response is invalid or they cannot clarify, treat it\n            as an error and proceed to [Handle Errors](#5-handle-errors)\n            (incorrect target).\n\n3.  **Handle Project Numbers**: If the target is a project but uses a purely\n    numeric ID (Project Number) instead of a Project ID (e.g.,\n    `projects\u002F123456789`):\n\n    *   `gcloud` recommender commands require a Project ID. Attempt to resolve\n        the Project Number to a Project ID using: `gcloud projects list\n        --filter=\"projectNumber={project_number}\" --format=\"value(projectId)\"`\n    *   If this resolution returns empty or fails with a permission error, do\n        not attempt to describe the project, search the codebase, or search for\n        mock data. Immediately return the standardized error JSON specified in\n        [Handle Errors](#5-handle-errors) and stop execution (do not call any\n        more tools).\n\n4.  **Record Validation**: Explicitly state the validated and formatted target\n    scope (e.g., `projects\u002F123456789` or `organizations\u002F123456789012`) in your\n    thought\u002Freasoning before proceeding to the fetch step.\n\n### 2. Fetch Recommendations and Insights (Fallback Flow)\n\nAttempt the following retrieval methods in order. Stop at the first success.\n\n**CRITICAL: Fail Fast on Errors** (To avoid redundant API calls that will fail\nfor the same authorization\u002Fpermission reasons): If any attempted method (Option\nA or Option B) fails with an API-level error (such as `PERMISSION_DENIED`,\n`UNAUTHENTICATED`, or resource `NOT_FOUND` \u002F does not exist) or a CLI validation\nerror (such as project number not allowed), **do NOT attempt any further\noptions** (including Option C or direct API\u002Fcurl calls). Stop immediately, do\nnot call any more tools, and return the standardized error JSON as specified in\nthe \"Handle Errors\" section.\n\n#### Option A: MCP Tool (Preferred)\n\nUse the MCP tool if available. MCP tools are designed for efficient, secure\nexecution within Google's internal environments, often providing streamlined\nauthentication and better integration compared to general-purpose CLI commands.\n\nIf an IAM Recommender MCP tool is available in your context:\n\n*   Call the tool with the `target` parameter.\n\n#### Option B: gcloud CLI (First Fallback)\n\nIf MCP is unavailable, use `run_command` to execute the following (replace\nvariables accordingly):\n\nTarget                            | Flag\n:-------------------------------- | :---------------------------------\n`projects\u002F{project_id}`           | `--project={project_id}`\n`folders\u002F{folder_id}`             | `--folder={folder_id}`\n`organizations\u002F{organization_id}` | `--organization={organization_id}`\n\n**Commands to run**:\n\n```bash\nGCLOUD_COMMON_FLAGS=\"--format=json --location=global \\\n--filter=stateInfo.state=ACTIVE\"\n\n# 1. Fetch Recommendations\ngcloud recommender recommendations list \\\n--recommender=google.iam.policy.Recommender $GCLOUD_COMMON_FLAGS {mapped_flag}\n\n# 2. Fetch Insights\ngcloud recommender insights list --insight-type=google.iam.policy.Insight\n$GCLOUD_COMMON_FLAGS {mapped_flag}\n```\n\n#### Option C: Google Cloud API (Final Fallback)\n\nOnly attempt this option if `gcloud` is physically unavailable in the\nenvironment (e.g., `gcloud: command not found`). API client libraries require\nmore setup and execution overhead, so they are only used as a last resort if CLI\ntools are missing. Do NOT use this option if `gcloud` is available but failed\nwith an API error.\n\nUse Google Cloud Recommender API client libraries via a helper script (or direct\nAPI calls if libraries are unavailable) to:\n\n1.  Call `list_recommendations` (or `recommendations.list`) for\n    `google.iam.policy.Recommender` (filter: `stateInfo.state=ACTIVE`).\n2.  Call `list_insights` (or `insights.list`) for `google.iam.policy.Insight`\n    (filter: `stateInfo.state=ACTIVE`).\n\n### 3. Determine Output Format and Deliver\n\n**CRITICAL**: Only proceed to this step if the retrieval in Step 2 was\nsuccessful. If the retrieval failed, skip this step and go directly to\n[Handle Errors](#5-handle-errors).\n\nBefore presenting the results, determine the desired output format.\n\n**CRITICAL**: If the user's initial prompt already specifies the output format\n(e.g., \"return the raw results in JSON\" or \"show it in a table\"), bypass asking\nand proceed directly to that format.\n\nOtherwise, ask the user in a dropdown menu, with the options being:\n\n1.  JSON file\n2.  Markdown table in chat\n\nBased on the choice (either pre-specified or chosen by the user), deliver the\noutput:\n\n#### Option A: JSON File\n\n1.  Write the raw results to a file named\n    `iam_recommendations_\u003Ctarget_id>_\u003Ctimestamp>.json` (where `\u003Ctarget_id>` is\n    the sanitized resource identifier and `\u003Ctimestamp>` is formatted as\n    `YYYYMMDD_HHMMSS`) in the current working directory.\n2.  The file content must match the structure shown in\n    [Example Execution](#4-example-execution).\n3.  Respond to the user with the file path.\n\n#### Option B: Chat Table\n\n1.  **Sort Recommendations**: Sort the retrieved recommendations, placing\n    service agent recommendations last in the list.\n2.  **Format Table**: Format the sorted recommendations into a markdown table.\n    The table should contain key fields:\n    -   **Subtype**: The recommender subtype or insight subtype (e.g.,\n        indicating if it's for resource-level roles).\n    -   **Recommended Action**: Summary of the recommendation.\n    -   **Rationale**: Rationale\u002Fjustification.\n    -   **Associated Insights**: The IDs of any linked insights (from\n        `associatedInsights`).