{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ck-rag-skill",
    "name": "ck-rag-skill",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/chenkun-nuaa/ck-rag-skill",
    "canonicalUrl": "https://clawhub.ai/chenkun-nuaa/ck-rag-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ck-rag-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ck-rag-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "scripts/query_ragflow.py",
      "scripts/quick_test.py",
      "scripts/test_api.sh",
      "SKILL.md",
      "TROUBLESHOOTING.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",
      "slug": "ck-rag-skill",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-11T19:43:15.358Z",
      "expiresAt": "2026-05-18T19:43:15.358Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ck-rag-skill",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ck-rag-skill",
        "contentDisposition": "attachment; filename=\"ck-rag-skill-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "ck-rag-skill"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ck-rag-skill"
    },
    "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/ck-rag-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/ck-rag-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ck-rag-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ck-rag-skill/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": "概述",
        "body": "此skill通过调用RAGFlow知识库API，为用户提供智能问答和操作指导。API使用流式输出（Stream）方式返回结果，需要耐心等待完整响应生成（通常5-10秒）。"
      },
      {
        "title": "步骤1: 识别问题类型",
        "body": "判断用户的问题是否适合通过知识库查询：\n\n技术问题（容器、Docker、Kubernetes等）\n系统运维问题\n故障排查\n操作指导\n其他需要专业知识库的场景"
      },
      {
        "title": "步骤2: 调用RAGFlow API",
        "body": "使用scripts/query_ragflow.py脚本查询知识库：\n\n标准查询（适合正常使用）：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"用户的问题\"\n\n调试模式（查看详细信息）：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"用户的问题\" -v\n# 或\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"用户的问题\" --verbose"
      },
      {
        "title": "步骤3: 等待流式响应",
        "body": "重要提示：\n\nRAGFlow API使用流式输出，响应需要时间生成\n无新数据超时：15秒（给流式生成足够时间）\n最大总超时：60秒\n请求超时：120秒\n通常5-10秒能完成，复杂问题可能更久\n\n脚本会显示进度点（.）表示正在接收数据，请耐心等待。"
      },
      {
        "title": "步骤4: 处理返回结果",
        "body": "API返回结果包含：\n\n助手回复：完整的AI生成答案\n引用文档：知识库中相关的文档来源\n统计信息：处理行数、数据块数量、耗时"
      },
      {
        "title": "步骤5: 总结和操作建议",
        "body": "根据返回结果：\n\n直接回答: 如果是简单问题，直接总结答案\n操作指导: 如果问题涉及具体操作（如容器挂了），提供步骤化的操作建议\n建议执行agent操作: 如果建议使用其他agent工具，明确指出"
      },
      {
        "title": "API配置",
        "body": "基本信息:\n\nAPI地址: http://172.28.20.46:30001/v1/conversation/completion\n认证方式: Bearer token + Cookie session\n输出方式: Server-Sent Events (SSE) 流式输出\n\n请求格式:\n\n方法: POST\nContent-Type: application/json\n\n关键参数:\n\nconversation_id: 会话ID（使用固定ID保持对话上下文）\nmessages: 对话历史数组，每个消息包含：\n\nrole: \"user\" 或 \"assistant\"\ncontent: 消息内容\nid: 消息唯一标识"
