{
  "schemaVersion": "1.0",
  "item": {
    "slug": "glm-understand-image",
    "name": "glm-understand-image",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Thincher/glm-understand-image",
    "canonicalUrl": "https://clawhub.ai/Thincher/glm-understand-image",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/glm-understand-image",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=glm-understand-image",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "_meta.json",
      "SKILL.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": "2026-05-07T17:22:31.273Z",
      "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/glm-understand-image"
    },
    "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/glm-understand-image",
    "agentPageUrl": "https://openagent3.xyz/skills/glm-understand-image/agent",
    "manifestUrl": "https://openagent3.xyz/skills/glm-understand-image/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/glm-understand-image/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": "glm-understand-image",
        "body": "使用 GLM 视觉 MCP 服务器进行图像理解和分析。"
      },
      {
        "title": "步骤 1: 检查并安装依赖",
        "body": "1.1 检查 mcporter 是否可用\n\nnpx -y mcporter --version\n\n如果命令返回成功，说明 mcporter 可用，跳到步骤 2。\n\nmcporter 可以直接通过 npx 使用，无需安装。"
      },
      {
        "title": "步骤 2: 检查 API Key 配置",
        "body": "cat ~/.openclaw/config/glm.json 2>/dev/null | python3 -c \"import json,sys; d=json.load(sys.stdin); print(d.get('api_key', ''))\"\n\n如果返回非空的 API Key，跳到步骤 4。"
      },
      {
        "title": "步骤 3: 配置 API Key（如果未配置）",
        "body": "3.2 如果没有找到 Key，向用户索要\n\n询问用户提供智谱 API Key。\n\n如果用户没有智谱 API Key，可以访问 https://www.bigmodel.cn/glm-coding?ic=OOKF4KGGTW 购买。\n\n3.3 保存 API Key\n\nmkdir -p ~/.openclaw/config\ncat > ~/.openclaw/config/glm.json << EOF\n{\n  \"api_key\": \"API密钥\"\n}\nEOF"
      },
      {
        "title": "步骤 4: 添加 MCP 服务器",
        "body": "使用 mcporter 添加 GLM 视觉 MCP 服务器：\n\nmcporter config add glm-vision \\\n  --command \"npx -y @z_ai/mcp-server\" \\\n  --env Z_AI_API_KEY=\"your-key\" \\\n  --env Z_AI_MODE=\"ZHIPU\" \\\n  --env HOME=\"$PWD\"\n\n注意：将 your-key 替换为实际的智谱 API Key。HOME 环境变量设置为当前工作目录以避免日志文件权限问题。"
      },
      {
        "title": "步骤 5: 测试连接",
        "body": "mcporter list\n\n确认 glm-vision 服务器已成功添加。"
      },
      {
        "title": "步骤 6: 使用 MCP 处理图像",
        "body": "6.1 准备图片\n\n将图片放到可访问路径，例如：\n\n~/.openclaw/workspace/images/图片名.jpg\n或者使用 URL\n\n6.2 使用 mcporter 调用 MCP 工具\n\n使用 mcporter 调用 MCP 服务：\n\nmcporter call glm-vision.analyze_image prompt=\"<对图片的提问>\" image_source=\"<图片路径或URL>\"\n\n示例：\n\n# 描述图片内容\nmcporter call glm-vision.analyze_image prompt=\"详细描述这张图片的内容\" image_source=\"~/image.jpg\"\n\n# 使用 URL\nmcporter call glm-vision.analyze_image prompt=\"这张图片展示了什么？\" image_source=\"https://example.com/image.jpg\"\n\n# 提取图片中的文字\nmcporter call glm-vision.extract_text_from_screenshot image_source=\"~/screenshot.png\"\n\n# 诊断错误截图\nmcporter call glm-vision.diagnose_error_screenshot prompt=\"分析这个错误\" image_source=\"~/error.png\"\n\n6.3 API 参数说明\n\n参数说明类型image_source图片路径或 URLstring (必填)prompt对图片的提问string (必填)"
      },
      {
        "title": "支持的工具",
        "body": "重要提示：如果出现问题以官方说明为准\n官方版说明 ： https://docs.bigmodel.cn/cn/coding-plan/mcp/vision-mcp-server\n\nGLM 视觉 MCP 服务器提供以下工具：\n\nui_to_artifact - 将 UI 截图转换为代码、提示词、设计规范或自然语言描述\nextract_text_from_screenshot - 使用先进的 OCR 能力从截图中提取和识别文字\ndiagnose_error_screenshot - 解析错误弹窗、堆栈和日志截图，给出定位与修复建议\nunderstand_technical_diagram - 针对架构图、流程图、UML、ER 图等技术图纸生成结构化解读\nanalyze_data_visualization - 阅读仪表盘、统计图表，提炼趋势、异常与业务要点\nui_diff_check - 对比两张 UI 截图，识别视觉差异和实现偏差\nanalyze_image - 通用图像理解能力，适配未被专项工具覆盖的视觉内容\nvideo_analysis - 支持 MP4/MOV/M4V 等格式的视频场景解析，抓取关键帧、事件与要点"