\n3.  **Limit Chat Display**: Display only the top 10 recommendations in the chat\n    table.\n4.  **Provide Full List**: Save the complete list of recommendations and\n    insights to a markdown file (e.g.,\n    `iam_recommendations_\u003Ctarget_id>_\u003Ctimestamp>.md`, where `\u003Ctarget_id>` is the\n    sanitized resource identifier and `\u003Ctimestamp>` is formatted as\n    `YYYYMMDD_HHMMSS`) and provide a link for the user to download it.\n5.  **Format Insights Table**: If insights are present, format them in a\n    separate table in the markdown file (and optionally show a summary in chat\n    if appropriate, but keep the chat clean). The table should contain key\n    fields:\n    -   **Insight ID**: The insight identifier (`INSIGHT_ID`).\n    -   **State**: The insight state (`INSIGHT_STATE`).\n    -   **Subtype**: The insight subtype (`INSIGHT_SUBTYPE`).\n    -   **Description**: Description of the insight (`DESCRIPTION`).\n6.  **DO NOT** provide a JSON file with the raw results if this option is\n    chosen.\n\n### 4. Example Execution\n\n*   **Input Target**: projects\u002Fmy-test-project\n*   **Mapped Flag**: --project=my-test-project\n*   **Action (Option B)**: Run `gcloud recommender recommendations list\n    --recommender=google.iam.policy.Recommender --format=json --location=global\n    --filter=stateInfo.state=ACTIVE --project=my-test-project`\n*   **Expected Output Structure**:\n\n    ```json\n    {\n      \"raw_results\": {\n        \"recommendations\": [\n          {\n            \"name\": \"projects\u002Fmy-test-project\u002Flocations\u002Fglobal\u002Frecommenders\u002F \\\n            google.iam.policy.Recommender\u002Frecommendations\u002F123\",\n            \"content\": { ... }\n          }\n        ],\n        \"insights\": []\n      },\n      \"error\": null\n    }\n    ```\n\n### 5. Handle Errors\n\n**CRITICAL**: If you encounter any of the error conditions below (during\nvalidation or fetch), **stop immediately**. Do not attempt to debug, switch\naccounts, search the codebase, or verify resource existence. Immediately output\nthe specified JSON structure as your final response and call no further tools.\n\nIf all methods fail, return:\n\n*   For incorrect target: `{\"raw_results\": null, \"error\": \"The specified target\n    resource is incorrect or does not exist.\"}`\n*   For authentication issues: `{\"raw_results\": null, \"error\": \"User is\n    unauthenticated. Please authenticate (e.g., run 'gcloud auth login').\"}`\n*   For permissions: `{\"raw_results\": null, \"error\": \"Insufficient permissions.\n    Please ensure you have 'roles\u002Frecommender.iamViewer' on the target scope.\"}`\n*   Other: `{\"raw_results\": null, \"error\": \"Failed to fetch: {error_details}\"}`\n    (Do not mention MCP tool failures to the user).\n\n## Gotchas\n\n*   **State Filter**: Always ensure you are filtering for `ACTIVE`\n    recommendations.\n*   **Location**: The location for IAM Recommender is always global.\n",{"name":5,"metadata":24,"description":7},{"category":25},"Identity","main","be3de0244dc1a57e323d8160787ebb40fb64930e","public\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fiam-recommendations-fetcher","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 23:20:13",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Solizardking\u002Fskillhub-main --skill iam-recommendations-fetcher",{"tool":41,"command":42},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill iam-recommendations-fetcher",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill iam-recommendations-fetcher","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fiam-recommendations-fetcher\u002FSKILL.md",true,[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"metadata.json","REFERENCE","参考文档",626,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fiam-recommendations-fetcher\u002Fmetadata.json",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"verification.json",1335,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fpublic\u002Fapi\u002Fskills\u002Fgoogle\u002Fcloud\u002Fiam-recommendations-fetcher\u002Fverification.json",[60,67,74,81,88,96],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M78E0TGCAMNPS207BA3G07S7","zkrouter","Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzkrouter\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M78E0R1Z8BDT6EDTHY17MTNB","zk","For custom ZK Solana programs and privacy-preserving applications to prevent double spending. Guide to integrate rent-free nullifier PDAs for double-spend prevention.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M78E0P3ZTZ1YWF8MD5MM23QE","zk-omni-messaging","Zero-knowledge omnichain messaging between Robinhood Chain and Solana using CheshireZkOmniMessenger (msgType 4) with nullifier anti-replay and the zk-omni-relayer service.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk-omni-messaging\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M78E0JXZ2PNB1896VXAGDBWD","zerion-wallet-data","Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzerion-wallet-data\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":15,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M78E0G14FH9GRRTQYMKD5E59","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M78E0C2ZYA99CFFDNB7ZMK5S","yield-optimization","Multi-chain yield optimization via yield.xyz (StakeKit). Discover 2,988+ yield opportunities across 75+ blockchains, build deposit\u002Fwithdrawal transactions with shell scripts, and sign them with a MoonPay wallet. Use when the user wants to earn yield, find the best lending or staking rate, enter\u002Fexit a position, or check portfolio balances.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyield-optimization\u002FSKILL.md",[],[]]