{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ms-qwen-vl",
    "name": "Ms Qwen Vl",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/crocketc/ms-qwen-vl",
    "canonicalUrl": "https://clawhub.ai/crocketc/ms-qwen-vl",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ms-qwen-vl",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ms-qwen-vl",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/api-guide.md",
      "references/models.md",
      "requirements.txt",
      "scripts/ms_qwen_vl.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": "2026-04-30T16:55:25.780Z",
      "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/ms-qwen-vl"
    },
    "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/ms-qwen-vl",
    "agentPageUrl": "https://openagent3.xyz/skills/ms-qwen-vl/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ms-qwen-vl/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ms-qwen-vl/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": "MS-Qwen-VL Skill",
        "body": "基于 ModelScope Qwen3-VL 系列模型的多模态视觉识别技能，使用 OpenAI SDK 兼容方式调用。"
      },
      {
        "title": "功能特点",
        "body": "OpenAI SDK 兼容：使用标准 OpenAI SDK 调用 API\n多种任务支持：图像描述、OCR、视觉问答、目标检测、图表解析\n双模型模式：默认快速模型（30B）+ 精细高精度模型（235B）\n灵活输入：支持本地图片和 URL"
      },
      {
        "title": "安装与配置",
        "body": "# 安装依赖\npip install -r requirements.txt\n\n# 配置 API Key\ncp .env.example .env\n\n编辑 .env 文件，填入从 https://modelscope.cn/my/myaccesstoken 获取的 API Key：\n\nMODELSCOPE_API_KEY=your_api_key_here"
      },
      {
        "title": "重要：处理本地图片",
        "body": "当用户提供本地图片路径时（如桌面截图），必须使用 Python 脚本处理：\n\npython scripts/ms_qwen_vl.py \"<图片路径>\" --task <任务类型>\n\n脚本会自动将本地文件转换为 ModelScope API 需要的 base64 格式。"
      },
      {
        "title": "处理 URL 图片",
        "body": "当用户提供网络 URL 时，同样使用上述命令，脚本会自动识别：\n\npython scripts/ms_qwen_vl.py \"<URL>\" --task <任务类型>"
      },
      {
        "title": "Claude Code 对话示例",
        "body": "场景 1：分析桌面截图\n\n用户: 请帮我描述这张图片 C:\\Users\\...\\Desktop\\screenshot.png\n助手: [执行] python scripts/ms_qwen_vl.py \"C:\\Users\\...\\Desktop\\screenshot.png\"\n\n场景 2：OCR 识别本地图片\n\n用户: 识别这张图中的文字: D:\\Documents\\invoice.jpg\n助手: [执行] python scripts/ms_qwen_vl.py \"D:\\Documents\\invoice.jpg\" --task ocr\n\n场景 3：分析网络图片\n\n用户: 分析这张图片 https://example.com/photo.jpg\n助手: [执行] python scripts/ms_qwen_vl.py \"https://example.com/photo.jpg\" --task describe\n\n场景 4：视觉问答\n\n用户: 这张图里有几个人？C:\\Users\\...\\Desktop\\photo.png\n助手: [执行] python scripts/ms_qwen_vl.py \"C:\\Users\\...\\Desktop\\photo.png\" --task ask --question \"图片里有几个人？\""
      },
      {
        "title": "任务类型对照",
        "body": "用户需求--task 参数描述图片内容describe识别文字/OCRocr回答关于图片的问题ask（需要 --question）检测物体detect解析图表chart"
      },
      {
        "title": "快速使用",
        "body": "# 图像描述（默认）\npython scripts/ms_qwen_vl.py image.jpg\n\n# OCR 文字识别\npython scripts/ms_qwen_vl.py image.jpg --task ocr\n\n# 视觉问答\npython scripts/ms_qwen_vl.py image.jpg --task ask --question \"图片里有什么？\"\n\n# 使用精细模式（235B 模型）\npython scripts/ms_qwen_vl.py image.jpg --task describe --precise\n\nPython 代码调用：\n\nfrom scripts.ms_qwen_vl import analyze_image\n\nresult = analyze_image(\"image.jpg\", task=\"ocr\")\nprint(result)"
      },
      {
        "title": "任务类型",
