{
  "schemaVersion": "1.0",
  "item": {
    "slug": "local-rag-search",
    "name": "Local Rag Search",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/nkapila6/local-rag-search",
    "canonicalUrl": "https://clawhub.ai/nkapila6/local-rag-search",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/local-rag-search",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=local-rag-search",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "package.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/local-rag-search"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/local-rag-search",
    "agentPageUrl": "https://openagent3.xyz/skills/local-rag-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/local-rag-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/local-rag-search/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Local RAG Search Skill",
        "body": "This skill enables you to effectively use the mcp-local-rag MCP server for intelligent web searches with semantic ranking. The server performs RAG-like similarity scoring to prioritize the most relevant results without requiring any external APIs."
      },
      {
        "title": "1. rag_search_ddgs - DuckDuckGo Search",
        "body": "Use this for privacy-focused, general web searches.\n\nWhen to use:\n\nUser prefers privacy-focused searches\nGeneral information lookup\nDefault choice for most queries\n\nParameters:\n\nquery: Natural language search query\nnum_results: Initial results to fetch (default: 10)\ntop_k: Most relevant results to return (default: 5)\ninclude_urls: Include source URLs (default: true)"
      },
      {
        "title": "2. rag_search_google - Google Search",
        "body": "Use this for comprehensive, technical, or detailed searches.\n\nWhen to use:\n\nTechnical or scientific queries\nNeed comprehensive coverage\nSearching for specific documentation"
      },
      {
        "title": "3. deep_research - Multi-Engine Deep Research",
        "body": "Use this for comprehensive research across multiple search engines.\n\nWhen to use:\n\nResearching complex topics requiring broad coverage\nNeed diverse perspectives from multiple sources\nGathering comprehensive information on a subject\n\nAvailable backends:\n\nduckduckgo: Privacy-focused general search\ngoogle: Comprehensive technical results\nbing: Microsoft's search engine\nbrave: Privacy-first search\nwikipedia: Encyclopedia/factual content\nyahoo, yandex, mojeek, grokipedia: Alternative engines\n\nDefault: [\"duckduckgo\", \"google\"]"
      },
      {
        "title": "4. deep_research_google - Google-Only Deep Research",
        "body": "Shortcut for deep research using only Google."
      },
      {
        "title": "5. deep_research_ddgs - DuckDuckGo-Only Deep Research",
        "body": "Shortcut for deep research using only DuckDuckGo."
      },
      {
        "title": "Query Formulation",
        "body": "Use natural language: Write queries as questions or descriptive phrases\n\nGood: \"latest developments in quantum computing\"\nGood: \"how to implement binary search in Python\"\nAvoid: Single keywords like \"quantum\" or \"Python\"\n\n\n\nBe specific: Include context and details\n\nGood: \"React hooks best practices for 2024\"\nBetter: \"React useEffect cleanup function best practices\""
      },
      {
        "title": "Tool Selection Strategy",
        "body": "Single Topic, Quick Answer → Use rag_search_ddgs or rag_search_google\nrag_search_ddgs(\n    query=\"What is the capital of France?\",\n    top_k=3\n)\n\n\n\nTechnical/Scientific Query → Use rag_search_google\nrag_search_google(\n    query=\"Docker multi-stage build optimization techniques\",\n    num_results=15,\n    top_k=7\n)\n\n\n\nComprehensive Research → Use deep_research with multiple search terms\ndeep_research(\n    search_terms=[\n        \"machine learning fundamentals\",\n        \"neural networks architecture\",\n        \"deep learning best practices 2024\"\n    ],\n    backends=[\"google\", \"duckduckgo\"],\n    top_k_per_term=5\n)\n\n\n\nFactual/Encyclopedia Content → Use deep_research with Wikipedia\ndeep_research(\n    search_terms=[\"World War II timeline\", \"WWII key battles\"],\n    backends=[\"wikipedia\"],\n    num_results_per_term=5\n)"
      },
      {
        "title": "Parameter Tuning",
        "body": "For quick answers:\n\nnum_results=5-10, top_k=3-5\n\nFor comprehensive research:\n\nnum_results=15-20, top_k=7-10\n\nFor deep research:\n\nnum_results_per_term=10-15, top_k_per_term=3-5\nUse 2-5 related search terms\nUse 1-3 backends (more = more comprehensive but slower)"