      },
      {
        "title": "示例1: 容器故障排查",
        "body": "用户: 容器挂了怎么办\n→ 调用API查询\"容器挂了怎么办\"\n→ 等待约6秒，接收完整流式响应（94行数据）\n→ 返回故障排查步骤并引用文档\n→ 总结操作建议：直接删除容器，重新创建并加版本号\n\n实际执行：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"容器挂了怎么办\"\n\n# 输出：\n[查询] 容器挂了怎么办\n.........................................................................\n# 完整答案\n如果容器挂了，你需要直接删除这个容器，然后重新创建一个新的容器，\n并且给新容器的名字后缀加上一个版本号[ID:0]。\n\n[引用文档]\n- 运维测试文档.doc\n--------------------------------------------------------------------------------\n[成功] 查询完成 (耗时: 6.19秒)"
      },
      {
        "title": "示例2: 技术知识查询",
        "body": "用户: Docker网络模式有哪些？\n→ 调用API查询\"Docker网络模式\"\n→ 等待流式响应\n→ 返回bridge、host、overlay等模式的说明\n→ 总结并简要说明各模式特点\n→ 如果知识库没相关内容，返回\"知识库中未找到您要的答案！\""
      },
      {
        "title": "示例3: 需要执行agent操作",
        "body": "用户: 怎么查看容器日志？\n→ 调用API查询\"查看容器日志\"\n→ API返回使用docker logs命令的方法\n→ 总结：使用`docker logs <container_name>`查看日志\n→ 建议用户提供容器名称，使用exec工具执行命令"
      },
      {
        "title": "超时配置说明",
        "body": "脚本已针对流式输出优化超时配置：\n\n参数值说明STREAM_NO_DATA_TIMEOUT15秒无新数据则认为完成（给流式生成足够时间）STREAM_MAX_TIMEOUT60秒最大总等待时间（防止无限等待）请求超时120秒HTTP连接超时\n\n如果超时：\n\n使用调试模式（-v）查看详细信息\n检查网络连接到RAGFlow服务器\n确认API服务状态"
      },
      {
        "title": "调试模式",
        "body": "使用-v或--verbose参数获取详细调试信息：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"测试问题\" -v\n\n调试信息包括：\n\n完整的请求URL和参数\n响应状态码\n数据接收过程\n处理的行数、数据块数量、耗时\n完整的JSON响应"
      },
      {
        "title": "注意事项",
        "body": "流式输出等待: RAGFlow使用流式输出，需要耐心等待，不要提前终止\n会话管理: conversation_id可以复用，保持对话上下文\n错误处理: 如果API调用失败，检查网络连接和API服务状态\n结果总结: 不要只是复制返回结果，要进行总结和提炼\n操作建议: 当API返回包含操作步骤时，转化为可执行的命令或明确指引\n安全性: API认证信息已固化在脚本中，注意不要泄露"
      },
      {
        "title": "扩展使用",
        "body": "对于需要agent执行的命令：\n\n明确告知用户可以执行的命令\n如果用户确认，使用exec工具执行\n反馈执行结果\n\n对于需要多次查询的复杂问题：\n\n拆分为多个子问题\n逐步查询和确认\n最后整合完整答案"
      },
      {
        "title": "API请求失败",
        "body": "# 测试连接\ncurl -I http://172.28.20.46:30001/v1/conversation/completion\n\n# 查看详细错误\npython3 scripts/query_ragflow.py \"测试\" -v"
      },
      {
        "title": "认证失败",
        "body": "检查Authorization token是否过期\n检查session cookie是否有效\n查看HTTP状态码（401/403表示权限问题）"
      },
      {
        "title": "返回\"知识库中未找到\"",
        "body": "知识库确实没有相关内容\n或者检索关键词匹配不上\n尝试更换问题描述方式"
      }
    ],
    "body": "RAGFlow知识库问答Skill\n概述\n\n此skill通过调用RAGFlow知识库API，为用户提供智能问答和操作指导。API使用流式输出（Stream）方式返回结果，需要耐心等待完整响应生成（通常5-10秒）。\n\n工作流程\n步骤1: 识别问题类型\n\n判断用户的问题是否适合通过知识库查询：\n\n技术问题（容器、Docker、Kubernetes等）\n系统运维问题\n故障排查\n操作指导\n其他需要专业知识库的场景\n步骤2: 调用RAGFlow API\n\n使用scripts/query_ragflow.py脚本查询知识库：\n\n标准查询（适合正常使用）：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"用户的问题\"\n\n\n调试模式（查看详细信息）：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"用户的问题\" -v\n# 或\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"用户的问题\" --verbose\n\n步骤3: 等待流式响应\n\n重要提示：\n\nRAGFlow API使用流式输出，响应需要时间生成\n无新数据超时：15秒（给流式生成足够时间）\n最大总超时：60秒\n请求超时：120秒\n通常5-10秒能完成，复杂问题可能更久\n\n脚本会显示进度点（.）