{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ragtop-agent",
    "name": "Ragtop Agent",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/qbs784/ragtop-agent",
    "canonicalUrl": "https://clawhub.ai/qbs784/ragtop-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ragtop-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ragtop-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/workflow.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/ragtop-agent"
    },
    "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/ragtop-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/ragtop-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ragtop-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ragtop-agent/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": "ragtop-agent Skill",
        "body": "本 Skill 允许 AI 通过 curl 调用 RAGTOP 后端接口。AI 必须根据用户请求的性质，在“简单指令”与“深度调研”两种模式间切换。"
      },
      {
        "title": "Configuration",
        "body": "The following environment variables are required:\n\nRAGTOP_API_URL: RAGTOP API base URL. Defaults to http://10.71.10.71:9380 if not set.\nRAGTOP_API_TOKEN: Your RAGTOP API access token. Can be configured via the OpenClaw Web UI."
      },
      {
        "title": "1. 核心工具构建指南 (How to build curl)",
        "body": "在调用以下接口前，请确保已获取环境变量 ${RAGTOP_API_URL} 和 ${RAGTOP_API_TOKEN}。如果 ${RAGTOP_API_URL} 为空，请使用默认值 http://10.71.10.71:9380。"
      },
      {
        "title": "A. 列出知识库 (list_kb)",
        "body": "用于获取所有可用的 knowledge_id。\n\ncurl -L -X POST \"${RAGTOP_API_URL}/api/v1/ragtop/tool/list_kb\" \\\n     -H \"Authorization: Bearer ${RAGTOP_API_TOKEN}\" \\\n     -H \"Content-Type: application/json\""
      },
      {
        "title": "B. 列出文档 (list_doc)",
        "body": "用于获取特定知识库内的 doc_id 列表，以便缩小检索范围。\n\nPayload: {\"knowledge_id\": \"string\"}\n\ncurl -L -X POST \"${RAGTOP_API_URL}/api/v1/ragtop/tool/list_doc\" \\\n     -H \"Authorization: Bearer ${RAGTOP_API_TOKEN}\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\"knowledge_id\": \"YOUR_KB_ID\"}'"
      },
      {
        "title": "C. 内容检索 (retrieval)",
        "body": "用于执行语义搜索。支持单查询或多查询。\n\nPayload 关键参数:\n\nknowledge_id: 必填。\nquery: 字符串（单查询）。\nqueries: 字符串数组（多查询，推荐用于复杂任务）。\ndoc_ids: 数组（可选，限定文件范围）。\nretrieval_setting: {\"top_k\": 16, \"score_threshold\": 0.3}\n\ncurl -L -X POST \"${RAGTOP_API_URL}/api/v1/ragtop/tool/retrieval\" \\\n     -H \"Authorization: Bearer ${RAGTOP_API_TOKEN}\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\n       \"knowledge_id\": \"YOUR_KB_ID\",\n       \"queries\": [\"查询1\", \"查询2\"],\n       \"retrieval_setting\": {\"top_k\": 5}\n     }'"
      },
      {
        "title": "情况 A：简单指令 (Simple Instructions)",
        "body": "适用场景: 用户询问“有哪些知识库？”、“这个库里有哪些文件？”等管理类问题。\n执行逻辑:\n\n直接根据需求构建 list_kb 或 list_doc 的 curl 命令。\n将返回的 JSON 结果整理成易读的表格或列表告知用户。"
      },
      {
        "title": "情况 B：深度调研 (Deep Investigation / Agentic RAG)",