      },
      {
        "title": "Example 1: Current Events",
        "body": "Task: \"What happened at the UN climate summit last week?\"\n\n1. Use rag_search_google for recent news coverage\n2. Set top_k=7 for comprehensive view\n3. Present findings with source URLs"
      },
      {
        "title": "Example 2: Technical Deep Dive",
        "body": "Task: \"How do I optimize PostgreSQL queries?\"\n\n1. Use deep_research with multiple specific terms:\n   - \"PostgreSQL query optimization techniques\"\n   - \"PostgreSQL index best practices\"\n   - \"PostgreSQL EXPLAIN ANALYZE tutorial\"\n2. Use backends=[\"google\", \"stackoverflow\"] if available\n3. Synthesize findings into actionable guide"
      },
      {
        "title": "Example 3: Multi-Perspective Research",
        "body": "Task: \"Research the impact of remote work on productivity\"\n\n1. Use deep_research with diverse search terms:\n   - \"remote work productivity statistics 2024\"\n   - \"hybrid work model effectiveness studies\"\n   - \"work from home challenges research\"\n2. Use backends=[\"google\", \"duckduckgo\"] for broad coverage\n3. Synthesize different perspectives and studies"
      },
      {
        "title": "Guidelines",
        "body": "Always cite sources: When include_urls=True, reference the source URLs in your response\nVerify recency: Check if the content appears current and relevant\nCross-reference: For important facts, use multiple search terms or engines\nRespect privacy: Use DuckDuckGo for general queries unless specific needs require Google\nBatch related queries: When researching a topic, create multiple related search terms for deep_research\nSemantic relevance: Trust the RAG scoring - top results are semantically closest to the query\nExplain your choice: Briefly mention which tool you're using and why"
      },
      {
        "title": "Error Handling",
        "body": "If a search returns insufficient results:\n\nTry rephrasing the query with different keywords\nSwitch to a different backend\nIncrease num_results parameter\nUse deep_research with multiple related search terms"
      },
      {
        "title": "Privacy Considerations",
        "body": "DuckDuckGo: Privacy-focused, doesn't track users\nGoogle: Most comprehensive but tracks searches\nRecommend DuckDuckGo as default unless user specifically needs Google's coverage"
      },
      {
        "title": "Performance Notes",
        "body": "First search may be slower (model loading)\nSubsequent searches are faster (cached models)\nMore backends = more comprehensive but slower\nAdjust num_results and top_k based on use case"
      }
    ],
    "body": "Local RAG Search Skill\n\nThis skill enables you to effectively use the mcp-local-rag MCP server for intelligent web searches with semantic ranking. The server performs RAG-like similarity scoring to prioritize the most relevant results without requiring any external APIs.\n\nAvailable Tools\n1. rag_search_ddgs - DuckDuckGo Search\n\nUse this for privacy-focused, general web searches.\n\nWhen to use:\n\nUser prefers privacy-focused searches\nGeneral information lookup\nDefault choice for most queries\n\nParameters:\n\nquery: Natural language search query\nnum_results: Initial results to fetch (default: 10)\ntop_k: Most relevant results to return (default: 5)\ninclude_urls: Include source URLs (default: true)\n2. rag_search_google - Google Search\n\nUse this for comprehensive, technical, or detailed searches.\n\nWhen to use:\n\nTechnical or scientific queries\nNeed comprehensive coverage\nSearching for specific documentation\n3. deep_research - Multi-Engine Deep Research\n\nUse this for comprehensive research across multiple search engines.\n\nWhen to use:\n\nResearching complex topics requiring broad coverage\nNeed diverse perspectives from multiple sources\nGathering comprehensive information on a subject\n\nAvailable backends:\n\nduckduckgo: Privacy-focused general search\ngoogle: Comprehensive technical results\nbing: Microsoft's search engine\nbrave: Privacy-first search\nwikipedia: Encyclopedia/factual content\nyahoo, yandex, mojeek, grokipedia: Alternative engines\n\nDefault: [\"duckduckgo\", \"google\"]\n\n4. deep_research_google - Google-Only Deep Research\n\nShortcut for deep research using only Google.\n\n5. deep_research_ddgs - DuckDuckGo-Only Deep Research\n\nShortcut for deep research using only DuckDuckGo.