{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-xhs",
    "name": "小红书自动化",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/pearl799/openclaw-xhs",
    "canonicalUrl": "https://clawhub.ai/pearl799/openclaw-xhs",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-xhs",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-xhs",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "README_CN.md",
      "SKILL.md",
      "config.example.json",
      "install.sh",
      "scripts/configure_openclaw.py"
    ],
    "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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/openclaw-xhs"
    },
    "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/openclaw-xhs",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-xhs/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-xhs/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-xhs/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": "小红书自动化 (XHS)",
        "body": "重要：所有小红书操作必须使用 exec 工具执行以下命令，不要用 browser 工具打开网页。"
      },
      {
        "title": "环境变量",
        "body": "变量必填说明XHS_TOOLKIT_DIR是xhs-toolkit 项目路径（git clone https://github.com/pearl799/xhs-toolkit）IMAGE_API_KEY是图片生成 API Key（任意 OpenAI 兼容的图片生成服务）IMAGE_BASE_URL是图片生成 API Base URL（例如 https://openrouter.ai/api/v1/chat/completions）IMAGE_MODEL是图片生成模型名称（例如 google/gemini-3-pro-image-preview）OPENCLAW_GATEWAY_TOKEN否OpenClaw Gateway token（文案生成用，如果 gateway 开了 auth）XHS_DATA_DIR否数据目录，默认 ~/.openclaw/skills/xhs/data"
      },
      {
        "title": "命令",
        "body": "检查登录状态：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_status.py\n\n登录小红书（用户说\"登录小红书\"/\"xhs login\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_auth.py\n\n会在 Mac 桌面打开 Chrome，告知用户去扫码。\n\n发布笔记（用户说\"发小红书\"/\"发布笔记\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_publish.py --title \"标题\" --content \"正文\" --images \"/path/1.png,/path/2.png\" --topics \"话题1,话题2\"\n\n发布前先用 xhs_status.py 检查登录。--images 必须是本地文件路径，1-9 张。--dry-run 可验证不发布。\n\n爬取热点（用户说\"小红书热点\"/\"trending\"/\"今天什么热门\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_trending.py --category \"综合\" --limit 20\n\n支持 --keyword \"AI\" 搜索。分类：综合/时尚/美食/旅行/美妆/科技/健身/宠物/家居/教育。\n\nAI 生成内容（用户说\"生成小红书\"/\"帮我生成\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_generate_content.py --topic \"主题\" --style \"干货分享\" --image-count 4\n\n生成文案+配图。生成后发给用户预览，确认后再调 xhs_publish.py 发布。\n\n全自动流水线（用户说\"自动发布\"/\"全自动\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_auto_pipeline.py --mode preview\n\n热点→选题→生成→预览/发布。--mode auto 直接发布。\n\n所有脚本输出 JSON，解析 status 字段判断结果。MEDIA: 行表示附件图片。"
      },
      {
        "title": "注意事项",
        "body": "每个命令只需调用一次，等待结果即可，不要重复执行\n脚本输出的 JSON 是给你解析用的，转述关键信息给用户即可，不要原样转发\n生成内容后，把标题、正文、话题发给用户预览，图片用 MEDIA 行的路径作为附件\n不要在一次回复中发送多条消息，合并为一条"
      }
    ],
    "body": "小红书自动化 (XHS)\n\n重要：所有小红书操作必须使用 exec 工具执行以下命令，不要用 browser 工具打开网页。\n\n环境变量\n变量\t必填\t说明\nXHS_TOOLKIT_DIR\t是\txhs-toolkit 项目路径（git clone https://github.com/pearl799/xhs-toolkit）\nIMAGE_API_KEY\t是\t图片生成 API Key（任意 OpenAI 兼容的图片生成服务）\nIMAGE_BASE_URL\t是\t图片生成 API Base URL（例如 https://openrouter.ai/api/v1/chat/completions）\nIMAGE_MODEL\t是\t图片生成模型名称（例如 google/gemini-3-pro-image-preview）\nOPENCLAW_GATEWAY_TOKEN\t否\tOpenClaw Gateway token（文案生成用，如果 gateway 开了 auth）\nXHS_DATA_DIR\t否\t数据目录，默认 ~/.openclaw/skills/xhs/data\n命令\n\n检查登录状态：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_status.py\n\n\n登录小红书（用户说\"登录小红书\"/\"xhs login\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_auth.py\n\n\n会在 Mac 桌面打开 Chrome，告知用户去扫码。\n\n发布笔记（用户说\"发小红书\"/\"发布笔记\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_publish.py --title \"标题\" --content \"正文\" --images \"/path/1.png,/path/2.png\" --topics \"话题1,话题2\"\n\n\n发布前先用 xhs_status.py 检查登录。--images 必须是本地文件路径，1-9 张。--dry-run 可验证不发布。\n\n爬取热点（用户说\"小红书热点\"/\"trending\"/\"今天什么热门\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_trending.py --category \"综合\" --limit 20\n\n\n支持 --keyword \"AI\" 搜索。分类：综合/时尚/美食/旅行/美妆/科技/健身/宠物/家居/教育。\n\nAI 生成内容（用户说\"生成小红书\"/\"帮我生成\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_generate_content.py --topic \"主题\" --style \"干货分享\" --image-count 4\n\n\n生成文案+配图。生成后发给用户预览，确认后再调 xhs_publish.py 发布。\n\n全自动流水线（用户说\"自动发布\"/\"全自动\"时）：\n\nuv run --project $XHS_TOOLKIT_DIR {baseDir}/scripts/xhs_auto_pipeline.py --mode preview\n\n\n热点→选题→生成→预览/发布。--mode auto 直接发布。\n\n所有脚本输出 JSON，解析 status 字段判断结果。MEDIA: 行表示附件图片。\n\n注意事项\n每个命令只需调用一次，等待结果即可，不要重复执行\n脚本输出的 JSON 是给你解析用的，转述关键信息给用户即可，不要原样转发\n生成内容后，把标题、正文、话题发给用户预览，图片用 MEDIA 行的路径作为附件\n不要在一次回复中发送多条消息，合并为一条"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/pearl799/openclaw-xhs",
    "publisherUrl": "https://clawhub.ai/pearl799/openclaw-xhs",
    "owner": "pearl799",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-xhs",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-xhs",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-xhs/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-xhs/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-xhs/agent.md"
  }
}