        "body": "任务参数说明图像描述describe详细描述图片内容（默认）OCR 识别ocr识别图片中的文字视觉问答ask回答关于图片的问题目标检测detect检测图片中的物体图表解析chart解析图表数据"
      },
      {
        "title": "环境变量",
        "body": "变量名说明MODELSCOPE_API_KEYAPI 密钥（必需）MODELSCOPE_MODEL默认模型（可选）MODELSCOPE_MODEL_PRECISE精细模式模型（可选）"
      },
      {
        "title": "scripts/",
        "body": "ms_qwen_vl.py - 核心解析脚本，提供 analyze_image() 统一接口"
      },
      {
        "title": "references/",
        "body": "api-guide.md - OpenAI SDK 兼容调用方式详细说明\nmodels.md - Qwen3-VL 系列模型及推荐使用场景"
      }
    ],
    "body": "MS-Qwen-VL Skill\n\n基于 ModelScope Qwen3-VL 系列模型的多模态视觉识别技能，使用 OpenAI SDK 兼容方式调用。\n\n功能特点\nOpenAI SDK 兼容：使用标准 OpenAI SDK 调用 API\n多种任务支持：图像描述、OCR、视觉问答、目标检测、图表解析\n双模型模式：默认快速模型（30B）+ 精细高精度模型（235B）\n灵活输入：支持本地图片和 URL\n安装与配置\n# 安装依赖\npip install -r requirements.txt\n\n# 配置 API Key\ncp .env.example .env\n\n\n编辑 .env 文件，填入从 https://modelscope.cn/my/myaccesstoken 获取的 API Key：\n\nMODELSCOPE_API_KEY=your_api_key_here\n\nClaude Code 使用方式\n重要：处理本地图片\n\n当用户提供本地图片路径时（如桌面截图），必须使用 Python 脚本处理：\n\npython scripts/ms_qwen_vl.py \"<图片路径>\" --task <任务类型>\n\n\n脚本会自动将本地文件转换为 ModelScope API 需要的 base64 格式。\n\n处理 URL 图片\n\n当用户提供网络 URL 时，同样使用上述命令，脚本会自动识别：\n\npython scripts/ms_qwen_vl.py \"<URL>\" --task <任务类型>\n\nClaude Code 对话示例\n\n场景 1：分析桌面截图\n\n用户: 请帮我描述这张图片 C:\\Users\\...\\Desktop\\screenshot.png\n助手: [执行] python scripts/ms_qwen_vl.py \"C:\\Users\\...\\Desktop\\screenshot.png\"\n\n\n场景 2：OCR 识别本地图片\n\n用户: 识别这张图中的文字: D:\\Documents\\invoice.jpg\n助手: [执行] python scripts/ms_qwen_vl.py \"D:\\Documents\\invoice.jpg\" --task ocr\n\n\n场景 3：分析网络图片\n\n用户: 分析这张图片 https://example.com/photo.jpg\n助手: [执行] python scripts/ms_qwen_vl.py \"https://example.com/photo.jpg\" --task describe\n\n\n场景 4：视觉问答\n\n用户: 这张图里有几个人？C:\\Users\\...\\Desktop\\photo.png\n助手: [执行] python scripts/ms_qwen_vl.py \"C:\\Users\\...\\Desktop\\photo.png\" --task ask --question \"图片里有几个人？\"\n\n任务类型对照\n用户需求\t--task 参数\n描述图片内容\tdescribe\n识别文字/OCR\tocr\n回答关于图片的问题\task（需要 --question）\n检测物体\tdetect\n解析图表\tchart\n快速使用\n# 图像描述（默认）\npython scripts/ms_qwen_vl.py image.jpg\n\n# OCR 文字识别\npython scripts/ms_qwen_vl.py image.jpg --task ocr\n\n# 视觉问答\npython scripts/ms_qwen_vl.py image.jpg --task ask --question \"图片里有什么？\"\n\n# 使用精细模式（235B 模型）\npython scripts/ms_qwen_vl.py image.jpg --task describe --precise\n\n\nPython 代码调用：\n\nfrom scripts.ms_qwen_vl import analyze_image\n\nresult = analyze_image(\"image.jpg\", task=\"ocr\")\nprint(result)\n\n任务类型\n任务\t参数\t说明\n图像描述\tdescribe\t详细描述图片内容（默认）\nOCR 识别\tocr\t识别图片中的文字\n视觉问答\task\t回答关于图片的问题\n目标检测\tdetect\t检测图片中的物体\n图表解析\tchart\t解析图表数据\n环境变量\n变量名\t说明\nMODELSCOPE_API_KEY\tAPI 密钥（必需）\nMODELSCOPE_MODEL\t默认模型（可选）\nMODELSCOPE_MODEL_PRECISE\t精细模式模型（可选）\nResources\nscripts/\n\nms_qwen_vl.py - 核心解析脚本，提供 analyze_image() 统一接口\n\nreferences/\n\napi-guide.md - OpenAI SDK 兼容调用方式详细说明 models.md - Qwen3-VL 系列模型及推荐使用场景"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/crocketc/ms-qwen-vl",
    "publisherUrl": "https://clawhub.ai/crocketc/ms-qwen-vl",
    "owner": "crocketc",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ms-qwen-vl",
    "downloadUrl": "https://openagent3.xyz/downloads/ms-qwen-vl",
    "agentUrl": "https://openagent3.xyz/skills/ms-qwen-vl/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ms-qwen-vl/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ms-qwen-vl/agent.md"
  }
}