        "body": "适用场景: 用户提出具体业务问题、对比分析或需要跨文档总结。\n执行逻辑:\n\n参考 references/workflow.md 执行“分析-分解-检索-综合”流程。\n多步编排:\n\n第一步：调用 list_kb 确定相关的知识库 ID。\n第二步（可选）：调用 list_doc 锁定相关文件。\n第三步：构建包含多个改写问题的 retrieval 请求，利用多路召回提高准确率。\n第四步：根据检索到的多个 chunks 进行逻辑推理和引用标注。"
      },
      {
        "title": "3. 运行规范",
        "body": "严禁提及 ragflow，统一使用 ragtop。\n引用必填: 所有深度调研的回答必须注明引用的文档名称。\n错误处理: 如果 curl 返回非 SUCCESS，应检查 Token 有效性并告知用户。"
      }
    ],
    "body": "ragtop-agent Skill\n\n本 Skill 允许 AI 通过 curl 调用 RAGTOP 后端接口。AI 必须根据用户请求的性质，在“简单指令”与“深度调研”两种模式间切换。\n\nConfiguration\n\nThe following environment variables are required:\n\nRAGTOP_API_URL: RAGTOP API base URL. Defaults to http://10.71.10.71:9380 if not set.\nRAGTOP_API_TOKEN: Your RAGTOP API access token. Can be configured via the OpenClaw Web UI.\n1. 核心工具构建指南 (How to build curl)\n\n在调用以下接口前，请确保已获取环境变量 ${RAGTOP_API_URL} 和 ${RAGTOP_API_TOKEN}。如果 ${RAGTOP_API_URL} 为空，请使用默认值 http://10.71.10.71:9380。\n\nA. 列出知识库 (list_kb)\n\n用于获取所有可用的 knowledge_id。\n\ncurl -L -X POST \"${RAGTOP_API_URL}/api/v1/ragtop/tool/list_kb\" \\\n     -H \"Authorization: Bearer ${RAGTOP_API_TOKEN}\" \\\n     -H \"Content-Type: application/json\"\n\nB. 列出文档 (list_doc)\n\n用于获取特定知识库内的 doc_id 列表，以便缩小检索范围。\n\nPayload: {\"knowledge_id\": \"string\"}\ncurl -L -X POST \"${RAGTOP_API_URL}/api/v1/ragtop/tool/list_doc\" \\\n     -H \"Authorization: Bearer ${RAGTOP_API_TOKEN}\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\"knowledge_id\": \"YOUR_KB_ID\"}'\n\nC. 内容检索 (retrieval)\n\n用于执行语义搜索。支持单查询或多查询。\n\nPayload 关键参数:\nknowledge_id: 必填。\nquery: 字符串（单查询）。\nqueries: 字符串数组（多查询，推荐用于复杂任务）。\ndoc_ids: 数组（可选，限定文件范围）。\nretrieval_setting: {\"top_k\": 16, \"score_threshold\": 0.3}\ncurl -L -X POST \"${RAGTOP_API_URL}/api/v1/ragtop/tool/retrieval\" \\\n     -H \"Authorization: Bearer ${RAGTOP_API_TOKEN}\" \\\n     -H \"Content-Type: application/json\" \\\n     -d '{\n       \"knowledge_id\": \"YOUR_KB_ID\",\n       \"queries\": [\"查询1\", \"查询2\"],\n       \"retrieval_setting\": {\"top_k\": 5}\n     }'\n\n2. 任务分类处理逻辑\n情况 A：简单指令 (Simple Instructions)\n\n适用场景: 用户询问“有哪些知识库？”、“这个库里有哪些文件？”等管理类问题。 执行逻辑:\n\n直接根据需求构建 list_kb 或 list_doc 的 curl 命令。\n将返回的 JSON 结果整理成易读的表格或列表告知用户。\n情况 B：深度调研 (Deep Investigation / Agentic RAG)\n\n适用场景: 用户提出具体业务问题、对比分析或需要跨文档总结。 执行逻辑:\n\n参考 references/workflow.md 执行“分析-分解-检索-综合”流程。\n多步编排:\n第一步：调用 list_kb 确定相关的知识库 ID。\n第二步（可选）：调用 list_doc 锁定相关文件。\n第三步：构建包含多个改写问题的 retrieval 请求，利用多路召回提高准确率。\n第四步：根据检索到的多个 chunks 进行逻辑推理和引用标注。\n3. 运行规范\n严禁提及 ragflow，统一使用 ragtop。\n引用必填: 所有深度调研的回答必须注明引用的文档名称。\n错误处理: 如果 curl 返回非 SUCCESS，应检查 Token 有效性并告知用户。"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/qbs784/ragtop-agent",
    "publisherUrl": "https://clawhub.ai/qbs784/ragtop-agent",
    "owner": "qbs784",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ragtop-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/ragtop-agent",
    "agentUrl": "https://openagent3.xyz/skills/ragtop-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ragtop-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ragtop-agent/agent.md"
  }
}