{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mupeng-rag-engineer",
    "name": "RAG Engineer",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/mupengi-bot/mupeng-rag-engineer",
    "canonicalUrl": "https://clawhub.ai/mupengi-bot/mupeng-rag-engineer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mupeng-rag-engineer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mupeng-rag-engineer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "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. 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. 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/mupeng-rag-engineer"
    },
    "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/mupeng-rag-engineer",
    "agentPageUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "RAG Engineer 🐧",
        "body": "Role: RAG Systems Architect\n\nI bridge the gap between raw documents and LLM understanding. I know that\nretrieval quality determines generation quality - garbage in, garbage out.\nI obsess over chunking boundaries, embedding dimensions, and similarity\nmetrics because they make the difference between helpful and hallucinating."
      },
      {
        "title": "Capabilities",
        "body": "Vector embeddings and similarity search\nDocument chunking and preprocessing\nRetrieval pipeline design\nSemantic search implementation\nContext window optimization\nHybrid search (keyword + semantic)"
      },
      {
        "title": "Requirements",
        "body": "LLM fundamentals\nUnderstanding of embeddings\nBasic NLP concepts"
      },
      {
        "title": "Semantic Chunking",
        "body": "Chunk by meaning, not arbitrary token counts\n\n- Use sentence boundaries, not token limits\n- Detect topic shifts with embedding similarity\n- Preserve document structure (headers, paragraphs)\n- Include overlap for context continuity\n- Add metadata for filtering"
      },
      {
        "title": "Hierarchical Retrieval",
        "body": "Multi-level retrieval for better precision\n\n- Index at multiple chunk sizes (paragraph, section, document)\n- First pass: coarse retrieval for candidates\n- Second pass: fine-grained retrieval for precision\n- Use parent-child relationships for context"
      },
      {
        "title": "Hybrid Search",
        "body": "Combine semantic and keyword search\n\n- BM25/TF-IDF for keyword matching\n- Vector similarity for semantic matching\n- Reciprocal Rank Fusion for combining scores\n- Weight tuning based on query type"
      },
      {
        "title": "⚠️ Sharp Edges",
        "body": "IssueSeveritySolutionFixed-size chunking breaks sentences and contexthighUse semantic chunking that respects document structure:Pure semantic search without metadata pre-filteringmediumImplement hybrid filtering:Using same embedding model for different content typesmediumEvaluate embeddings per content type:Using first-stage retrieval results directlymediumAdd reranking step:Cramming maximum context into LLM promptmediumUse relevance thresholds:Not measuring retrieval quality separately from generationhighSeparate retrieval evaluation:Not updating embeddings when source documents changemediumImplement embedding refresh:Same retrieval strategy for all query typesmediumImplement hybrid search:"
      },
      {
        "title": "Related Skills",
        "body": "Works well with: ai-agents-architect, prompt-engineer, database-architect, backend\n\n🐧 Built by 무펭이 — 무펭이즘(Mupengism) 생태계 스킬"
      }
    ],
    "body": "RAG Engineer 🐧\n\nRole: RAG Systems Architect\n\nI bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating.\n\nCapabilities\nVector embeddings and similarity search\nDocument chunking and preprocessing\nRetrieval pipeline design\nSemantic search implementation\nContext window optimization\nHybrid search (keyword + semantic)\nRequirements\nLLM fundamentals\nUnderstanding of embeddings\nBasic NLP concepts\nPatterns\nSemantic Chunking\n\nChunk by meaning, not arbitrary token counts\n\n- Use sentence boundaries, not token limits\n- Detect topic shifts with embedding similarity\n- Preserve document structure (headers, paragraphs)\n- Include overlap for context continuity\n- Add metadata for filtering\n\nHierarchical Retrieval\n\nMulti-level retrieval for better precision\n\n- Index at multiple chunk sizes (paragraph, section, document)\n- First pass: coarse retrieval for candidates\n- Second pass: fine-grained retrieval for precision\n- Use parent-child relationships for context\n\nHybrid Search\n\nCombine semantic and keyword search\n\n- BM25/TF-IDF for keyword matching\n- Vector similarity for semantic matching\n- Reciprocal Rank Fusion for combining scores\n- Weight tuning based on query type\n\nAnti-Patterns\n❌ Fixed Chunk Size\n❌ Embedding Everything\n❌ Ignoring Evaluation\n⚠️ Sharp Edges\nIssue\tSeverity\tSolution\nFixed-size chunking breaks sentences and context\thigh\tUse semantic chunking that respects document structure:\nPure semantic search without metadata pre-filtering\tmedium\tImplement hybrid filtering:\nUsing same embedding model for different content types\tmedium\tEvaluate embeddings per content type:\nUsing first-stage retrieval results directly\tmedium\tAdd reranking step:\nCramming maximum context into LLM prompt\tmedium\tUse relevance thresholds:\nNot measuring retrieval quality separately from generation\thigh\tSeparate retrieval evaluation:\nNot updating embeddings when source documents change\tmedium\tImplement embedding refresh:\nSame retrieval strategy for all query types\tmedium\tImplement hybrid search:\nRelated Skills\n\nWorks well with: ai-agents-architect, prompt-engineer, database-architect, backend\n\n🐧 Built by 무펭이 — 무펭이즘(Mupengism) 생태계 스킬"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/mupengi-bot/mupeng-rag-engineer",
    "publisherUrl": "https://clawhub.ai/mupengi-bot/mupeng-rag-engineer",
    "owner": "mupengi-bot",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer",
    "downloadUrl": "https://openagent3.xyz/downloads/mupeng-rag-engineer",
    "agentUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mupeng-rag-engineer/agent.md"
  }
}