\n\nBest Practices\nQuery Formulation\n\nUse natural language: Write queries as questions or descriptive phrases\n\nGood: \"latest developments in quantum computing\"\nGood: \"how to implement binary search in Python\"\nAvoid: Single keywords like \"quantum\" or \"Python\"\n\nBe specific: Include context and details\n\nGood: \"React hooks best practices for 2024\"\nBetter: \"React useEffect cleanup function best practices\"\nTool Selection Strategy\n\nSingle Topic, Quick Answer → Use rag_search_ddgs or rag_search_google\n\nrag_search_ddgs(\n    query=\"What is the capital of France?\",\n    top_k=3\n)\n\n\nTechnical/Scientific Query → Use rag_search_google\n\nrag_search_google(\n    query=\"Docker multi-stage build optimization techniques\",\n    num_results=15,\n    top_k=7\n)\n\n\nComprehensive Research → Use deep_research with multiple search terms\n\ndeep_research(\n    search_terms=[\n        \"machine learning fundamentals\",\n        \"neural networks architecture\",\n        \"deep learning best practices 2024\"\n    ],\n    backends=[\"google\", \"duckduckgo\"],\n    top_k_per_term=5\n)\n\n\nFactual/Encyclopedia Content → Use deep_research with Wikipedia\n\ndeep_research(\n    search_terms=[\"World War II timeline\", \"WWII key battles\"],\n    backends=[\"wikipedia\"],\n    num_results_per_term=5\n)\n\nParameter Tuning\n\nFor quick answers:\n\nnum_results=5-10, top_k=3-5\n\nFor comprehensive research:\n\nnum_results=15-20, top_k=7-10\n\nFor deep research:\n\nnum_results_per_term=10-15, top_k_per_term=3-5\nUse 2-5 related search terms\nUse 1-3 backends (more = more comprehensive but slower)\nWorkflow Examples\nExample 1: Current Events\nTask: \"What happened at the UN climate summit last week?\"\n\n1. Use rag_search_google for recent news coverage\n2. Set top_k=7 for comprehensive view\n3. Present findings with source URLs\n\nExample 2: Technical Deep Dive\nTask: \"How do I optimize PostgreSQL queries?\"\n\n1. Use deep_research with multiple specific terms:\n   - \"PostgreSQL query optimization techniques\"\n   - \"PostgreSQL index best practices\"\n   - \"PostgreSQL EXPLAIN ANALYZE tutorial\"\n2. Use backends=[\"google\", \"stackoverflow\"] if available\n3. Synthesize findings into actionable guide\n\nExample 3: Multi-Perspective Research\nTask: \"Research the impact of remote work on productivity\"\n\n1. Use deep_research with diverse search terms:\n   - \"remote work productivity statistics 2024\"\n   - \"hybrid work model effectiveness studies\"\n   - \"work from home challenges research\"\n2. Use backends=[\"google\", \"duckduckgo\"] for broad coverage\n3. Synthesize different perspectives and studies\n\nGuidelines\nAlways cite sources: When include_urls=True, reference the source URLs in your response\nVerify recency: Check if the content appears current and relevant\nCross-reference: For important facts, use multiple search terms or engines\nRespect privacy: Use DuckDuckGo for general queries unless specific needs require Google\nBatch related queries: When researching a topic, create multiple related search terms for deep_research\nSemantic relevance: Trust the RAG scoring - top results are semantically closest to the query\nExplain your choice: Briefly mention which tool you're using and why\nError Handling\n\nIf a search returns insufficient results:\n\nTry rephrasing the query with different keywords\nSwitch to a different backend\nIncrease num_results parameter\nUse deep_research with multiple related search terms\nPrivacy Considerations\nDuckDuckGo: Privacy-focused, doesn't track users\nGoogle: Most comprehensive but tracks searches\nRecommend DuckDuckGo as default unless user specifically needs Google's coverage\nPerformance Notes\nFirst search may be slower (model loading)\nSubsequent searches are faster (cached models)\nMore backends = more comprehensive but slower\nAdjust num_results and top_k based on use case"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nkapila6/local-rag-search",
    "publisherUrl": "https://clawhub.ai/nkapila6/local-rag-search",
    "owner": "nkapila6",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/local-rag-search",
    "downloadUrl": "https://openagent3.xyz/downloads/local-rag-search",
    "agentUrl": "https://openagent3.xyz/skills/local-rag-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/local-rag-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/local-rag-search/agent.md"
  }
}