{ "schemaVersion": "1.0", "item": { "slug": "rag", "name": "RAG", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/rag", "canonicalUrl": "https://clawhub.ai/ivangdavila/rag", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/rag", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=rag", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "architecture.md", "evaluation.md", "implementation.md", "security.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/rag" }, "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/rag", "agentPageUrl": "https://openagent3.xyz/skills/rag/agent", "manifestUrl": "https://openagent3.xyz/skills/rag/agent.json", "briefUrl": "https://openagent3.xyz/skills/rag/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": "When to Use", "body": "User wants to implement, improve, or troubleshoot Retrieval-Augmented Generation systems." }, { "title": "Quick Reference", "body": "TopicFilePipeline components & architecturearchitecture.mdImplementation patterns & codeimplementation.mdEvaluation metrics & debuggingevaluation.mdSecurity & compliancesecurity.md" }, { "title": "Core Capabilities", "body": "Architecture design — Select embedding models, vector DBs, and chunking strategies based on requirements\nImplementation — Write ingestion pipelines, query handlers, and update logic\nRetrieval optimization — Tune top-k, reranking, hybrid search parameters\nEvaluation — Build test datasets, measure recall/precision, diagnose failures\nProduction ops — Monitor quality drift, set up alerts, debug degradation\nSecurity — PII detection, access control, compliance requirements" }, { "title": "Decision Checklist", "body": "Before recommending architecture, ask:\n\nWhat document types and volume?\n Latency requirements (real-time chat vs batch)?\n Update frequency (how often do docs change)?\n Access control needs (who can see what)?\n Compliance constraints (GDPR, HIPAA, SOC2)?\n Budget (managed vs self-hosted, embedding costs)?" }, { "title": "Critical Rules", "body": "Never skip access control — Filter at retrieval time, not after\nAlways overlap chunks — 10-20% prevents context loss at boundaries\nEvaluate before optimizing — Build eval dataset first, then tune\nSame embedding model — Query and documents must use identical model\nMonitor similarity scores — Dropping averages signal drift or issues\nPlan for deletion — GDPR erasure requires re-embedding capability" }, { "title": "Common Failure Patterns", "body": "SymptomLikely CauseFixWrong docs retrievedQuery too vague, poor chunksQuery expansion, smaller chunksRelevant doc missedNot indexed, low similarityCheck ingestion, hybrid searchHallucinated answersContext too shortIncrease top-k, better rerankingSlow responsesLarge chunks, no cachingOptimize chunk size, cache embeddingsInconsistent resultsNon-deterministic rerankingSet seeds, use stable sorting" } ], "body": "When to Use\n\nUser wants to implement, improve, or troubleshoot Retrieval-Augmented Generation systems.\n\nQuick Reference\nTopic\tFile\nPipeline components & architecture\tarchitecture.md\nImplementation patterns & code\timplementation.md\nEvaluation metrics & debugging\tevaluation.md\nSecurity & compliance\tsecurity.md\nCore Capabilities\nArchitecture design — Select embedding models, vector DBs, and chunking strategies based on requirements\nImplementation — Write ingestion pipelines, query handlers, and update logic\nRetrieval optimization — Tune top-k, reranking, hybrid search parameters\nEvaluation — Build test datasets, measure recall/precision, diagnose failures\nProduction ops — Monitor quality drift, set up alerts, debug degradation\nSecurity — PII detection, access control, compliance requirements\nDecision Checklist\n\nBefore recommending architecture, ask:\n\n What document types and volume?\n Latency requirements (real-time chat vs batch)?\n Update frequency (how often do docs change)?\n Access control needs (who can see what)?\n Compliance constraints (GDPR, HIPAA, SOC2)?\n Budget (managed vs self-hosted, embedding costs)?\nCritical Rules\nNever skip access control — Filter at retrieval time, not after\nAlways overlap chunks — 10-20% prevents context loss at boundaries\nEvaluate before optimizing — Build eval dataset first, then tune\nSame embedding model — Query and documents must use identical model\nMonitor similarity scores — Dropping averages signal drift or issues\nPlan for deletion — GDPR erasure requires re-embedding capability\nCommon Failure Patterns\nSymptom\tLikely Cause\tFix\nWrong docs retrieved\tQuery too vague, poor chunks\tQuery expansion, smaller chunks\nRelevant doc missed\tNot indexed, low similarity\tCheck ingestion, hybrid search\nHallucinated answers\tContext too short\tIncrease top-k, better reranking\nSlow responses\tLarge chunks, no caching\tOptimize chunk size, cache embeddings\nInconsistent results\tNon-deterministic reranking\tSet seeds, use stable sorting" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/rag", "publisherUrl": "https://clawhub.ai/ivangdavila/rag", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/rag", "downloadUrl": "https://openagent3.xyz/downloads/rag", "agentUrl": "https://openagent3.xyz/skills/rag/agent", "manifestUrl": "https://openagent3.xyz/skills/rag/agent.json", "briefUrl": "https://openagent3.xyz/skills/rag/agent.md" } }