表示正在接收数据，请耐心等待。\n\n步骤4: 处理返回结果\n\nAPI返回结果包含：\n\n助手回复：完整的AI生成答案\n引用文档：知识库中相关的文档来源\n统计信息：处理行数、数据块数量、耗时\n步骤5: 总结和操作建议\n\n根据返回结果：\n\n直接回答: 如果是简单问题，直接总结答案\n操作指导: 如果问题涉及具体操作（如容器挂了），提供步骤化的操作建议\n建议执行agent操作: 如果建议使用其他agent工具，明确指出\nAPI配置\n\n基本信息:\n\nAPI地址: http://172.28.20.46:30001/v1/conversation/completion\n认证方式: Bearer token + Cookie session\n输出方式: Server-Sent Events (SSE) 流式输出\n\n请求格式:\n\n方法: POST\nContent-Type: application/json\n\n关键参数:\n\nconversation_id: 会话ID（使用固定ID保持对话上下文）\nmessages: 对话历史数组，每个消息包含：\nrole: \"user\" 或 \"assistant\"\ncontent: 消息内容\nid: 消息唯一标识\n使用示例\n示例1: 容器故障排查\n用户: 容器挂了怎么办\n→ 调用API查询\"容器挂了怎么办\"\n→ 等待约6秒，接收完整流式响应（94行数据）\n→ 返回故障排查步骤并引用文档\n→ 总结操作建议：直接删除容器，重新创建并加版本号\n\n\n实际执行：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"容器挂了怎么办\"\n\n# 输出：\n[查询] 容器挂了怎么办\n.........................................................................\n# 完整答案\n如果容器挂了，你需要直接删除这个容器，然后重新创建一个新的容器，\n并且给新容器的名字后缀加上一个版本号[ID:0]。\n\n[引用文档]\n- 运维测试文档.doc\n--------------------------------------------------------------------------------\n[成功] 查询完成 (耗时: 6.19秒)\n\n示例2: 技术知识查询\n用户: Docker网络模式有哪些？\n→ 调用API查询\"Docker网络模式\"\n→ 等待流式响应\n→ 返回bridge、host、overlay等模式的说明\n→ 总结并简要说明各模式特点\n→ 如果知识库没相关内容，返回\"知识库中未找到您要的答案！\"\n\n示例3: 需要执行agent操作\n用户: 怎么查看容器日志？\n→ 调用API查询\"查看容器日志\"\n→ API返回使用docker logs命令的方法\n→ 总结：使用`docker logs <container_name>`查看日志\n→ 建议用户提供容器名称，使用exec工具执行命令\n\n超时配置说明\n\n脚本已针对流式输出优化超时配置：\n\n参数\t值\t说明\nSTREAM_NO_DATA_TIMEOUT\t15秒\t无新数据则认为完成（给流式生成足够时间）\nSTREAM_MAX_TIMEOUT\t60秒\t最大总等待时间（防止无限等待）\n请求超时\t120秒\tHTTP连接超时\n\n如果超时：\n\n使用调试模式（-v）查看详细信息\n检查网络连接到RAGFlow服务器\n确认API服务状态\n调试模式\n\n使用-v或--verbose参数获取详细调试信息：\n\npython3 /home/onestack/.openclaw/workspace/ragflow-kb/scripts/query_ragflow.py \"测试问题\" -v\n\n\n调试信息包括：\n\n完整的请求URL和参数\n响应状态码\n数据接收过程\n处理的行数、数据块数量、耗时\n完整的JSON响应\n注意事项\n流式输出等待: RAGFlow使用流式输出，需要耐心等待，不要提前终止\n会话管理: conversation_id可以复用，保持对话上下文\n错误处理: 如果API调用失败，检查网络连接和API服务状态\n结果总结: 不要只是复制返回结果，要进行总结和提炼\n操作建议: 当API返回包含操作步骤时，转化为可执行的命令或明确指引\n安全性: API认证信息已固化在脚本中，注意不要泄露\n扩展使用\n\n对于需要agent执行的命令：\n\n明确告知用户可以执行的命令\n如果用户确认，使用exec工具执行\n反馈执行结果\n\n对于需要多次查询的复杂问题：\n\n拆分为多个子问题\n逐步查询和确认\n最后整合完整答案\n故障排查\nAPI请求失败\n# 测试连接\ncurl -I http://172.28.20.46:30001/v1/conversation/completion\n\n# 查看详细错误\npython3 scripts/query_ragflow.py \"测试\" -v\n\n认证失败\n检查Authorization token是否过期\n检查session cookie是否有效\n查看HTTP状态码（401/403表示权限问题）\n返回\"知识库中未找到\"\n知识库确实没有相关内容\n或者检索关键词匹配不上\n尝试更换问题描述方式"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/chenkun-nuaa/ck-rag-skill",
    "publisherUrl": "https://clawhub.ai/chenkun-nuaa/ck-rag-skill",
    "owner": "chenkun-nuaa",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ck-rag-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/ck-rag-skill",
    "agentUrl": "https://openagent3.xyz/skills/ck-rag-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ck-rag-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ck-rag-skill/agent.md"
  }
}