      },
      {
        "title": "MCP 配置",
        "body": "MCP 服务器名称：glm-vision\n\nMCP 服务器配置：@z_ai/mcp-server\n\n环境变量：\n\nZ_AI_API_KEY - 智谱 API Key（必需）\nZ_AI_MODE - 服务平台选择，默认为 ZHIPU"
      }
    ],
    "body": "glm-understand-image\n\n使用 GLM 视觉 MCP 服务器进行图像理解和分析。\n\n执行流程（首次需要安装，后续直接步骤6调用）\n步骤 1: 检查并安装依赖\n1.1 检查 mcporter 是否可用\nnpx -y mcporter --version\n\n\n如果命令返回成功，说明 mcporter 可用，跳到步骤 2。\n\nmcporter 可以直接通过 npx 使用，无需安装。\n\n步骤 2: 检查 API Key 配置\ncat ~/.openclaw/config/glm.json 2>/dev/null | python3 -c \"import json,sys; d=json.load(sys.stdin); print(d.get('api_key', ''))\"\n\n\n如果返回非空的 API Key，跳到步骤 4。\n\n步骤 3: 配置 API Key（如果未配置）\n3.2 如果没有找到 Key，向用户索要\n\n询问用户提供智谱 API Key。\n\n如果用户没有智谱 API Key，可以访问 https://www.bigmodel.cn/glm-coding?ic=OOKF4KGGTW 购买。\n\n3.3 保存 API Key\nmkdir -p ~/.openclaw/config\ncat > ~/.openclaw/config/glm.json << EOF\n{\n  \"api_key\": \"API密钥\"\n}\nEOF\n\n步骤 4: 添加 MCP 服务器\n\n使用 mcporter 添加 GLM 视觉 MCP 服务器：\n\nmcporter config add glm-vision \\\n  --command \"npx -y @z_ai/mcp-server\" \\\n  --env Z_AI_API_KEY=\"your-key\" \\\n  --env Z_AI_MODE=\"ZHIPU\" \\\n  --env HOME=\"$PWD\"\n\n\n注意：将 your-key 替换为实际的智谱 API Key。HOME 环境变量设置为当前工作目录以避免日志文件权限问题。\n\n步骤 5: 测试连接\nmcporter list\n\n\n确认 glm-vision 服务器已成功添加。\n\n步骤 6: 使用 MCP 处理图像\n6.1 准备图片\n\n将图片放到可访问路径，例如：\n\n~/.openclaw/workspace/images/图片名.jpg\n或者使用 URL\n6.2 使用 mcporter 调用 MCP 工具\n\n使用 mcporter 调用 MCP 服务：\n\nmcporter call glm-vision.analyze_image prompt=\"<对图片的提问>\" image_source=\"<图片路径或URL>\"\n\n\n示例：\n\n# 描述图片内容\nmcporter call glm-vision.analyze_image prompt=\"详细描述这张图片的内容\" image_source=\"~/image.jpg\"\n\n# 使用 URL\nmcporter call glm-vision.analyze_image prompt=\"这张图片展示了什么？\" image_source=\"https://example.com/image.jpg\"\n\n# 提取图片中的文字\nmcporter call glm-vision.extract_text_from_screenshot image_source=\"~/screenshot.png\"\n\n# 诊断错误截图\nmcporter call glm-vision.diagnose_error_screenshot prompt=\"分析这个错误\" image_source=\"~/error.png\"\n\n6.3 API 参数说明\n参数\t说明\t类型\nimage_source\t图片路径或 URL\tstring (必填)\nprompt\t对图片的提问\tstring (必填)\n支持的工具\n\n重要提示：如果出现问题以官方说明为准 官方版说明 ： https://docs.bigmodel.cn/cn/coding-plan/mcp/vision-mcp-server\n\nGLM 视觉 MCP 服务器提供以下工具：\n\nui_to_artifact - 将 UI 截图转换为代码、提示词、设计规范或自然语言描述\nextract_text_from_screenshot - 使用先进的 OCR 能力从截图中提取和识别文字\ndiagnose_error_screenshot - 解析错误弹窗、堆栈和日志截图，给出定位与修复建议\nunderstand_technical_diagram - 针对架构图、流程图、UML、ER 图等技术图纸生成结构化解读\nanalyze_data_visualization - 阅读仪表盘、统计图表，提炼趋势、异常与业务要点\nui_diff_check - 对比两张 UI 截图，识别视觉差异和实现偏差\nanalyze_image - 通用图像理解能力，适配未被专项工具覆盖的视觉内容\nvideo_analysis - 支持 MP4/MOV/M4V 等格式的视频场景解析，抓取关键帧、事件与要点\nMCP 配置\n\nMCP 服务器名称：glm-vision\n\nMCP 服务器配置：@z_ai/mcp-server\n\n环境变量：\n\nZ_AI_API_KEY - 智谱 API Key（必需）\nZ_AI_MODE - 服务平台选择，默认为 ZHIPU"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Thincher/glm-understand-image",
    "publisherUrl": "https://clawhub.ai/Thincher/glm-understand-image",
    "owner": "Thincher",
    "version": "1.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/glm-understand-image",
    "downloadUrl": "https://openagent3.xyz/downloads/glm-understand-image",
    "agentUrl": "https://openagent3.xyz/skills/glm-understand-image/agent",
    "manifestUrl": "https://openagent3.xyz/skills/glm-understand-image/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/glm-understand-image/agent.md"
  }
}